1 VERITAS dataset description

Unlike the Eligibility or Health questionnaires, which can mostly be encoded as a flat table, the VERITAS questionnaire implicitly records a series of entities and their relationships:

  • Places: list of geocoded locations visited by participants, along with the following characteristics: category, name, visit frequency, transportation mode
  • Social contacts: people and/or groups frequented by participants
  • Relationships: between social contacts (who knows who / who belongs to which group) as well as between locations and social contacts (places visited along with whom)

The diagram below illustrates the various entities collected throught the VERITAS questionnaire:

VERITAS entities
VERITAS entities

New participants and returning participants are presented separately below, as they were presented two slightly different question flows.

2 Basic descriptive statistics for new participants

2.1 Section 1: Residence and Neighbourhood

2.1.1 Now, let’s start with your home. What is your address?

home_location <- locations[locations$location_category == 1, ]

## version ggmap
vic_aoi <- st_bbox(home_location)
names(vic_aoi) <- c("left", "bottom", "right", "top")
vic_aoi[["left"]] <- vic_aoi[["left"]] - .07
vic_aoi[["right"]] <- vic_aoi[["right"]] + .07
vic_aoi[["top"]] <- vic_aoi[["top"]] + .01
vic_aoi[["bottom"]] <- vic_aoi[["bottom"]] - .01

bm <- get_stadiamap(vic_aoi, zoom = 11, maptype = "stamen_toner_lite") %>%
  ggmap(extent = "device")
bm + geom_sf(data = st_jitter(home_location, .008), inherit.aes = FALSE, color = "blue", size = 1.8, alpha = .3) # see https://github.com/r-spatial/sf/issues/336

NB: Home locations have been randomly shifted from their original position to protect privacy.

# Number of participants by municipalites
home_by_municipalites <- st_join(home_location, municipalities["NAME"])
home_by_mun_cnt <- as.data.frame(home_by_municipalites) %>%
  group_by(NAME) %>%
  dplyr::count() %>%
  arrange(desc(n), NAME)
home_by_mun_cnt$Shape <- NULL
kable(home_by_mun_cnt, caption = "Number of participants by municipalities") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of participants by municipalities
NAME n
Victoria 63
Saanich 39
Esquimalt 7
Oak Bay 5
Colwood 3
Langford 3
View Royal 3
Central Saanich 2
New Songhees 1A 1

2.1.2 When did you move to your current address?

# N of addresses by date of move
year_of_move <- veritas_main[c("interact_id", "home_move_date")]
year_of_move$home_move_date <- year(ymd(year_of_move$home_move_date))
ggplot(data = year_of_move) +
  geom_histogram(aes(x = home_move_date))

# recode date of move
year_of_move$home_move_date_recode <- as.character(year_of_move$home_move_date)
year_of_move$home_move_date_recode[year_of_move$home_move_date <= 2005] <- "2005 - 2001"
year_of_move$home_move_date_recode[year_of_move$home_move_date <= 2000] <- "2000 - 1991"
year_of_move$home_move_date_recode[year_of_move$home_move_date <= 1990] <- paste("1990 -", min(year_of_move$home_move_date))

year_of_move_cnt <- year_of_move %>%
  group_by(home_move_date_recode) %>%
  dplyr::count() %>%
  arrange(desc(home_move_date_recode))
kable(year_of_move_cnt, caption = "Year of move to current address") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Year of move to current address
home_move_date_recode n
2019 15
2018 26
2017 14
2016 10
2015 10
2014 5
2013 6
2012 3
2011 1
2010 2
2009 5
2008 4
2007 3
2006 1
2005 - 2001 7
2000 - 1991 11
1990 - 1965 3

2.1.3 If you were asked to draw the boundaries of your neighbourhood, what would they be?

prn <- poly_geom[poly_geom$area_type == "neighborhood", ]

## version ggmap
bm + geom_sf(data = prn, inherit.aes = FALSE, fill = alpha("blue", 0.05), color = alpha("blue", 0.3))

# Min, max, median & mean area of PRN
prn$area_m2 <- st_area(prn$geom)
kable(t(as.matrix(summary(prn$area_m2))),
  caption = "Area (in square meters) of the perceived residential neighborhood",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Area (in square meters) of the perceived residential neighborhood
Min. 1st Qu. Median Mean 3rd Qu. Max.
24435.5 574578.1 1122532 2156111 2270551 41824885

NB only 118 valid neighborhoods were collected, as many participants struggled to draw polygons on the map.

2.1.4 How attached are you to your neighbourhood?

# extract and recode
.ngh_att <- veritas_main[veritas_main$neighbourhood_attach != 99, c("interact_id", "neighbourhood_attach")] %>% dplyr::rename(neighbourhood_attach_code = neighbourhood_attach)
.ngh_att$neighbourhood_attach <- factor(ifelse(.ngh_att$neighbourhood_attach_code == 1, "1 [Not attached at all]",
  ifelse(.ngh_att$neighbourhood_attach_code == 6, "6 [Very attached]",
    .ngh_att$neighbourhood_attach_code
  )
))

# histogram of attachment
ggplot(data = .ngh_att) +
  geom_histogram(aes(x = neighbourhood_attach), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "neighbourhood_attach")

.ngh_att_cnt <- .ngh_att %>%
  group_by(neighbourhood_attach) %>%
  dplyr::count() %>%
  arrange(neighbourhood_attach)
kable(.ngh_att_cnt, caption = "Neigbourhood attachment") %>% 
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Neigbourhood attachment
neighbourhood_attach n
1 [Not attached at all] 5
2 9
3 10
4 32
5 35
6 [Very attached] 32

2.1.5 On average, how many hours per day do you spend outside of your home?

# histogram of n hours out
ggplot(data = veritas_main) +
  geom_histogram(aes(x = hours_out))

# Min, max, median & mean hours/day out
kable(t(as.matrix(summary(veritas_main$hours_out))),
  caption = "Hours/day outside home",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Hours/day outside home
Min. 1st Qu. Median Mean 3rd Qu. Max.
1 8 10 9 11 14

2.1.6 Of this time spent outside your home, on average how many hours do you spend outside your neighbourhood?

# histogram of n hours out
ggplot(data = veritas_main) +
  geom_histogram(aes(x = hours_out_neighb))

# Min, max, median & mean hours/day out of neighborhood
kable(t(as.matrix(summary(veritas_main$hours_out_neighb))),
  caption = "Hours/day outside neighbourhood",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Hours/day outside neighbourhood
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 6 8 7.3 9 12

2.1.7 Are there one or more areas close to where you live that you tend to avoid because you do not feel safe there (for any reason)?

# extract and recode
.unsafe <- veritas_main[c("interact_id", "unsafe_area")] %>% dplyr::rename(unsafe_area_code = unsafe_area)
.unsafe$unsafe_area <- factor(ifelse(.unsafe$unsafe_area_code == 1, "1 [Yes]",
  ifelse(.unsafe$unsafe_area_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .unsafe) +
  geom_histogram(aes(x = unsafe_area), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "unsafe_area")

.unsafe_cnt <- .unsafe %>%
  group_by(unsafe_area) %>%
  dplyr::count() %>%
  arrange(unsafe_area)
kable(.unsafe_cnt, caption = "Unsafe areas") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Unsafe areas
unsafe_area n
1 [Yes] 22
2 [No] 104
# map
unsafe <- poly_geom[poly_geom$area_type == "unsafe area", ]

## version ggmap
bm + geom_sf(data = unsafe, inherit.aes = FALSE, fill = alpha("blue", 0.3), color = alpha("blue", 0.5))

# Min, max, median & mean area of PRN
unsafe$area_m2 <- st_area(unsafe$geom)
kable(t(as.matrix(summary(unsafe$area_m2))),
  caption = "Area (in square meters) of the perceived unsafe area",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Area (in square meters) of the perceived unsafe area
Min. 1st Qu. Median Mean 3rd Qu. Max.
11109.7 33768.7 94741.3 199977.2 248634.9 1499185

2.1.8 Do you spend the night somewhere other than your home at least once per week?

# extract and recode
.o_res <- veritas_main[c("interact_id", "other_resid")] %>% dplyr::rename(other_resid_code = other_resid)
.o_res$other_resid <- factor(ifelse(.o_res$other_resid_code == 1, "1 [Yes]",
  ifelse(.o_res$other_resid_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .o_res) +
  geom_histogram(aes(x = other_resid), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "other_resid")

.o_res_cnt <- .o_res %>%
  group_by(other_resid) %>%
  dplyr::count() %>%
  arrange(other_resid)
kable(.o_res_cnt, caption = "Other residence") %>% 
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Other residence
other_resid n
1 [Yes] 8
2 [No] 118

2.2 Section 2: Occupation

2.2.1 Are you currently working?

# extract and recode
.work <- veritas_main[c("interact_id", "working")] %>% dplyr::rename(working_code = working)
.work$working <- factor(ifelse(.work$working_code == 1, "1 [Yes]",
  ifelse(.work$working_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .work) +
  geom_histogram(aes(x = working), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "working")

.work_cnt <- .work %>%
  group_by(working) %>%
  dplyr::count() %>%
  arrange(working)
kable(.work_cnt, caption = "Currently working") %>% 
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Currently working
working n
1 [Yes] 114
2 [No] 12

2.2.2 Where do you work?

work_location <- locations[locations$location_category == 3, ]

bm + geom_sf(data = work_location, inherit.aes = FALSE, color = "blue", size = 1.8, alpha = .3)

2.2.3 On average, how many hours per week do you work?

# histogram of n hours out
ggplot(data = veritas_main[veritas_main$working == 1, ]) +
  geom_histogram(aes(x = work_hours))

# Min, max, median & mean hours/day out
kable(t(as.matrix(summary(veritas_main$work_hours[veritas_main$working == 1]))),
  caption = "Work hours/week",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Work hours/week
Min. 1st Qu. Median Mean 3rd Qu. Max.
7 35 38 36 40 60

2.2.4 Which of the following categories best describes the amount of physical activity required for your job?

# extract and recode
.work_pa <- veritas_main[veritas_main$working == 1, c("interact_id", "work_pa")] %>% dplyr::rename(work_pa_code = work_pa)
.work_pa$work_pa <- factor(ifelse(.work_pa$work_pa_code == 1, "1 [Mainly sitting with slight arm movements]",
  ifelse(.work_pa$work_pa_code == 2, "2 [Sitting and standing with some walking]",
    ifelse(.work_pa$work_pa_code == 3, "3 [Walking, with some handling of materials generally weighing less than 25 kg (55 lbs)]",
      ifelse(.work_pa$work_pa_code == 4, "4 [Walking and heavy manual work often requiring handling of materials weighing over 25 kg (50 lbs)]", "N/A")
    )
  )
))

# histogram of answers
ggplot(data = .work_pa) +
  geom_histogram(aes(x = work_pa), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "Physical activity at work")

.work_pa_cnt <- .work_pa %>%
  group_by(work_pa) %>%
  dplyr::count() %>%
  arrange(work_pa)
kable(.work_pa_cnt, caption = "Physical activity at work") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Physical activity at work
work_pa n
1 [Mainly sitting with slight arm movements] 57
2 [Sitting and standing with some walking] 44
3 [Walking, with some handling of materials generally weighing less than 25 kg (55 lbs)] 13

2.2.5 Are you currently a registered student?

# extract and recode
.study <- veritas_main[c("interact_id", "studying")] %>% dplyr::rename(studying_code = studying)
.study$studying <- factor(ifelse(.study$studying_code == 1, "1 [Yes]",
  ifelse(.study$studying_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .study) +
  geom_histogram(aes(x = studying), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "Studying")

.study_cnt <- .study %>%
  group_by(studying) %>%
  dplyr::count() %>%
  arrange(studying)
kable(.study_cnt, caption = "Currently studying") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Currently studying
studying n
1 [Yes] 11
2 [No] 115

2.2.6 Where do you study?

study_location <- locations[locations$location_category == 4, ]

bm + geom_sf(data = study_location, inherit.aes = FALSE, color = "blue", size = 1.8, alpha = .3)

2.2.7 On average, how many hours per week do you study?

# histogram of n hours out
ggplot(data = veritas_main[veritas_main$studying == 1, ]) +
  geom_histogram(aes(x = study_hours))

# Min, max, median & mean hours/day out
kable(t(as.matrix(summary(veritas_main$study_hours[veritas_main$studying == 1]))),
  caption = "study hours/week",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
study hours/week
Min. 1st Qu. Median Mean 3rd Qu. Max.
1 6 10 18.1 22.5 65

2.3 Section 3: Shopping activities

The following questions are used to generate the locations grouped into this section:

  1. Do you shop for groceries at a supermarket at least once per month?
  2. Do you shop at a public/farmer’s market at least once per month?
  3. Do you shop at a bakery at least once per month?
  4. Do you go to a specialty food store at least once per month? For example: a cheese shop, fruit and vegetable store, butcher’s shop, natural and health food store.
  5. Do you go to a convenience store at least once per month?
  6. Do you go to a liquor store at least once per month?
shop_lut <- data.frame(
  location_category_code = c(5, 6, 7, 8, 9, 10),
  location_category = factor(c(
    " 5 [Supermarket]",
    " 6 [Public/farmer’s market]",
    " 7 [Bakery]",
    " 8 [Specialty food store]",
    " 9 [Convenience store/Dépanneur]",
    "10 [Liquor store/SAQ]"
  ))
)
shop_location <- locations[locations$location_category %in% shop_lut$location_category_code, ] %>%
  dplyr::rename(location_category_code = location_category) %>%
  inner_join(shop_lut, by = "location_category_code")

# map
bm + geom_sf(data = shop_location, inherit.aes = FALSE, aes(color = location_category), size = 1.5, alpha = .3) +
  scale_color_brewer(palette = "Accent") +
  theme(legend.position = "bottom", legend.text = element_text(size = 8), legend.title = element_blank())

# compute number of shopping locations by category
ggplot(data = shop_location) +
  geom_histogram(aes(x = location_category), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "Shopping locations by categories")

.location_category_cnt <- as.data.frame(shop_location[c("location_category")]) %>%
  group_by(location_category) %>%
  dplyr::count() %>%
  arrange(location_category)
kable(.location_category_cnt, caption = "Shopping locations by categories") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Shopping locations by categories
location_category n
5 [Supermarket] 357
6 [Public/farmer’s market] 42
7 [Bakery] 66
8 [Specialty food store] 59
9 [Convenience store/Dépanneur] 27
10 [Liquor store/SAQ] 152
# compute statistics on shopping locations by participants and categories
# > one needs to account for participants who did not report location for some categories
.loc_iid_category_cnt <- as.data.frame(shop_location[c("interact_id", "location_category")]) %>%
  group_by(interact_id, location_category) %>%
  dplyr::count()

# (cont'd) simulate SQL JOIN TABLE ON TRUE to build list of all combination iid/shopping categ
.dummy <- data_frame(
  interact_id = character(),
  location_category = character()
)
for (iid in as.vector(veritas_main$interact_id)) {
  .dmy <- data_frame(
    interact_id = as.character(iid),
    location_category = shop_lut$location_category
  )
  .dummy <- rbind(.dummy, .dmy)
}

# (cont'd) find iid/categ combination without match in veritas locations
.no_shop_iid <- dplyr::setdiff(.dummy, .loc_iid_category_cnt[c("location_category", "interact_id")]) %>%
  mutate(n = 0)
.loc_iid_category_cnt <- bind_rows(.loc_iid_category_cnt, .no_shop_iid)

.location_category_cnt <- .loc_iid_category_cnt %>%
  group_by(location_category) %>%
  dplyr::summarise(min = min(n), mean = round(mean(n), 2), median = median(n), max = max(n)) %>%
  arrange(location_category)
kable(.location_category_cnt, caption = "Number of shopping locations by participant and category") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of shopping locations by participant and category
location_category min mean median max
5 [Supermarket] 0 2.83 3 5
6 [Public/farmer’s market] 0 0.33 0 5
7 [Bakery] 0 0.52 0 5
8 [Specialty food store] 0 0.47 0 5
9 [Convenience store/Dépanneur] 0 0.21 0 3
10 [Liquor store/SAQ] 0 1.21 1 5

2.4 Section 4: Services

The following questions are used to generate the locations grouped into this section:

  1. Where is the bank you go to most often located?
  2. Where is the hair salon or barber shop you go to most often?
  3. Where is the post office where you go to most often?
  4. Where is the drugstore you go to most often?
  5. If you need to visit a doctor or other healthcare provider, where do you go most often?
serv_lut <- data.frame(
  location_category_code = c(11, 12, 13, 14, 15),
  location_category = factor(c(
    "11 [Bank]",
    "12 [Hair salon/barbershop]",
    "13 [Post office]",
    "14 [Drugstore]",
    "15 [Doctor/healthcare provider]"
  ))
)
serv_location <- locations[locations$location_category %in% serv_lut$location_category_code, ] %>%
  dplyr::rename(location_category_code = location_category) %>%
  inner_join(serv_lut, by = "location_category_code")

# map
bm + geom_sf(data = serv_location, inherit.aes = FALSE, aes(color = location_category), size = 1.5, alpha = .3) +
  scale_color_brewer(palette = "Accent") +
  theme(legend.position = "bottom", legend.text = element_text(size = 8), legend.title = element_blank())

# compute number of shopping locations by category
ggplot(data = serv_location) +
  geom_histogram(aes(x = location_category), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "Service locations by categories")

.location_category_cnt <- as.data.frame(serv_location[c("location_category")]) %>%
  group_by(location_category) %>%
  dplyr::count() %>%
  arrange(location_category)
kable(.location_category_cnt, caption = "Shopping locations by categories") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Shopping locations by categories
location_category n
11 [Bank] 113
12 [Hair salon/barbershop] 85
13 [Post office] 78
14 [Drugstore] 98
15 [Doctor/healthcare provider] 138
# compute statistics on shopping locations by participants and categories
# > one needs to account for participants who did not report location for some categories
.loc_iid_category_cnt <- as.data.frame(serv_location[c("interact_id", "location_category")]) %>%
  group_by(interact_id, location_category) %>%
  dplyr::count()

# (cont'd) simulate SQL JOIN TABLE ON TRUE
.dummy <- data_frame(
  interact_id = character(),
  location_category = character()
)
for (iid in as.vector(veritas_main$interact_id)) {
  .dmy <- data_frame(
    interact_id = as.character(iid),
    location_category = serv_lut$location_category
  )
  .dummy <- rbind(.dummy, .dmy)
}

# (cont'd) find iid/categ combination without match in veritas locations
.no_serv_iid <- dplyr::setdiff(.dummy, .loc_iid_category_cnt[c("location_category", "interact_id")]) %>%
  mutate(n = 0)
.loc_iid_category_cnt <- bind_rows(.loc_iid_category_cnt, .no_serv_iid)

.location_category_cnt <- .loc_iid_category_cnt %>%
  group_by(location_category) %>%
  dplyr::summarise(min = min(n), mean = round(mean(n), 2), median = median(n), max = max(n)) %>%
  arrange(location_category)
kable(.location_category_cnt, caption = "Number of shopping locations by participant and category") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of shopping locations by participant and category
location_category min mean median max
11 [Bank] 0 0.90 1 1
12 [Hair salon/barbershop] 0 0.67 1 1
13 [Post office] 0 0.62 1 1
14 [Drugstore] 0 0.78 1 1
15 [Doctor/healthcare provider] 0 1.10 1 5

2.5 Section 5: Transportation

2.5.1 Do you use public transit from your home?

# extract and recode
.transp <- veritas_main[c("interact_id", "public_transit")] %>% dplyr::rename(public_transit_code = public_transit)
.transp$public_transit <- factor(ifelse(.transp$public_transit_code == 1, "1 [Yes]",
  ifelse(.transp$public_transit_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .transp) +
  geom_histogram(aes(x = public_transit), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "public_transit")

.transp_cnt <- .transp %>%
  group_by(public_transit) %>%
  dplyr::count() %>%
  arrange(public_transit)
kable(.transp_cnt, caption = "Use public transit") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Use public transit
public_transit n
1 [Yes] 64
2 [No] 62

2.5.2 Where are the public transit stops that you access from your home?

transp_location <- locations[locations$location_category == 16, ]

bm + geom_sf(data = transp_location, inherit.aes = FALSE, color = "blue", size = 1.8, alpha = .3)

2.6 Section 6: Leisure activities

The following questions are used to generate the locations grouped into this section:

  1. Do you participate in any (individual or group) sports or leisure-time physical activities at least once per month?
  2. Do you visit a park at least once per month?
  3. Do you participate in or attend as a spectator a cultural or non-sport leisure activity at least once per month? For example: singing or drawing lessons, book or poker club, concert or play.
  4. Do you volunteer at least once per month?
  5. Do you engage in any religious or spiritual activities at least once per month?
  6. Do you go to a restaurant, café, bar or other food and drink establishment at least once per month?
  7. Do you get take-out food at least once per month?
  8. Do you regularly go for walks?
leisure_lut <- data.frame(
  location_category_code = c(17, 18, 19, 20, 21, 22, 23, 24),
  location_category = factor(c(
    "17 [Leisure-time physical activity]",
    "18 [Park]",
    "19 [Cultural activity]",
    "20 [Volunteering place]",
    "21 [Religious or spiritual activity]",
    "22 [Restaurant, café, bar, etc. ]",
    "23 [Take-out]",
    "24 [Walk]"
  ))
)
leisure_location <- locations[locations$location_category %in% leisure_lut$location_category_code, ] %>%
  dplyr::rename(location_category_code = location_category) %>%
  inner_join(leisure_lut, by = "location_category_code")

# map
bm + geom_sf(data = leisure_location, inherit.aes = FALSE, aes(color = location_category), size = 1.5, alpha = .3) +
  scale_color_brewer(palette = "Accent") +
  theme(legend.position = "bottom", legend.text = element_text(size = 8), legend.title = element_blank())

# compute number of shopping locations by category
ggplot(data = leisure_location) +
  geom_histogram(aes(x = location_category), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "Leisure locations by categories")

.location_category_cnt <- as.data.frame(leisure_location[c("location_category")]) %>%
  group_by(location_category) %>%
  dplyr::count() %>%
  arrange(location_category)
kable(.location_category_cnt, caption = "Shopping locations by categories") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Shopping locations by categories
location_category n
17 [Leisure-time physical activity] 162
18 [Park] 272
19 [Cultural activity] 54
20 [Volunteering place] 60
21 [Religious or spiritual activity] 14
22 [Restaurant, café, bar, etc. ] 285
23 [Take-out] 94
24 [Walk] 178
# compute statistics on shopping locations by participants and categories
# > one needs to account for participants who did not report location for some categories
.loc_iid_category_cnt <- as.data.frame(leisure_location[c("interact_id", "location_category")]) %>%
  group_by(interact_id, location_category) %>%
  dplyr::count()

# (cont'd) simulate SQL JOIN TABLE ON TRUE
.dummy <- data_frame(
  interact_id = character(),
  location_category = character()
)
for (iid in as.vector(veritas_main$interact_id)) {
  .dmy <- data_frame(
    interact_id = as.character(iid),
    location_category = leisure_lut$location_category
  )
  .dummy <- rbind(.dummy, .dmy)
}

# (cont'd) find iid/categ combination without match in veritas locations
.no_leisure_iid <- dplyr::setdiff(.dummy, .loc_iid_category_cnt[c("location_category", "interact_id")]) %>%
  mutate(n = 0)

.loc_iid_category_cnt <- bind_rows(.loc_iid_category_cnt, .no_leisure_iid)

.location_category_cnt <- .loc_iid_category_cnt %>%
  group_by(location_category) %>%
  dplyr::summarise(min = min(n), mean = round(mean(n), 2), median = median(n), max = max(n)) %>%
  arrange(location_category)
kable(.location_category_cnt, caption = "Number of leisure locations by participant and category") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of leisure locations by participant and category
location_category min mean median max
17 [Leisure-time physical activity] 0 1.29 1 5
18 [Park] 0 2.16 2 5
19 [Cultural activity] 0 0.43 0 4
20 [Volunteering place] 0 0.48 0 5
21 [Religious or spiritual activity] 0 0.11 0 2
22 [Restaurant, café, bar, etc. ] 0 2.26 2 5
23 [Take-out] 0 0.75 0 5
24 [Walk] 0 1.41 1 5

2.7 Section 7: Other places/activities

2.7.1 Are there other places that you go to at least once per month that we have not mentioned? For example: a mall, a daycare, a hardware store, or a community center.

# extract and recode
.other <- veritas_main[c("interact_id", "other")] %>% dplyr::rename(other_code = other)
.other$other <- factor(ifelse(.other$other_code == 1, "1 [Yes]",
  ifelse(.other$other_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .other) +
  geom_histogram(aes(x = other), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "other")

.other_cnt <- .other %>%
  group_by(other) %>%
  dplyr::count() %>%
  arrange(other)
kable(.other_cnt, caption = "Other places") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Other places
other n
1 [Yes] 43
2 [No] 83

2.7.2 Can you locate this place?

other_location <- locations[locations$location_category == 25, ]

bm + geom_sf(data = other_location, inherit.aes = FALSE, color = "blue", size = 1.8, alpha = .3)

2.8 Section 8: Areas of change

Participants were not asked for areas of change in Victoria

2.9 Section 9: Social contact

2.9.1 Do you visit anyone at his or her home at least once per month?

# extract and recode
.visiting <- veritas_main[c("interact_id", "visiting")] %>% dplyr::rename(visiting_code = visiting)
.visiting$visiting <- factor(ifelse(.visiting$visiting_code == 1, "1 [Yes]",
  ifelse(.visiting$visiting_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .visiting) +
  geom_histogram(aes(x = visiting), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "visiting")

.visiting_cnt <- .visiting %>%
  group_by(visiting) %>%
  dplyr::count() %>%
  arrange(visiting)
kable(.visiting_cnt, caption = "Social contact") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Social contact
visiting n
1 [Yes] 70
2 [No] 56

2.9.2 Great, we are almost done completing this questionnaire. You have documented all your activity places on a map, and specified with whom you generally do these activities. These last few questions concern the people you documented earlier.

# compute statistics on groups / participant
# > one needs to account for participants who did not report any group
.gr_iid_cnt <- as.data.frame(group[c("interact_id")]) %>%
  group_by(interact_id) %>%
  dplyr::count()

# (cont'd) find iid combination without match in veritas group
.no_gr_iid <- anti_join(veritas_main[c("interact_id")], .gr_iid_cnt, by = "interact_id") %>%
  mutate(n = 0)
.gr_iid_cnt <- bind_rows(.gr_iid_cnt, .no_gr_iid)

kable(t(as.matrix(summary(.gr_iid_cnt$n))), caption = "Number of groups per participant") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of groups per participant
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 1 1.603175 2 7
# compute statistics on people / participant
# > one needs to account for participants who did not report any group
.pl_iid_cnt <- as.data.frame(people[c("interact_id")]) %>%
  group_by(interact_id) %>%
  dplyr::count()

# (cont'd) find iid combination without match in veritas group
.no_pl_iid <- anti_join(veritas_main[c("interact_id")], .pl_iid_cnt, by = "interact_id") %>%
  mutate(n = 0)
.pl_iid_cnt <- bind_rows(.pl_iid_cnt, .no_pl_iid)

kable(t(as.matrix(summary(.pl_iid_cnt$n))), caption = "Number of people per participant") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of people per participant
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 2 4 4.976191 7 22
# histogram
.sc_iid_cnt <- .pl_iid_cnt %>% mutate(soc_type = "people")
.sc_iid_cnt <- .gr_iid_cnt %>%
  mutate(soc_type = "group") %>%
  bind_rows(.sc_iid_cnt)

ggplot(data = .sc_iid_cnt) +
  geom_histogram(aes(x = n, y = stat(count), fill = soc_type), position = "dodge") +
  labs(x = "Social network size by element type", fill = element_blank())

2.9.2.1 Among these people, who do you discuss important matters with?

# extract number of important people / participant
.n_important <- important %>% dplyr::count(interact_id)
.n_people <- people %>% dplyr::count(interact_id)

.n_people_imp <- left_join(veritas_main[c("interact_id")], .n_people, by = "interact_id") %>%
  left_join(.n_important, by = "interact_id") %>%
  mutate_all(~ replace(., is.na(.), 0)) %>%
  dplyr::rename(n_people = n.x, n_important = n.y) %>%
  mutate(pct = 100 * n_important / n_people)

kable(t(as.matrix(summary(.n_people_imp$n_important))),
  caption = "Number of important people per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of important people per participant
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 1 2 2.9 4 11
kable(t(as.matrix(summary(.n_people_imp$pct))),
  caption = "% of important people among social contact per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
% of important people among social contact per participant
Min. 1st Qu. Median Mean 3rd Qu. Max. NA’s
0 48.3 66.7 65.9 100 100 7

NB In Victoria, 3 participants also listed groups in this catagory, hence the max value over 100%.

2.9.2.2 Among these people, who do you like to socialize with?

# extract number of important people / participant
.n_socialize <- socialize %>% dplyr::count(interact_id)
.n_people <- people %>% dplyr::count(interact_id)

.n_people_soc <- left_join(veritas_main[c("interact_id")], .n_people, by = "interact_id") %>%
  left_join(.n_socialize, by = "interact_id") %>%
  mutate_all(~ replace(., is.na(.), 0)) %>%
  dplyr::rename(n_people = n.x, n_socialize = n.y) %>%
  mutate(pct = 100 * n_socialize / n_people)

kable(t(as.matrix(summary(.n_people_soc$n_socialize))),
  caption = "Number of people with whom to socialize per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of people with whom to socialize per participant
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 1 3 3.7 6 14
kable(t(as.matrix(summary(.n_people_soc$pct))),
  caption = "% of people with whom to  socialize among social contact per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
% of people with whom to socialize among social contact per participant
Min. 1st Qu. Median Mean 3rd Qu. Max. NA’s
0 54.5 100 77.5 100 100 7

NB In Victoria, 6 participants also listed groups in this catagory, hence the max value over 100%.

2.9.2.3 Among these people, who do you meet often with but do not necessarily feel close to?

# extract number of important people / participant
.n_not_close <- not_close %>% dplyr::count(interact_id)
.n_people <- people %>% dplyr::count(interact_id)

.n_people_not_close <- left_join(veritas_main[c("interact_id")], .n_people, by = "interact_id") %>%
  left_join(.n_not_close, by = "interact_id") %>%
  mutate_all(~ replace(., is.na(.), 0)) %>%
  dplyr::rename(n_people = n.x, n_not_close = n.y) %>%
  mutate(pct = 100 * n_not_close / n_people)

kable(t(as.matrix(summary(.n_people_not_close$n_not_close))),
  caption = "Number of not so close people per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of not so close people per participant
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 0 0.9 1 6
kable(t(as.matrix(summary(.n_people_not_close$pct))),
  caption = "% of not so close people among social contact per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
% of not so close people among social contact per participant
Min. 1st Qu. Median Mean 3rd Qu. Max. NA’s
0 0 0 16.8 27.9 100 7

2.9.2.4 Among these people, who knows whom?

# extract number of who knows who relationships
.n_relat <- relationship %>%
  filter(relationship_type == 1) %>%
  dplyr::count(interact_id)
.n_people <- people %>% dplyr::count(interact_id)

.n_people_relat <- left_join(veritas_main[c("interact_id")], .n_people, by = "interact_id") %>%
  left_join(.n_relat, by = "interact_id") %>%
  mutate_all(~ replace(., is.na(.), 0)) %>%
  dplyr::rename(n_people = n.x, n_relat = n.y) %>%
  mutate(pct = 100 * n_relat * 2 / (n_people * (n_people - 1))) # potential number of relationships = N x (N -1) / 2

kable(t(as.matrix(summary(.n_people_relat$n_relat))),
  caption = "Number of relationships « who knows who » per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of relationships « who knows who » per participant
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0.2 4.5 10.5 14 123
kable(t(as.matrix(summary(.n_people_relat$pct))),
  caption = "% of relationships « who knows who » per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
% of relationships « who knows who » per participant
Min. 1st Qu. Median Mean 3rd Qu. Max. NA’s
0 52 76.2 73.4 100 100 31

2.10 Derived metrics

2.10.1 Transportation mode preferences

Based on the answers to the question Usually, how do you go there? (Check all that apply.).

# code  en
# 1 By car and you drive
# 2 By car and someone else drives
# 3 By taxi/Uber
# 4 On foot
# 5 By bike
# 6 By bus
# 7 By subway
# 8 By train
# 99    Other

loc_labels <- data.frame(location_category = c(2:26), description = c(
  " 2 [Other residence]",
  " 3 [Work]",
  " 4 [School/College/University]",
  " 5 [Supermarket]",
  " 6 [Public/farmer’s market]",
  " 7 [Bakery]",
  " 8 [Specialty food store]",
  " 9 [Convenience store/Dépanneur]",
  "10 [Liquor store/SAQ]",
  "11 [Bank]",
  "12 [Hair salon/barbershop]",
  "13 [Post office]",
  "14 [Drugstore]",
  "15 [Doctor/healthcare provider]",
  "16 [Public transit stop]",
  "17 [Leisure-time physical activity]",
  "18 [Park]",
  "19 [Cultural activity]",
  "20 [Volunteering place]",
  "21 [Religious/spiritual activity]",
  "22 [Restaurant, café, bar, etc.]",
  "23 [Take-out]",
  "24 [Walk]",
  "25 [Other place]",
  "26 [Social contact residence]"
))

# extract and summary stats
.tm <- locations %>%
  st_set_geometry(NULL) %>%
  filter(location_category != 1) %>%
  left_join(loc_labels)

.tm_grouped <- .tm %>%
  group_by(description) %>%
  dplyr::summarise(
    N = n(), "By car (driver)" = sum(location_tmode_1),
    "By car (passenger)" = sum(location_tmode_2),
    "By taxi/Uber" = sum(location_tmode_3),
    "On foot" = sum(location_tmode_4),
    "By bike" = sum(location_tmode_5),
    "By bus" = sum(location_tmode_6),
    "By train" = sum(location_tmode_7),
    "Other" = sum(location_tmode_99)
  )

kable(.tm_grouped, caption = "Transportation mode preferences") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Transportation mode preferences
description N By car (driver) By car (passenger) By taxi/Uber On foot By bike By bus By train Other
2 [Other residence] 9 3 4 0 1 6 1 0 1
3 [Work] 146 28 5 0 26 115 24 0 9
4 [School/College/University] 14 1 0 0 3 9 8 0 2
5 [Supermarket] 357 190 39 0 129 182 9 0 2
6 [Public/farmer’s market] 42 16 4 0 17 23 1 0 1
7 [Bakery] 66 18 3 0 32 31 2 0 1
8 [Specialty food store] 59 18 6 0 28 31 4 0 1
9 [Convenience store/Dépanneur] 27 7 1 0 16 8 1 0 1
10 [Liquor store/SAQ] 152 61 7 0 68 77 4 0 0
11 [Bank] 113 38 4 0 48 60 7 0 1
12 [Hair salon/barbershop] 85 24 0 0 37 52 6 0 0
13 [Post office] 78 27 3 0 46 43 2 0 1
14 [Drugstore] 98 38 5 0 55 52 3 0 2
15 [Doctor/healthcare provider] 138 57 10 0 30 79 17 0 1
16 [Public transit stop] 125 1 1 0 108 10 14 0 3
17 [Leisure-time physical activity] 162 61 21 0 51 84 5 0 2
18 [Park] 272 56 19 0 163 102 3 0 3
19 [Cultural activity] 54 28 8 0 10 19 4 0 1
20 [Volunteering place] 60 24 5 0 18 37 5 0 1
21 [Religious/spiritual activity] 14 5 1 0 2 10 3 0 1
22 [Restaurant, café, bar, etc.] 285 80 40 0 155 141 18 0 3
23 [Take-out] 94 42 12 0 29 25 1 0 8
24 [Walk] 178 30 13 0 146 19 2 0 2
25 [Other place] 70 27 9 1 13 43 5 0 2
# graph
.tm1 <- .tm %>%
  filter(location_tmode_1 == 1) %>%
  mutate(tm = "[1] By car (driver)")
.tm2 <- .tm %>%
  filter(location_tmode_2 == 1) %>%
  mutate(tm = "[2] By car (passenger)")
.tm3 <- .tm %>%
  filter(location_tmode_3 == 1) %>%
  mutate(tm = "[3] By taxi/Uber")
.tm4 <- .tm %>%
  filter(location_tmode_4 == 1) %>%
  mutate(tm = "[4] On foot")
.tm5 <- .tm %>%
  filter(location_tmode_5 == 1) %>%
  mutate(tm = "[5] By bike")
.tm6 <- .tm %>%
  filter(location_tmode_6 == 1) %>%
  mutate(tm = "[6] By bus")
.tm7 <- .tm %>%
  filter(location_tmode_7 == 1) %>%
  mutate(tm = "[7] By train")
.tm99 <- .tm %>%
  filter(location_tmode_99 == 1) %>%
  mutate(tm = "[99] Other")
.tm <- bind_rows(.tm1, .tm2) %>%
  bind_rows(.tm3) %>%
  bind_rows(.tm4) %>%
  bind_rows(.tm5) %>%
  bind_rows(.tm6) %>%
  bind_rows(.tm7) %>%
  bind_rows(.tm99)

# histogram of answers
ggplot(data = .tm) +
  geom_bar(aes(x = fct_rev(description), fill = tm), position = "fill") +
  scale_fill_brewer(palette = "Set3", name = "Transport modes") +
  scale_y_continuous(labels = percent) +
  labs(y = "Proportion of transportation mode by location category", x = element_blank()) +
  coord_flip() +
  theme(legend.position = "bottom", legend.justification = c(0, 0), legend.text = element_text(size = 8)) +
  guides(fill = guide_legend(nrow = 3))

2.10.2 Visiting places alone

Based on the answers to the question Do you usually go to this place alone or with other people?.

loc_labels <- data.frame(location_category = c(2:26), description = c(
  " 2 [Other residence]",
  " 3 [Work]",
  " 4 [School/College/University]",
  " 5 [Supermarket]",
  " 6 [Public/farmer’s market]",
  " 7 [Bakery]",
  " 8 [Specialty food store]",
  " 9 [Convenience store/Dépanneur]",
  "10 [Liquor store/SAQ]",
  "11 [Bank]",
  "12 [Hair salon/barbershop]",
  "13 [Post office]",
  "14 [Drugstore]",
  "15 [Doctor/healthcare provider]",
  "16 [Public transit stop]",
  "17 [Leisure-time physical activity]",
  "18 [Park]",
  "19 [Cultural activity]",
  "20 [Volunteering place]",
  "21 [Religious/spiritual activity]",
  "22 [Restaurant, café, bar, etc.]",
  "23 [Take-out]",
  "24 [Walk]",
  "25 [Other place]",
  "26 [Social contact residence]"
))

# extract and summary stats
.alone <- locations %>%
  st_set_geometry(NULL) %>%
  filter(location_category != 1) %>%
  left_join(loc_labels) %>%
  mutate(location_alone_recode = case_when(
    location_alone2 == 1 ~ 1,
    location_alone2 == 2 ~ 0
  ))

.alone_grouped <- .alone %>%
  group_by(description) %>%
  dplyr::summarise(
    N = n(), "Visited alone" = sum(location_alone_recode),
    "Visited alone (%)" = round(sum(location_alone_recode) * 100.0 / n(), digits = 1)
  )

kable(.alone_grouped, caption = "Visiting places alone") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Visiting places alone
description N Visited alone Visited alone (%)
2 [Other residence] 9 1 11.1
3 [Work] 146 28 19.2
4 [School/College/University] 14 5 35.7
5 [Supermarket] 357 221 61.9
6 [Public/farmer’s market] 42 7 16.7
7 [Bakery] 66 44 66.7
8 [Specialty food store] 59 38 64.4
9 [Convenience store/Dépanneur] 27 18 66.7
10 [Liquor store/SAQ] 152 115 75.7
11 [Bank] 113 101 89.4
12 [Hair salon/barbershop] 85 82 96.5
13 [Post office] 78 69 88.5
14 [Drugstore] 98 77 78.6
15 [Doctor/healthcare provider] 138 114 82.6
16 [Public transit stop] 125 89 71.2
17 [Leisure-time physical activity] 162 65 40.1
18 [Park] 272 80 29.4
19 [Cultural activity] 54 7 13.0
20 [Volunteering place] 60 27 45.0
21 [Religious/spiritual activity] 14 3 21.4
22 [Restaurant, café, bar, etc.] 285 66 23.2
23 [Take-out] 94 54 57.4
24 [Walk] 178 87 48.9
25 [Other place] 70 24 34.3
# histogram of answers
ggplot(data = .alone) +
  geom_bar(aes(x = fct_rev(description), fill = factor(location_alone2)), position = "fill") +
  scale_fill_brewer(palette = "Set3", name = "Visiting places", labels = c("Alone", "With someone")) +
  scale_y_continuous(labels = percent) +
  labs(y = "Proportion of places visited alone", x = element_blank()) +
  coord_flip()

2.10.3 Visit frequency

Based on the answers to the question How often do you go there?.

loc_labels <- data.frame(location_category = c(2:26), description = c(
  " 2 [Other residence]",
  " 3 [Work]",
  " 4 [School/College/University]",
  " 5 [Supermarket]",
  " 6 [Public/farmer’s market]",
  " 7 [Bakery]",
  " 8 [Specialty food store]",
  " 9 [Convenience store/Dépanneur]",
  "10 [Liquor store/SAQ]",
  "11 [Bank]",
  "12 [Hair salon/barbershop]",
  "13 [Post office]",
  "14 [Drugstore]",
  "15 [Doctor/healthcare provider]",
  "16 [Public transit stop]",
  "17 [Leisure-time physical activity]",
  "18 [Park]",
  "19 [Cultural activity]",
  "20 [Volunteering place]",
  "21 [Religious/spiritual activity]",
  "22 [Restaurant, café, bar, etc.]",
  "23 [Take-out]",
  "24 [Walk]",
  "25 [Other place]",
  "26 [Social contact residence]"
))

# extract and summary stats
.freq <- locations %>%
  st_set_geometry(NULL) %>%
  filter(location_category != 1) %>%
  left_join(loc_labels)

.freq_grouped <- .freq %>%
  group_by(description) %>%
  dplyr::summarise(
    N = n(), min = min(location_freq_visit),
    max = max(location_freq_visit),
    mean = mean(location_freq_visit),
    median = median(location_freq_visit),
    sd = sd(location_freq_visit)
  )

kable(.freq_grouped, caption = "Visit frequency (expressed in times/year)") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Visit frequency (expressed in times/year)
description N min max mean median sd
2 [Other residence] 9 12 180 70.666667 52 63.466527
3 [Work] 146 2 365 200.123288 260 95.499478
4 [School/College/University] 14 0 260 104.214286 52 107.137710
5 [Supermarket] 357 0 364 57.722689 52 54.682165
6 [Public/farmer’s market] 42 2 208 28.023809 24 33.142330
7 [Bakery] 66 3 156 35.909091 24 33.702192
8 [Specialty food store] 59 1 260 51.237288 36 52.429374
9 [Convenience store/Dépanneur] 27 3 104 35.037037 24 33.419802
10 [Liquor store/SAQ] 152 2 156 27.513158 12 26.856249
11 [Bank] 113 1 156 18.699115 12 24.345315
12 [Hair salon/barbershop] 85 2 24 5.882353 4 4.351824
13 [Post office] 78 1 208 15.512821 5 33.651670
14 [Drugstore] 98 3 156 22.336735 12 25.847668
15 [Doctor/healthcare provider] 138 1 104 5.594203 3 10.962869
16 [Public transit stop] 125 0 520 41.512000 12 69.371443
17 [Leisure-time physical activity] 162 0 364 95.154321 52 73.396530
18 [Park] 272 1 728 75.992647 48 98.722392
19 [Cultural activity] 54 1 364 27.851852 12 53.145016
20 [Volunteering place] 60 1 364 50.050000 24 77.923566
21 [Religious/spiritual activity] 14 12 364 80.000000 36 111.890056
22 [Restaurant, café, bar, etc.] 285 2 520 29.771930 12 47.414050
23 [Take-out] 94 0 104 14.712766 12 14.871942
24 [Walk] 178 2 1820 100.977528 52 167.162594
25 [Other place] 70 4 260 55.585714 24 69.408994
# graph
ggplot(data = .freq) +
  geom_boxplot(aes(x = fct_rev(description), y = location_freq_visit)) +
  scale_y_continuous(limits = c(0, 365)) +
  labs(y = "Visits/year (Frequency over 1 visit/day not shown)", x = element_blank()) +
  coord_flip()

2.10.4 Spatial indicators: Camille Perchoux’s toolbox

Below is a list of indicators proposed by Camille Perchoux in her paper Assessing patterns of spatial behavior in health studies: Their socio-demographic determinants and associations with transportation modes (the RECORD Cohort Study).

-- Reading Camille tbx indics from Essence table
SELECT interact_id,
  n_acti_places, n_weekly_vst, n_acti_types,
  cvx_perimeter, cvx_surface,
  min_length, max_length, median_length, 
  pct_visits_neighb, 
  n_acti_prn, pct_visits_prn, prn_area_km2
FROM essence_table.essence_perchoux_tbx
WHERE city_id = 'Victoria' AND wave_id = 2 AND status = 'new'

2.10.5 Social indicators: Alexandre Naud’s toolbox

See Alex’s document for a more comprehensive presentation of the social indicators.

-- Reading Alex tbx indics from Essence table
SELECT interact_id,
  people_degree, 
  socialize_size, socialize_meet, socialize_chat,
  important_size, group_degree, simmelian
FROM essence_table.essence_naud_social
WHERE city_id = 'Victoria' AND wave_id = 2 AND status = 'new'

2.10.5.1 Number of people in the network (people_degree)

ggplot(ess.tab.alex) +
  geom_histogram(aes(x = people_degree))

kable(t(as.matrix(summary(ess.tab.alex$people_degree))), caption = "people_degree") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
people_degree
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 2 4 4.976191 7 22

2.10.5.2 Simmelian Brokerage (simmelian)

ggplot(ess.tab.alex) +
  geom_histogram(aes(x = simmelian))

kable(t(as.matrix(summary(ess.tab.alex$simmelian))), caption = "simmelian") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
simmelian
Min. 1st Qu. Median Mean 3rd Qu. Max. NA’s
1 4.083333 7.325 8.909501 11.83088 40.85106 12

2.10.5.3 Number of people with whom the participant like to socialize (socialize_size)

ggplot(ess.tab.alex) +
  geom_histogram(aes(x = socialize_size))

kable(t(as.matrix(summary(ess.tab.alex$socialize_size))), caption = "socialize_size") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
socialize_size
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 1 3 3.68254 6 14

2.10.5.4 Weekly face-to-face interactions among people with whom the participant like to socialize (socialize_meet)

ggplot(filter(ess.tab.alex, socialize_meet < 100)) +
  geom_histogram(aes(x = socialize_meet)) +
  annotate(geom = "text", x = 75, y = 100, label = "X-axis: values over 100 not displayed", alpha = .5)

kable(t(as.matrix(summary(ess.tab.alex$socialize_meet))), caption = "socialize_meet") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
socialize_meet
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 355 434 42261.19 792.5 5199948

2.10.5.5 Weekly ICT interactions among people with whom the participant like to socialize (socialize_chat)

ggplot(filter(ess.tab.alex, socialize_chat < 100)) +
  geom_histogram(aes(x = socialize_chat)) +
  annotate(geom = "text", x = 55, y = 100, label = "X-axis: values over 100 not displayed", alpha = .5)

kable(t(as.matrix(summary(ess.tab.alex$socialize_chat))), caption = "socialize_chat") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
socialize_chat
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 235 484 1436.69 1132 36860

2.10.5.6 Number of people with whom the participant discuss important matters (important_size)

ggplot(ess.tab.alex) +
  geom_histogram(aes(x = important_size))

kable(t(as.matrix(summary(ess.tab.alex$important_size))), caption = "important_size") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
important_size
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 1 2 2.920635 4 11

2.10.5.7 Number of people in all groups (group_degree)

ggplot(filter(ess.tab.alex, group_degree < 100)) +
  geom_histogram(aes(x = group_degree)) +
  annotate(geom = "text", x = 20, y = 100, label = "X-axis: values over 100 not displayed", alpha = .5)

kable(t(as.matrix(summary(ess.tab.alex$group_degree))), caption = "group_degree") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
group_degree
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 5 7.214286 10.75 39

3 Basic descriptive statistics for returning participants

3.1 Section 1: Residence and Neighbourhood

3.1.1 Now, let’s start with your home. What is your address?

home_location <- locations[locations$location_category == 1, ]

## version ggmap
vic_aoi <- st_bbox(home_location)
names(vic_aoi) <- c("left", "bottom", "right", "top")
vic_aoi[["left"]] <- vic_aoi[["left"]] - .07
vic_aoi[["right"]] <- vic_aoi[["right"]] + .07
vic_aoi[["top"]] <- vic_aoi[["top"]] + .01
vic_aoi[["bottom"]] <- vic_aoi[["bottom"]] - .01

bm <- get_stadiamap(vic_aoi, zoom = 11, maptype = "stamen_toner_lite") %>%
  ggmap(extent = "device")
bm + geom_sf(data = st_jitter(home_location, .008), inherit.aes = FALSE, color = "blue", size = 1.8, alpha = .3) # see https://github.com/r-spatial/sf/issues/336

NB: Home locations have been randomly shifted from their original position to protect privacy.

# Number of participants by municipalites
home_by_municipalites <- st_join(home_location, municipalities["NAME"])
home_by_mun_cnt <- as.data.frame(home_by_municipalites) %>%
  group_by(NAME) %>%
  dplyr::count() %>%
  arrange(desc(n), NAME)
home_by_mun_cnt$Shape <- NULL
kable(home_by_mun_cnt, caption = "Number of participants by municipalities") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of participants by municipalities
NAME n
Victoria 49
Saanich 33
Esquimalt 7
Langford 2
Oak Bay 2
View Royal 1

3.1.2 If you were asked to draw the boundaries of your neighbourhood, what would they be?

prn <- poly_geom[poly_geom$area_type == "neighborhood", ]

## version ggmap
bm + geom_sf(data = prn, inherit.aes = FALSE, fill = alpha("blue", 0.05), color = alpha("blue", 0.3))

# Min, max, median & mean area of PRN
prn$area_m2 <- st_area(prn$geom)
kable(t(as.matrix(summary(prn$area_m2))),
  caption = "Area (in square meters) of the perceived residential neighborhood",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Area (in square meters) of the perceived residential neighborhood
Min. 1st Qu. Median Mean 3rd Qu. Max.
8476.6 720596.6 1278462 2466199 2564457 35334533

NB only 87 valid neighborhoods were collected, as many participants struggled to draw polygons on the map.

3.1.3 How attached are you to your neighbourhood?

# extract and recode
.ngh_att <- veritas_main[veritas_main$neighbourhood_attach != 99, c("interact_id", "neighbourhood_attach")] %>% dplyr::rename(neighbourhood_attach_code = neighbourhood_attach)
.ngh_att$neighbourhood_attach <- factor(ifelse(.ngh_att$neighbourhood_attach_code == 1, "1 [Not attached at all]",
  ifelse(.ngh_att$neighbourhood_attach_code == 6, "6 [Very attached]",
    .ngh_att$neighbourhood_attach_code
  )
))

# histogram of attachment
ggplot(data = .ngh_att) +
  geom_histogram(aes(x = neighbourhood_attach), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "neighbourhood_attach")

.ngh_att_cnt <- .ngh_att %>%
  group_by(neighbourhood_attach) %>%
  dplyr::count() %>%
  arrange(neighbourhood_attach)
kable(.ngh_att_cnt, caption = "Neigbourhood attachment") %>% 
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Neigbourhood attachment
neighbourhood_attach n
1 [Not attached at all] 1
2 3
3 3
4 24
5 35
6 [Very attached] 28

3.1.4 On average, how many hours per day do you spend outside of your home?

# histogram of n hours out
ggplot(data = veritas_main) +
  geom_histogram(aes(x = hours_out))

# Min, max, median & mean hours/day out
kable(t(as.matrix(summary(veritas_main$hours_out))),
  caption = "Hours/day outside home",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Hours/day outside home
Min. 1st Qu. Median Mean 3rd Qu. Max.
1 6 9 8.4 10 15

3.1.5 Of this time spent outside your home, on average how many hours do you spend outside your neighbourhood?

# histogram of n hours out
ggplot(data = veritas_main) +
  geom_histogram(aes(x = hours_out_neighb))

# Min, max, median & mean hours/day out of neighborhood
kable(t(as.matrix(summary(veritas_main$hours_out_neighb))),
  caption = "Hours/day outside neighbourhood",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Hours/day outside neighbourhood
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 3.2 8 6.5 9 15

3.1.6 Are there one or more areas close to where you live that you tend to avoid because you do not feel safe there (for any reason)?

# extract and recode
.unsafe <- veritas_main[c("interact_id", "unsafe_area")] %>% dplyr::rename(unsafe_area_code = unsafe_area)
.unsafe$unsafe_area <- factor(ifelse(.unsafe$unsafe_area_code == 1, "1 [Yes]",
  ifelse(.unsafe$unsafe_area_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .unsafe) +
  geom_histogram(aes(x = unsafe_area), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "unsafe_area")

.unsafe_cnt <- .unsafe %>%
  group_by(unsafe_area) %>%
  dplyr::count() %>%
  arrange(unsafe_area)
kable(.unsafe_cnt, caption = "Unsafe areas") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Unsafe areas
unsafe_area n
1 [Yes] 15
2 [No] 79
# map
unsafe <- poly_geom[poly_geom$area_type == "unsafe area", ]

## version ggmap
bm + geom_sf(data = unsafe, inherit.aes = FALSE, fill = alpha("blue", 0.3), color = alpha("blue", 0.5))

# Min, max, median & mean area of PRN
unsafe$area_m2 <- st_area(unsafe$geom)
kable(t(as.matrix(summary(unsafe$area_m2))),
  caption = "Area (in square meters) of the perceived unsafe area",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Area (in square meters) of the perceived unsafe area
Min. 1st Qu. Median Mean 3rd Qu. Max.
4690 41624.9 149243.7 249137.5 352565.1 867053.9

3.1.7 Do you spend the night somewhere other than your home at least once per week?

# extract and recode
.o_res <- veritas_main[c("interact_id", "other_resid")] %>% dplyr::rename(other_resid_code = other_resid)
.o_res$other_resid <- factor(ifelse(.o_res$other_resid_code == 1, "1 [Yes]",
  ifelse(.o_res$other_resid_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .o_res) +
  geom_histogram(aes(x = other_resid), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "other_resid")

.o_res_cnt <- .o_res %>%
  group_by(other_resid) %>%
  dplyr::count() %>%
  arrange(other_resid)
kable(.o_res_cnt, caption = "Other residence") %>% 
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Other residence
other_resid n
1 [Yes] 1
2 [No] 93

3.2 Section 2: Occupation

3.2.1 Are you currently working?

# extract and recode
.work <- veritas_main[c("interact_id", "working")] %>% dplyr::rename(working_code = working)
.work$working <- factor(ifelse(.work$working_code == 1, "1 [Yes]",
  ifelse(.work$working_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .work) +
  geom_histogram(aes(x = working), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "working")

.work_cnt <- .work %>%
  group_by(working) %>%
  dplyr::count() %>%
  arrange(working)
kable(.work_cnt, caption = "Currently working") %>% 
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Currently working
working n
1 [Yes] 77
2 [No] 17

3.2.2 Where do you work?

work_location <- locations[locations$location_category == 3, ]

bm + geom_sf(data = work_location, inherit.aes = FALSE, color = "blue", size = 1.8, alpha = .3)

3.2.3 On average, how many hours per week do you work?

# histogram of n hours out
ggplot(data = veritas_main[veritas_main$working == 1, ]) +
  geom_histogram(aes(x = work_hours))

# Min, max, median & mean hours/day out
kable(t(as.matrix(summary(veritas_main$work_hours[veritas_main$working == 1]))),
  caption = "Work hours/week",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Work hours/week
Min. 1st Qu. Median Mean 3rd Qu. Max.
5 35 37 35.9 40 84

3.2.4 Which of the following categories best describes the amount of physical activity required for your job?

# extract and recode
.work_pa <- veritas_main[veritas_main$working == 1, c("interact_id", "work_pa")] %>% dplyr::rename(work_pa_code = work_pa)
.work_pa$work_pa <- factor(ifelse(.work_pa$work_pa_code == 1, "1 [Mainly sitting with slight arm movements]",
  ifelse(.work_pa$work_pa_code == 2, "2 [Sitting and standing with some walking]",
    ifelse(.work_pa$work_pa_code == 3, "3 [Walking, with some handling of materials generally weighing less than 25 kg (55 lbs)]",
      ifelse(.work_pa$work_pa_code == 4, "4 [Walking and heavy manual work often requiring handling of materials weighing over 25 kg (50 lbs)]", "N/A")
    )
  )
))

# histogram of answers
ggplot(data = .work_pa) +
  geom_histogram(aes(x = work_pa), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "Physical activity at work")

.work_pa_cnt <- .work_pa %>%
  group_by(work_pa) %>%
  dplyr::count() %>%
  arrange(work_pa)
kable(.work_pa_cnt, caption = "Physical activity at work") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Physical activity at work
work_pa n
1 [Mainly sitting with slight arm movements] 35
2 [Sitting and standing with some walking] 34
3 [Walking, with some handling of materials generally weighing less than 25 kg (55 lbs)] 6
4 [Walking and heavy manual work often requiring handling of materials weighing over 25 kg (50 lbs)] 2

3.2.5 Are you currently a registered student?

# extract and recode
.study <- veritas_main[c("interact_id", "studying")] %>% dplyr::rename(studying_code = studying)
.study$studying <- factor(ifelse(.study$studying_code == 1, "1 [Yes]",
  ifelse(.study$studying_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .study) +
  geom_histogram(aes(x = studying), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "Studying")

.study_cnt <- .study %>%
  group_by(studying) %>%
  dplyr::count() %>%
  arrange(studying)
kable(.study_cnt, caption = "Currently studying") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Currently studying
studying n
1 [Yes] 2
2 [No] 92

3.2.6 Where do you study?

study_location <- locations[locations$location_category == 4, ]

bm + geom_sf(data = study_location, inherit.aes = FALSE, color = "blue", size = 1.8, alpha = .3)

3.2.7 On average, how many hours per week do you study?

# histogram of n hours out
ggplot(data = veritas_main[veritas_main$studying == 1, ]) +
  geom_histogram(aes(x = study_hours))

# Min, max, median & mean hours/day out
kable(t(as.matrix(summary(veritas_main$study_hours[veritas_main$studying == 1]))),
  caption = "study hours/week",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
study hours/week
Min. 1st Qu. Median Mean 3rd Qu. Max.
4 6.8 9.5 9.5 12.2 15

3.3 Section 3: Shopping activities

3.3.1 In Date of Previous Data Collection Wave, you reported shopping at these locations. Do you still visit these places?

shop_lut <- data.frame(
  location_category_code = c(5, 6, 7, 8, 9, 10),
  location_category = factor(c(
    " 5 [Supermarket]",
    " 6 [Public/farmer’s market]",
    " 7 [Bakery]",
    " 8 [Specialty food store]",
    " 9 [Convenience store/Dépanneur]",
    "10 [Liquor store/SAQ]"
  ))
)
shop_location <- locations[locations$location_category %in% shop_lut$location_category_code, ] %>%
  filter(location_current == 1) %>%
  dplyr::rename(location_category_code = location_category) %>%
  inner_join(shop_lut, by = "location_category_code")

# map
bm + geom_sf(data = shop_location, inherit.aes = FALSE, aes(color = location_category), size = 1.5, alpha = .3) +
  scale_color_brewer(palette = "Accent") +
  theme(legend.position = "bottom", legend.text = element_text(size = 8), legend.title = element_blank())

# compute number of shopping locations by category
ggplot(data = shop_location) +
  geom_histogram(aes(x = location_category), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "Shopping locations by categories")

.location_category_cnt <- as.data.frame(shop_location[c("location_category")]) %>%
  group_by(location_category) %>%
  dplyr::count() %>%
  arrange(location_category)
kable(.location_category_cnt, caption = "Shopping locations by categories") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Shopping locations by categories
location_category n
5 [Supermarket] 273
6 [Public/farmer’s market] 35
7 [Bakery] 53
8 [Specialty food store] 47
9 [Convenience store/Dépanneur] 13
# compute statistics on shopping locations by participants and categories
# > one needs to account for participants who did not report location for some categories
.loc_iid_category_cnt <- as.data.frame(shop_location[c("interact_id", "location_category")]) %>%
  group_by(interact_id, location_category) %>%
  dplyr::count()

# (cont'd) simulate SQL JOIN TABLE ON TRUE to build list of all combination iid/shopping categ
.dummy <- data_frame(
  interact_id = character(),
  location_category = character()
)
for (iid in as.vector(veritas_main$interact_id)) {
  .dmy <- data_frame(
    interact_id = as.character(iid),
    location_category = shop_lut$location_category
  )
  .dummy <- rbind(.dummy, .dmy)
}

# (cont'd) find iid/categ combination without match in veritas locations
.no_shop_iid <- dplyr::setdiff(.dummy, .loc_iid_category_cnt[c("location_category", "interact_id")]) %>%
  mutate(n = 0)
.loc_iid_category_cnt <- bind_rows(.loc_iid_category_cnt, .no_shop_iid)

.location_category_cnt <- .loc_iid_category_cnt %>%
  group_by(location_category) %>%
  dplyr::summarise(min = min(n), mean = round(mean(n), 2), median = median(n), max = max(n)) %>%
  arrange(location_category)
kable(.location_category_cnt, caption = "Number of shopping locations by participant and category") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of shopping locations by participant and category
location_category min mean median max
5 [Supermarket] 0 2.90 3 5
6 [Public/farmer’s market] 0 0.37 0 4
7 [Bakery] 0 0.56 0 4
8 [Specialty food store] 0 0.50 0 5
9 [Convenience store/Dépanneur] 0 0.14 0 3
10 [Liquor store/SAQ] 0 0.00 0 0

3.3.2 Thinking about the places where you shop, are there other supermarkets, farmers markets, bakeries, specialty stores, convenience stores or liquor stores you visit at least once per month?

NB: Variable grp_shopping_new has not been properly recorded in Victoria wave 2 for returning participants.

# extract and recode
.grp_shopping <- veritas_main[c("interact_id", "grp_shopping_new")] %>% dplyr::rename(grp_shopping_new_code = grp_shopping_new)
.grp_shopping$grp_shopping_new <- factor(ifelse(.grp_shopping$grp_shopping_new_code == 1, "1 [Yes]",
  ifelse(.grp_shopping$grp_shopping_new_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .grp_shopping) +
  geom_histogram(aes(x = grp_shopping_new), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "grp_shopping_new")

.grp_shopping_cnt <- .grp_shopping %>%
  group_by(grp_shopping_new) %>%
  dplyr::count() %>%
  arrange(grp_shopping_new)
kable(.grp_shopping_cnt, caption = "New shopping places") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")

3.4 Section 4: Services

3.4.1 In Date of Previous Data Collection Wave, you reported using services at these locations. Do you still visit these places?

serv_lut <- data.frame(
  location_category_code = c(11, 12, 13, 14, 15),
  location_category = factor(c(
    "11 [Bank]",
    "12 [Hair salon/barbershop]",
    "13 [Post office]",
    "14 [Drugstore]",
    "15 Doctor/healthcare provider]"
  ))
)
serv_location <- locations[locations$location_category %in% serv_lut$location_category_code, ] %>%
  filter(location_current == 1) %>%
  dplyr::rename(location_category_code = location_category) %>%
  inner_join(serv_lut, by = "location_category_code")

# map
bm + geom_sf(data = serv_location, inherit.aes = FALSE, aes(color = location_category), size = 1.5, alpha = .3) +
  scale_color_brewer(palette = "Accent") +
  theme(legend.position = "bottom", legend.text = element_text(size = 8), legend.title = element_blank())

# compute number of shopping locations by category
ggplot(data = serv_location) +
  geom_histogram(aes(x = location_category), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "Service locations by categories")

.location_category_cnt <- as.data.frame(serv_location[c("location_category")]) %>%
  group_by(location_category) %>%
  dplyr::count() %>%
  arrange(location_category)
kable(.location_category_cnt, caption = "Shopping locations by categories") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Shopping locations by categories
location_category n
11 [Bank] 72
12 [Hair salon/barbershop] 48
13 [Post office] 59
14 [Drugstore] 69
15 Doctor/healthcare provider] 86
# compute statistics on shopping locations by participants and categories
# > one needs to account for participants who did not report location for some categories
.loc_iid_category_cnt <- as.data.frame(serv_location[c("interact_id", "location_category")]) %>%
  group_by(interact_id, location_category) %>%
  dplyr::count()

# (cont'd) simulate SQL JOIN TABLE ON TRUE
.dummy <- data_frame(
  interact_id = character(),
  location_category = character()
)
for (iid in as.vector(veritas_main$interact_id)) {
  .dmy <- data_frame(
    interact_id = as.character(iid),
    location_category = serv_lut$location_category
  )
  .dummy <- rbind(.dummy, .dmy)
}

# (cont'd) find iid/categ combination without match in veritas locations
.no_serv_iid <- dplyr::setdiff(.dummy, .loc_iid_category_cnt[c("location_category", "interact_id")]) %>%
  mutate(n = 0)
.loc_iid_category_cnt <- bind_rows(.loc_iid_category_cnt, .no_serv_iid)

.location_category_cnt <- .loc_iid_category_cnt %>%
  group_by(location_category) %>%
  dplyr::summarise(min = min(n), mean = round(mean(n), 2), median = median(n), max = max(n)) %>%
  arrange(location_category)
kable(.location_category_cnt, caption = "Number of shopping locations by participant and category") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of shopping locations by participant and category
location_category min mean median max
11 [Bank] 0 0.77 1 1
12 [Hair salon/barbershop] 0 0.51 1 1
13 [Post office] 0 0.63 1 1
14 [Drugstore] 0 0.73 1 1
15 Doctor/healthcare provider] 0 0.91 1 5

3.4.2 Thinking about the places where you use services, are there other banks, hair salons, post offices, drugstores, doctors or other healthcare providers you visit at least once per month?

NB: Variable grp_services_new has not been properly recorded in Victoria wave 2 for returning participants.

# extract and recode
.grp_services <- veritas_main[c("interact_id", "grp_services_new")] %>% dplyr::rename(grp_services_new_code = grp_services_new)
.grp_services$grp_services_new <- factor(ifelse(.grp_services$grp_services_new_code == 1, "1 [Yes]",
  ifelse(.grp_services$grp_services_new_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .grp_services) +
  geom_histogram(aes(x = grp_services_new), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "grp_services_new")

.grp_services_cnt <- .grp_services %>%
  group_by(grp_services_new) %>%
  dplyr::count() %>%
  arrange(grp_services_new)
kable(.grp_services_cnt, caption = "New services places") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")

3.5 Section 5: Transportation

3.5.1 In Date of Previous Data Collection Wave, you reported accessing these public transit stops from your home. Do you still access these places?

transp_location <- locations[locations$location_category == 16, ] %>% filter(location_current == 1)

bm + geom_sf(data = transp_location, inherit.aes = FALSE, color = "blue", size = 1.8, alpha = .3)

3.5.2 Are there other public transit stops you access from your home at least once per month?

NB: Variable grp_ptransit_new has not been properly recorded in Victoria wave 2 for returning participants.

# extract and recode
.grp_ptransit <- veritas_main[c("interact_id", "grp_ptransit_new")] %>% dplyr::rename(grp_ptransit_new_code = grp_ptransit_new)
.grp_ptransit$grp_ptransit_new <- factor(ifelse(.grp_ptransit$grp_ptransit_new_code == 1, "1 [Yes]",
  ifelse(.grp_ptransit$grp_ptransit_new_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .grp_ptransit) +
  geom_histogram(aes(x = grp_ptransit_new), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "grp_ptransit_new")

.grp_ptransit_cnt <- .grp_ptransit %>%
  group_by(grp_ptransit_new) %>%
  dplyr::count() %>%
  arrange(grp_ptransit_new)
kable(.grp_ptransit_cnt, caption = "New transit places") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")

3.6 Section 6: Leisure activities

3.6.1 In Date of Previous Data Collection Wave, you reported doing leisure activities at these locations. Do you still visit these places?

leisure_lut <- data.frame(
  location_category_code = c(17, 18, 19, 20, 21, 22, 23, 24),
  location_category = factor(c(
    "17 [Leisure-time physical activity]",
    "18 [Park]",
    "19 [Cultural activity]",
    "20 [Volunteering place]",
    "21 [Religious or spiritual activity]",
    "22 [Restaurant, café, bar, etc. ]",
    "23 [Take-out]",
    "24 [Walk]"
  ))
)
leisure_location <- locations[locations$location_category %in% leisure_lut$location_category_code, ] %>%
  dplyr::rename(location_category_code = location_category) %>%
  inner_join(leisure_lut, by = "location_category_code")

# map
bm + geom_sf(data = leisure_location, inherit.aes = FALSE, aes(color = location_category), size = 1.5, alpha = .3) +
  scale_color_brewer(palette = "Accent") +
  theme(legend.position = "bottom", legend.text = element_text(size = 8), legend.title = element_blank())

# compute number of shopping locations by category
ggplot(data = leisure_location) +
  geom_histogram(aes(x = location_category), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "Leisure locations by categories")

.location_category_cnt <- as.data.frame(leisure_location[c("location_category")]) %>%
  group_by(location_category) %>%
  dplyr::count() %>%
  arrange(location_category)
kable(.location_category_cnt, caption = "Shopping locations by categories") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Shopping locations by categories
location_category n
17 [Leisure-time physical activity] 113
18 [Park] 180
19 [Cultural activity] 64
20 [Volunteering place] 37
21 [Religious or spiritual activity] 5
22 [Restaurant, café, bar, etc. ] 196
23 [Take-out] 46
24 [Walk] 168
# compute statistics on shopping locations by participants and categories
# > one needs to account for participants who did not report location for some categories
.loc_iid_category_cnt <- as.data.frame(leisure_location[c("interact_id", "location_category")]) %>%
  group_by(interact_id, location_category) %>%
  dplyr::count()

# (cont'd) simulate SQL JOIN TABLE ON TRUE
.dummy <- data_frame(
  interact_id = character(),
  location_category = character()
)
for (iid in as.vector(veritas_main$interact_id)) {
  .dmy <- data_frame(
    interact_id = as.character(iid),
    location_category = leisure_lut$location_category
  )
  .dummy <- rbind(.dummy, .dmy)
}

# (cont'd) find iid/categ combination without match in veritas locations
.no_leisure_iid <- dplyr::setdiff(.dummy, .loc_iid_category_cnt[c("location_category", "interact_id")]) %>%
  mutate(n = 0)

.loc_iid_category_cnt <- bind_rows(.loc_iid_category_cnt, .no_leisure_iid)

.location_category_cnt <- .loc_iid_category_cnt %>%
  group_by(location_category) %>%
  dplyr::summarise(min = min(n), mean = round(mean(n), 2), median = median(n), max = max(n)) %>%
  arrange(location_category)
kable(.location_category_cnt, caption = "Number of leisure locations by participant and category") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of leisure locations by participant and category
location_category min mean median max
17 [Leisure-time physical activity] 0 1.20 1 5
18 [Park] 0 1.91 1 5
19 [Cultural activity] 0 0.68 0 5
20 [Volunteering place] 0 0.39 0 3
21 [Religious or spiritual activity] 0 0.05 0 1
22 [Restaurant, café, bar, etc. ] 0 2.09 2 5
23 [Take-out] 0 0.49 0 5
24 [Walk] 0 1.79 1 5

3.6.2 Thinking about the places where you do leisure activities, are there other parks, gyms, movie theaters, concert halls, churchs, temples, restaurants, cafés, bars or any places where you do leisure activities and that you visit at least once per month?

NB: Variable grp_leisure_new has not been properly recorded in Victoria wave 2 for returning participants.

# extract and recode
.grp_leisure <- veritas_main[c("interact_id", "grp_leisure_new")] %>% dplyr::rename(grp_leisure_new_code = grp_leisure_new)
.grp_leisure$grp_leisure_new <- factor(ifelse(.grp_leisure$grp_leisure_new_code == 1, "1 [Yes]",
  ifelse(.grp_leisure$grp_leisure_new_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .grp_leisure) +
  geom_histogram(aes(x = grp_leisure_new), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "grp_leisure_new")

.grp_leisure_cnt <- .grp_leisure %>%
  group_by(grp_leisure_new) %>%
  dplyr::count() %>%
  arrange(grp_leisure_new)
kable(.grp_leisure_cnt, caption = "New leisure places") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")

3.7 Section 7: Other places/activities

3.7.1 Here are the other places you reported regularly visiting in Date of Previous Data Collection Wave. Do you still visit these places?

other_location <- locations[locations$location_category == 25, ] %>% filter(location_current == 1)

bm + geom_sf(data = other_location, inherit.aes = FALSE, color = "blue", size = 1.8, alpha = .3)

3.7.2 Are there other places that you go to at least once per month that we have not mentioned? For example: a mall, a daycare, a hardware store, or a community center.

NB: Variable other_new has not been properly recorded in Victoria wave 2 for returning participants.

# extract and recode
.other <- veritas_main[c("interact_id", "other_new")] %>% dplyr::rename(other_new_code = other_new)
.other$other_new <- factor(ifelse(.other$other_new_code == 1, "1 [Yes]",
  ifelse(.other$other_new_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .other) +
  geom_histogram(aes(x = other_new), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "other_new")

.other_cnt <- .other %>%
  group_by(other_new) %>%
  dplyr::count() %>%
  arrange(other_new)
kable(.other_cnt, caption = "New other places") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")

3.8 Section 8: Areas of change

Participants were not asked for areas of change in Victoria

3.9 Section 9: Social contact

3.9.1 In Date of Previous Data Collection Wave, you reported visiting people at their home. Do you still visit these places?

visiting_location <- locations[locations$location_category == 26, ] %>% filter(location_current == 1)

bm + geom_sf(data = visiting_location, inherit.aes = FALSE, color = "blue", size = 1.8, alpha = .3)

3.9.2 Do you visit anyone else at his or her home at least once per month?

NB: Variable visiting_new has not been properly recorded in Victoria wave 2 for returning participants.

# extract and recode
.visiting <- veritas_main[c("interact_id", "visiting_new")] %>% dplyr::rename(visiting_code = visiting_new)
.visiting$visiting_new <- factor(ifelse(.visiting$visiting_code == 1, "1 [Yes]",
  ifelse(.visiting$visiting_code == 2, "2 [No]", "N/A")
))

# histogram of answers
ggplot(data = .visiting) +
  geom_histogram(aes(x = visiting_new), stat = "count") +
  scale_x_discrete(labels = function(lbl) str_wrap(lbl, width = 20)) +
  labs(x = "visiting_new")

.visiting_cnt <- .visiting %>%
  group_by(visiting_new) %>%
  dplyr::count() %>%
  arrange(visiting_new)
kable(.visiting_cnt, caption = "Social contact") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")

3.9.3 Great, we are almost done completing this questionnaire. You have documented all your activity places on a map, and specified with whom you generally do these activities. These last few questions concern the people you documented earlier.

# compute statistics on groups / participant
# > one needs to account for participants who did not report any group
.gr_iid_cnt <- as.data.frame(group[c("interact_id")]) %>%
  group_by(interact_id) %>%
  dplyr::count()

# (cont'd) find iid combination without match in veritas group
.no_gr_iid <- anti_join(veritas_main[c("interact_id")], .gr_iid_cnt, by = "interact_id") %>%
  mutate(n = 0)
.gr_iid_cnt <- bind_rows(.gr_iid_cnt, .no_gr_iid)

kable(t(as.matrix(summary(.gr_iid_cnt$n))), caption = "Number of groups per participant") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of groups per participant
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 1 2 2.329787 3 8
# compute statistics on people / participant
# > one needs to account for participants who did not report any group
.pl_iid_cnt <- as.data.frame(people[c("interact_id")]) %>%
  group_by(interact_id) %>%
  dplyr::count()

# (cont'd) find iid combination without match in veritas group
.no_pl_iid <- anti_join(veritas_main[c("interact_id")], .pl_iid_cnt, by = "interact_id") %>%
  mutate(n = 0)
.pl_iid_cnt <- bind_rows(.pl_iid_cnt, .no_pl_iid)

kable(t(as.matrix(summary(.pl_iid_cnt$n))), caption = "Number of people per participant") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of people per participant
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 3 5 7.117021 9.75 53
# histogram
.sc_iid_cnt <- .pl_iid_cnt %>% mutate(soc_type = "people")
.sc_iid_cnt <- .gr_iid_cnt %>%
  mutate(soc_type = "group") %>%
  bind_rows(.sc_iid_cnt)

ggplot(data = .sc_iid_cnt) +
  geom_histogram(aes(x = n, y = stat(count), fill = soc_type), position = "dodge") +
  labs(x = "Social network size by element type", fill = element_blank())

3.9.3.1 Among these people, who do you discuss important matters with?

# extract number of important people / participant
.n_important <- important %>% dplyr::count(interact_id)
.n_people <- people %>% dplyr::count(interact_id)

.n_people_imp <- left_join(veritas_main[c("interact_id")], .n_people, by = "interact_id") %>%
  left_join(.n_important, by = "interact_id") %>%
  mutate_all(~ replace(., is.na(.), 0)) %>%
  dplyr::rename(n_people = n.x, n_important = n.y) %>%
  mutate(pct = 100 * n_important / n_people)

kable(t(as.matrix(summary(.n_people_imp$n_important))),
  caption = "Number of important people per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of important people per participant
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 1 2 3.3 4 19
kable(t(as.matrix(summary(.n_people_imp$pct))),
  caption = "% of important people among social contact per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
% of important people among social contact per participant
Min. 1st Qu. Median Mean 3rd Qu. Max. NA’s
0 33.3 57.1 57.4 83.3 100 1

NB In Victoria, 3 participants also listed groups in this catagory, hence the max value over 100%.

3.9.3.2 Among these people, who do you like to socialize with?

# extract number of important people / participant
.n_socialize <- socialize %>% dplyr::count(interact_id)
.n_people <- people %>% dplyr::count(interact_id)

.n_people_soc <- left_join(veritas_main[c("interact_id")], .n_people, by = "interact_id") %>%
  left_join(.n_socialize, by = "interact_id") %>%
  mutate_all(~ replace(., is.na(.), 0)) %>%
  dplyr::rename(n_people = n.x, n_socialize = n.y) %>%
  mutate(pct = 100 * n_socialize / n_people)

kable(t(as.matrix(summary(.n_people_soc$n_socialize))),
  caption = "Number of people with whom to socialize per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of people with whom to socialize per participant
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 1 3.5 5 6.8 25
kable(t(as.matrix(summary(.n_people_soc$pct))),
  caption = "% of people with whom to  socialize among social contact per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
% of people with whom to socialize among social contact per participant
Min. 1st Qu. Median Mean 3rd Qu. Max. NA’s
0 53.8 80 74.4 100 100 1

3.9.3.3 Among these people, who do you meet often with but do not necessarily feel close to?

# extract number of important people / participant
.n_not_close <- not_close %>% dplyr::count(interact_id)
.n_people <- people %>% dplyr::count(interact_id)

.n_people_not_close <- left_join(veritas_main[c("interact_id")], .n_people, by = "interact_id") %>%
  left_join(.n_not_close, by = "interact_id") %>%
  mutate_all(~ replace(., is.na(.), 0)) %>%
  dplyr::rename(n_people = n.x, n_not_close = n.y) %>%
  mutate(pct = 100 * n_not_close / n_people)

kable(t(as.matrix(summary(.n_people_not_close$n_not_close))),
  caption = "Number of not so close people per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of not so close people per participant
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 0 1 2 7
kable(t(as.matrix(summary(.n_people_not_close$pct))),
  caption = "% of not so close people among social contact per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
% of not so close people among social contact per participant
Min. 1st Qu. Median Mean 3rd Qu. Max. NA’s
0 0 0 13.3 25 100 1

3.9.3.4 Among these people, who knows whom?

# extract number of who knows who relationships
.n_relat <- relationship %>%
  filter(relationship_type == 1) %>%
  dplyr::count(interact_id)
.n_people <- people %>% dplyr::count(interact_id)

.n_people_relat <- left_join(veritas_main[c("interact_id")], .n_people, by = "interact_id") %>%
  left_join(.n_relat, by = "interact_id") %>%
  mutate_all(~ replace(., is.na(.), 0)) %>%
  dplyr::rename(n_people = n.x, n_relat = n.y) %>%
  mutate(pct = 100 * n_relat * 2 / (n_people * (n_people - 1))) # potential number of relationships = N x (N -1) / 2

kable(t(as.matrix(summary(.n_people_relat$n_relat))),
  caption = "Number of relationships « who knows who » per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Number of relationships « who knows who » per participant
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 1 6 13.2 18 75
kable(t(as.matrix(summary(.n_people_relat$pct))),
  caption = "% of relationships « who knows who » per participant",
  digits = 1
) %>%
  kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
% of relationships « who knows who » per participant
Min. 1st Qu. Median Mean 3rd Qu. Max. NA’s
0 29.1 50 55.6 95 100 15

3.10 Derived metrics

3.10.1 Transportation mode preferences

Based on the answers to the question Usually, how do you go there? (Check all that apply.).

# code  en
# 1 By car and you drive
# 2 By car and someone else drives
# 3 By taxi/Uber
# 4 On foot
# 5 By bike
# 6 By bus
# 7 By subway
# 8 By train
# 99    Other

loc_labels <- data.frame(location_category = c(2:26), description = c(
  " 2 [Other residence]",
  " 3 [Work]",
  " 4 [School/College/University]",
  " 5 [Supermarket]",
  " 6 [Public/farmer’s market]",
  " 7 [Bakery]",
  " 8 [Specialty food store]",
  " 9 [Convenience store/Dépanneur]",
  "10 [Liquor store/SAQ]",
  "11 [Bank]",
  "12 [Hair salon/barbershop]",
  "13 [Post office]",
  "14 [Drugstore]",
  "15 [Doctor/healthcare provider]",
  "16 [Public transit stop]",
  "17 [Leisure-time physical activity]",
  "18 [Park]",
  "19 [Cultural activity]",
  "20 [Volunteering place]",
  "21 [Religious/spiritual activity]",
  "22 [Restaurant, café, bar, etc.]",
  "23 [Take-out]",
  "24 [Walk]",
  "25 [Other place]",
  "26 [Social contact residence]"
))

# extract and summary stats
.tm <- locations %>%
  st_set_geometry(NULL) %>%
  filter(location_category != 1 & location_current == 1) %>%
  left_join(loc_labels)

.tm_grouped <- .tm %>%
  group_by(description) %>%
  dplyr::summarise(
    N = n(), "By car (driver)" = sum(location_tmode_1),
    "By car (passenger)" = sum(location_tmode_2),
    "By taxi/Uber" = sum(location_tmode_3),
    "On foot" = sum(location_tmode_4),
    "By bike" = sum(location_tmode_5),
    "By bus" = sum(location_tmode_6),
    "By train" = sum(location_tmode_7),
    "Other" = sum(location_tmode_99)
  )

kable(.tm_grouped, caption = "Transportation mode preferences") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Transportation mode preferences
description N By car (driver) By car (passenger) By taxi/Uber On foot By bike By bus By train Other
2 [Other residence] 1 1 0 0 0 0 0 0 0
3 [Work] 106 18 2 0 15 85 13 1 12
4 [School/College/University] 2 1 0 0 0 1 1 0 0
5 [Supermarket] 273 118 35 0 88 170 4 0 4
6 [Public/farmer’s market] 35 8 3 0 13 19 1 0 0
7 [Bakery] 53 9 9 0 25 35 0 0 1
8 [Specialty food store] 47 18 6 0 18 22 0 0 0
9 [Convenience store/Dépanneur] 13 0 0 0 12 9 0 0 0
11 [Bank] 72 21 4 0 33 50 3 0 0
12 [Hair salon/barbershop] 48 8 0 0 18 29 2 0 1
13 [Post office] 59 19 1 0 31 38 0 0 0
14 [Drugstore] 69 24 3 0 35 45 3 0 0
15 [Doctor/healthcare provider] 86 30 5 0 17 60 5 0 3
16 [Public transit stop] 97 1 0 0 93 2 4 0 1
17 [Leisure-time physical activity] 113 40 17 0 29 70 5 0 3
18 [Park] 180 36 29 0 109 78 7 0 0
19 [Cultural activity] 64 19 5 0 26 39 9 0 1
20 [Volunteering place] 37 12 2 0 12 23 1 0 4
21 [Religious/spiritual activity] 5 2 1 0 2 4 0 0 0
22 [Restaurant, café, bar, etc.] 196 43 14 2 106 98 17 0 2
23 [Take-out] 46 21 14 1 18 19 1 0 2
24 [Walk] 168 24 15 0 137 61 2 0 0
25 [Other place] 57 21 8 0 17 37 3 1 2
26 [Social contact residence] 78 36 11 0 28 43 4 0 0
# graph
.tm1 <- .tm %>%
  filter(location_tmode_1 == 1) %>%
  mutate(tm = "[1] By car (driver)")
.tm2 <- .tm %>%
  filter(location_tmode_2 == 1) %>%
  mutate(tm = "[2] By car (passenger)")
.tm3 <- .tm %>%
  filter(location_tmode_3 == 1) %>%
  mutate(tm = "[3] By taxi/Uber")
.tm4 <- .tm %>%
  filter(location_tmode_4 == 1) %>%
  mutate(tm = "[4] On foot")
.tm5 <- .tm %>%
  filter(location_tmode_5 == 1) %>%
  mutate(tm = "[5] By bike")
.tm6 <- .tm %>%
  filter(location_tmode_6 == 1) %>%
  mutate(tm = "[6] By bus")
.tm7 <- .tm %>%
  filter(location_tmode_7 == 1) %>%
  mutate(tm = "[7] By train")
.tm99 <- .tm %>%
  filter(location_tmode_99 == 1) %>%
  mutate(tm = "[99] Other")
.tm <- bind_rows(.tm1, .tm2) %>%
  bind_rows(.tm3) %>%
  bind_rows(.tm4) %>%
  bind_rows(.tm5) %>%
  bind_rows(.tm6) %>%
  bind_rows(.tm7) %>%
  bind_rows(.tm99)

# histogram of answers
ggplot(data = .tm) +
  geom_bar(aes(x = fct_rev(description), fill = tm), position = "fill") +
  scale_fill_brewer(palette = "Set3", name = "Transport modes") +
  scale_y_continuous(labels = percent) +
  labs(y = "Proportion of transportation mode by location category", x = element_blank()) +
  coord_flip() +
  theme(legend.position = "bottom", legend.justification = c(0, 0), legend.text = element_text(size = 8)) +
  guides(fill = guide_legend(nrow = 3))

3.10.2 Visiting places alone

Based on the answers to the question Do you usually go to this place alone or with other people?.

loc_labels <- data.frame(location_category = c(2:26), description = c(
  " 2 [Other residence]",
  " 3 [Work]",
  " 4 [School/College/University]",
  " 5 [Supermarket]",
  " 6 [Public/farmer’s market]",
  " 7 [Bakery]",
  " 8 [Specialty food store]",
  " 9 [Convenience store/Dépanneur]",
  "10 [Liquor store/SAQ]",
  "11 [Bank]",
  "12 [Hair salon/barbershop]",
  "13 [Post office]",
  "14 [Drugstore]",
  "15 [Doctor/healthcare provider]",
  "16 [Public transit stop]",
  "17 [Leisure-time physical activity]",
  "18 [Park]",
  "19 [Cultural activity]",
  "20 [Volunteering place]",
  "21 [Religious/spiritual activity]",
  "22 [Restaurant, café, bar, etc.]",
  "23 [Take-out]",
  "24 [Walk]",
  "25 [Other place]",
  "26 [Social contact residence]"
))

# extract and summary stats
.alone <- locations %>%
  st_set_geometry(NULL) %>%
  filter(location_category != 1 & location_current == 1) %>%
  left_join(loc_labels) %>%
  mutate(location_alone_recode = case_when(
    location_alone2 == 1 ~ 1,
    location_alone2 == 2 ~ 0
  ))

.alone_grouped <- .alone %>%
  group_by(description) %>%
  dplyr::summarise(
    N = n(), "Visited alone" = sum(location_alone_recode),
    "Visited alone (%)" = round(sum(location_alone_recode) * 100.0 / n(), digits = 1)
  )

kable(.alone_grouped, caption = "Visiting places alone") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Visiting places alone
description N Visited alone Visited alone (%)
2 [Other residence] 1 0 0.0
3 [Work] 106 24 22.6
4 [School/College/University] 2 1 50.0
5 [Supermarket] 273 190 69.6
6 [Public/farmer’s market] 35 14 40.0
7 [Bakery] 53 28 52.8
8 [Specialty food store] 47 29 61.7
9 [Convenience store/Dépanneur] 13 11 84.6
11 [Bank] 72 67 93.1
12 [Hair salon/barbershop] 48 46 95.8
13 [Post office] 59 54 91.5
14 [Drugstore] 69 61 88.4
15 [Doctor/healthcare provider] 86 76 88.4
16 [Public transit stop] 97 76 78.4
17 [Leisure-time physical activity] 113 35 31.0
18 [Park] 180 49 27.2
19 [Cultural activity] 64 13 20.3
20 [Volunteering place] 37 12 32.4
21 [Religious/spiritual activity] 5 1 20.0
22 [Restaurant, café, bar, etc.] 196 42 21.4
23 [Take-out] 46 19 41.3
24 [Walk] 168 52 31.0
25 [Other place] 57 23 40.4
26 [Social contact residence] 78 NA NA
# histogram of answers
ggplot(data = .alone) +
  geom_bar(aes(x = fct_rev(description), fill = factor(location_alone2)), position = "fill") +
  scale_fill_brewer(palette = "Set3", name = "Visiting places", labels = c("N/A", "Alone", "With someone")) +
  scale_y_continuous(labels = percent) +
  labs(y = "Proportion of places visited alone", x = element_blank()) +
  coord_flip()

3.10.3 Visit frequency

Based on the answers to the question How often do you go there?.

loc_labels <- data.frame(location_category = c(2:26), description = c(
  " 2 [Other residence]",
  " 3 [Work]",
  " 4 [School/College/University]",
  " 5 [Supermarket]",
  " 6 [Public/farmer’s market]",
  " 7 [Bakery]",
  " 8 [Specialty food store]",
  " 9 [Convenience store/Dépanneur]",
  "10 [Liquor store/SAQ]",
  "11 [Bank]",
  "12 [Hair salon/barbershop]",
  "13 [Post office]",
  "14 [Drugstore]",
  "15 [Doctor/healthcare provider]",
  "16 [Public transit stop]",
  "17 [Leisure-time physical activity]",
  "18 [Park]",
  "19 [Cultural activity]",
  "20 [Volunteering place]",
  "21 [Religious/spiritual activity]",
  "22 [Restaurant, café, bar, etc.]",
  "23 [Take-out]",
  "24 [Walk]",
  "25 [Other place]",
  "26 [Social contact residence]"
))

# extract and summary stats
.freq <- locations %>%
  st_set_geometry(NULL) %>%
  filter(location_category != 1 & location_current == 1) %>%
  left_join(loc_labels)

.freq_grouped <- .freq %>%
  group_by(description) %>%
  dplyr::summarise(
    N = n(), min = min(location_freq_visit),
    max = max(location_freq_visit),
    mean = mean(location_freq_visit),
    median = median(location_freq_visit),
    sd = sd(location_freq_visit)
  )

kable(.freq_grouped, caption = "Visit frequency (expressed in times/year)") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
Visit frequency (expressed in times/year)
description N min max mean median sd
2 [Other residence] 1 36 36 36.00000 36 NA
3 [Work] 106 1 988 210.67925 260 123.284151
4 [School/College/University] 2 72 260 166.00000 166 132.936075
5 [Supermarket] 273 1 312 51.85348 36 58.004695
6 [Public/farmer’s market] 35 1 104 20.11429 12 23.574377
7 [Bakery] 53 2 208 29.88679 12 43.656729
8 [Specialty food store] 47 1 156 28.89362 20 29.368894
9 [Convenience store/Dépanneur] 13 4 156 38.00000 12 49.571497
11 [Bank] 72 1 60 16.15278 12 15.963567
12 [Hair salon/barbershop] 48 0 24 5.81250 4 5.114253
13 [Post office] 59 1 208 15.03390 6 27.930928
14 [Drugstore] 69 2 208 28.42029 12 36.971931
15 [Doctor/healthcare provider] 86 0 52 5.77907 2 8.430199
16 [Public transit stop] 97 0 260 23.64948 6 50.043740
17 [Leisure-time physical activity] 113 0 364 80.61947 52 88.179334
18 [Park] 180 0 364 54.72778 24 78.559079
19 [Cultural activity] 64 1 260 23.43750 9 40.063788
20 [Volunteering place] 37 2 364 76.08108 24 114.753692
21 [Religious/spiritual activity] 5 52 364 156.00000 52 147.078211
22 [Restaurant, café, bar, etc.] 196 0 520 26.09184 11 53.288203
23 [Take-out] 46 2 52 11.89130 12 10.511852
24 [Walk] 168 1 364 63.36310 24 88.074371
25 [Other place] 57 0 728 56.84211 24 106.741140
26 [Social contact residence] 78 1 364 48.84615 18 72.614277
# graph
ggplot(data = .freq) +
  geom_boxplot(aes(x = fct_rev(description), y = location_freq_visit)) +
  scale_y_continuous(limits = c(0, 365)) +
  labs(y = "Visits/year (Frequency over 1 visit/day not shown)", x = element_blank()) +
  coord_flip()

3.10.4 Spatial indicators: Camille Perchoux’s toolbox

Below is a list of indicators proposed by Camille Perchoux in her paper Assessing patterns of spatial behavior in health studies: Their socio-demographic determinants and associations with transportation modes (the RECORD Cohort Study).

-- Reading Camille tbx indics from Essence table
SELECT interact_id,
  n_acti_places, n_weekly_vst, n_acti_types,
  cvx_perimeter, cvx_surface,
  min_length, max_length, median_length, 
  pct_visits_neighb, 
  n_acti_prn, pct_visits_prn, prn_area_km2
FROM essence_table.essence_perchoux_tbx
WHERE city_id = 'Victoria' AND wave_id = 2 AND status = 'return'

3.10.5 Social indicators: Alexandre Naud’s toolbox

See Alex’s document for a more comprehensive presentation of the social indicators.

-- Reading Alex tbx indics from Essence table
SELECT interact_id,
  people_degree, 
  socialize_size, socialize_meet, socialize_chat,
  important_size, group_degree, simmelian
FROM essence_table.essence_naud_social
WHERE city_id = 'Victoria' AND wave_id = 2 AND status = 'return'

3.10.5.1 Number of people in the network (people_degree)

ggplot(ess.tab.alex) +
  geom_histogram(aes(x = people_degree))

kable(t(as.matrix(summary(ess.tab.alex$people_degree))), caption = "people_degree") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
people_degree
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 3 4.5 6.404255 9 36

3.10.5.2 Simmelian Brokerage (simmelian)

ggplot(ess.tab.alex) +
  geom_histogram(aes(x = simmelian))

kable(t(as.matrix(summary(ess.tab.alex$simmelian))), caption = "simmelian") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
simmelian
Min. 1st Qu. Median Mean 3rd Qu. Max. NA’s
1 3 9.589744 12.25945 19.26923 62.92308 1

3.10.5.3 Number of people with whom the participant like to socialize (socialize_size)

ggplot(ess.tab.alex) +
  geom_histogram(aes(x = socialize_size))

kable(t(as.matrix(summary(ess.tab.alex$socialize_size))), caption = "socialize_size") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
socialize_size
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 1 3.5 4.978723 6 25

3.10.5.4 Weekly face-to-face interactions among people with whom the participant like to socialize (socialize_meet)

ggplot(filter(ess.tab.alex, socialize_meet < 100)) +
  geom_histogram(aes(x = socialize_meet)) +
  annotate(geom = "text", x = 75, y = 100, label = "X-axis: values over 100 not displayed", alpha = .5)

kable(t(as.matrix(summary(ess.tab.alex$socialize_meet))), caption = "socialize_meet") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
socialize_meet
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 364 460 1220.106 734 52000

3.10.5.5 Weekly ICT interactions among people with whom the participant like to socialize (socialize_chat)

ggplot(filter(ess.tab.alex, socialize_chat < 100)) +
  geom_histogram(aes(x = socialize_chat)) +
  annotate(geom = "text", x = 55, y = 100, label = "X-axis: values over 100 not displayed", alpha = .5)

kable(t(as.matrix(summary(ess.tab.alex$socialize_chat))), caption = "socialize_chat") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
socialize_chat
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 314 552 892.0851 1040 5720

3.10.5.6 Number of people with whom the participant discuss important matters (important_size)

ggplot(ess.tab.alex) +
  geom_histogram(aes(x = important_size))

kable(t(as.matrix(summary(ess.tab.alex$important_size))), caption = "important_size") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
important_size
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 1 2 3.255319 4 19

3.10.5.7 Number of people in all groups (group_degree)

ggplot(filter(ess.tab.alex, group_degree < 100)) +
  geom_histogram(aes(x = group_degree)) +
  annotate(geom = "text", x = 20, y = 100, label = "X-axis: values over 100 not displayed", alpha = .5)

kable(t(as.matrix(summary(ess.tab.alex$group_degree))), caption = "group_degree") %>% kable_styling(bootstrap_options = "striped", full_width = T, position = "left")
group_degree
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 2.25 7 10.70213 16.5 74