Retarget Pilot Descriptive Analysis

knitr::opts_chunk$set(echo = TRUE, 
                      message = F, 
                      warning = F)
library(tidyverse)
library(here)
library(RColorBrewer)
library(janitor)
library(psych)
library(ggtext)
library(knitr)
library(kableExtra)
library(forcats)
library(gtools)
library(ggrepel)
library(DT)
library(papeR)
library(compareGroups)
library(ggcorrplot)

df_full = read.csv("Share_Your_Voice_2023_01_11_19_08_50.csv")

df_retarget = df_full %>% 
  filter(pilot_version == 'retarget_pilot_regular_ads')

Summary Statistics Tables

Who do they trust?

Question: On a scale from 1 to 5, how much would you say you trust the follwing people or organizations to give you good information about the vaccine?

df_retarget = 
  df_retarget %>%
  mutate(
    vax_status_retarget = case_when(
      num_dose == "0" ~ 0,
      num_dose %in% c("1", "2", "3") ~ 1
    ),
    vax_status_retarget_4 = case_when(
      num_dose == "0" ~ 0,
      num_dose == "1" ~ 1,
      num_dose == "2" ~ 2,
      num_dose == "3" ~ 3
    )
  )

df_retarget$vax_status_retarget = factor(df_retarget$vax_status_retarget, levels = c(0, 1))
df_retarget$vax_status_retarget_4 = factor(df_retarget$vax_status_retarget_4, levels = c(0,1,2,3))

df_retarget$country_answer[!df_retarget$country_answer %in% c("South Africa","Kenya","Nigeria","Ghana")] = NA
df_retarget$country_answer = factor(df_retarget$country_answer, levels = c("South Africa","Kenya","Nigeria","Ghana"))
df_retarget = df_retarget %>% filter(!is.na(country_answer))

## clean data
df_retarget$doctor[!df_retarget$doctor %in% c("1","2","3","4","5")] = NA
df_retarget$doctor = strtoi(df_retarget$doctor)
df_retarget$family[!df_retarget$family %in% c("1","2","3","4","5")] = NA
df_retarget$family = strtoi(df_retarget$family)
df_retarget$friends[!df_retarget$friends %in% c("1","2","3","4","5")] = NA
df_retarget$friends = strtoi(df_retarget$friends)
df_retarget$minister_religious_leader[!df_retarget$minister_religious_leader %in% c("1","2","3","4","5")] = NA
df_retarget$minister_religious_leader = strtoi(df_retarget$minister_religious_leader)
df_retarget$community_leader[!df_retarget$community_leader %in% c("1","2","3","4","5")] = NA
df_retarget$community_leader = strtoi(df_retarget$community_leader)

df_retarget$clinic_worker[!df_retarget$clinic_worker %in% c("1","2","3","4","5")] = NA
df_retarget$clinic_worker = strtoi(df_retarget$clinic_worker)
df_retarget$community_based_org[!df_retarget$community_based_org %in% c("1","2","3","4","5")] = NA
df_retarget$community_based_org = strtoi(df_retarget$community_based_org)
df_retarget$health_department[!df_retarget$health_department %in% c("1","2","3","4","5")] = NA
df_retarget$health_department = strtoi(df_retarget$health_department)
df_retarget$WHO[!df_retarget$WHO %in% c("1","2","3","4","5")] = NA
df_retarget$WHO = strtoi(df_retarget$WHO)
df_retarget$african_scientist[!df_retarget$african_scientist %in% c("1","2","3","4","5")] = NA
df_retarget$african_scientist = strtoi(df_retarget$african_scientist)
df_retarget$international_scientist[!df_retarget$international_scientist %in% c("1","2","3","4","5")] = NA
df_retarget$international_scientist = strtoi(df_retarget$international_scientist)
df_retarget$international_ngo[!df_retarget$international_ngo %in% c("1","2","3","4","5")] = NA
df_retarget$international_ngo = strtoi(df_retarget$international_ngo)
df_retarget$local_news_media[!df_retarget$local_news_media %in% c("1","2","3","4","5")] = NA
df_retarget$local_news_media = strtoi(df_retarget$local_news_media)
df_retarget$international_news_media[!df_retarget$international_news_media %in% c("1","2","3","4","5")] = NA
df_retarget$international_news_media = strtoi(df_retarget$international_news_media)

Summary Statistics

df_retarget %>%
  #select_if(is.numeric) %>%
  select(doctor, family, friends, `Ministers/Religious Leaders` = minister_religious_leader, `Community Leaders` = community_leader, `Local Health Clinic Worker` = clinic_worker, `Community-Based Organizations` = community_based_org, `Department of Health` = health_department, WHO, `African scientists` = african_scientist, `International Scientists` = international_scientist, `International NGOs` = international_ngo, `Local News/Media` = local_news_media, `International News/Media` = international_news_media) %>%
  describe(quant = c(.25,.75) ) %>%
  select(n, mean, sd, se, min, min, first_quartile = Q0.25, median, third_quartile = Q0.75, max) %>%
  clean_names(case = "title") %>%
  rename(SD = Sd, SE = Se) %>%
  kable(caption = "Summary Statistics for 'Who do they trust'", digits = 3)%>%
  kable_styling(bootstrap_options = c("striped", "hover"))

Summary Statistics for ‘Who do they trust’

	N	Mean	SD	SE	Min	First Quartile	Median	Third Quartile	Max
doctor	1602	3.721	1.443	0.036	1	3	4	5	5
family	1580	3.175	1.482	0.037	1	2	3	5	5
friends	1568	2.416	1.300	0.033	1	1	2	3	5
Ministers/Religious Leaders	1561	2.689	1.442	0.036	1	1	3	4	5
Community Leaders	1553	2.459	1.336	0.034	1	1	2	3	5
Local Health Clinic Worker	1544	3.498	1.384	0.035	1	2	4	5	5
Community-Based Organizations	1531	2.937	1.370	0.035	1	2	3	4	5
Department of Health	1526	3.635	1.504	0.039	1	2	4	5	5
WHO	1521	3.862	1.492	0.038	1	3	5	5	5
African scientists	1517	3.178	1.457	0.037	1	2	3	5	5
International Scientists	1509	3.318	1.486	0.038	1	2	4	5	5
International NGOs	1500	3.096	1.394	0.036	1	2	3	4	5
Local News/Media	1496	2.721	1.381	0.036	1	1	3	4	5
International News/Media	1493	2.903	1.388	0.036	1	2	3	4	5

Summary Statistics by Vaccination Status

df_retarget %>%
  select(vax_status_retarget, doctor, family, friends, `Ministers/Religious Leaders` = minister_religious_leader, `Community Leaders` = community_leader, `Local Health Clinic Worker` = clinic_worker, `Community-Based Organizations` = community_based_org, `Department of Health` = health_department, WHO, `African scientists` = african_scientist, `International Scientists` = international_scientist, `International NGOs` = international_ngo, `Local News/Media` = local_news_media, `International News/Media` = international_news_media) %>% 
  split(.$vax_status_retarget) %>% 
  map(describe) %>% 
  do.call(rbind, .) %>%
  data.frame() %>%
  select(n, mean , se) %>%
  rownames_to_column() %>%
  separate(rowname, c("vax_status_retarget", "variable"), sep = "\\.") %>%
  filter(variable != "vax_status_retarget*") %>%
  pivot_longer(cols = c("n", "mean", "se")) %>%
  mutate(column = paste(vax_status_retarget, name, sep = "_")) %>%
  select(column, variable, value) %>%
  pivot_wider(names_from = column) %>%
  kable(digits = 3,caption = "Summary Statistics for Trust Variables by Vaccination Status", 
        col.names = c("", "N", "Mean", "SE", "N", "Mean", "SE")) %>%
  kable_styling(bootstrap_options = c("striped", "hover"))%>%
  add_header_above(c(" " = 1, "Unvaccinated" = 3, "Vaccinated" = 3))

Summary Statistics for Trust Variables by Vaccination Status

	Unvaccinated			Vaccinated
	N	Mean	SE	N	Mean	SE
doctor	291	3.629	0.079	795	4.020	0.045
family	292	3.192	0.085	795	3.360	0.051
friends	292	2.226	0.068	795	2.600	0.046
Ministers/Religious Leaders	292	2.705	0.084	795	2.808	0.050
Community Leaders	292	2.260	0.074	795	2.605	0.046
Local Health Clinic Worker	292	3.134	0.076	795	3.845	0.044
Community-Based Organizations	292	2.760	0.071	795	3.157	0.047
Department of Health	292	3.295	0.088	795	3.980	0.047
WHO	292	3.767	0.085	795	4.169	0.046
African scientists	292	3.075	0.078	795	3.459	0.049
International Scientists	292	3.188	0.082	795	3.628	0.049
International NGOs	291	2.993	0.078	795	3.316	0.048
Local News/Media	292	2.455	0.073	795	2.923	0.048
International News/Media	292	2.723	0.075	795	3.116	0.049

Summary Statistics by Vaccination Dose

df_retarget %>%
  select(vax_status_retarget_4, doctor, family, friends, `Ministers/Religious Leaders` = minister_religious_leader, `Community Leaders` = community_leader, `Local Health Clinic Worker` = clinic_worker, `Community-Based Organizations` = community_based_org, `Department of Health` = health_department, WHO, `African scientists` = african_scientist, `International Scientists` = international_scientist, `International NGOs` = international_ngo, `Local News/Media` = local_news_media, `International News/Media` = international_news_media) %>% 
  split(.$vax_status_retarget_4) %>% 
  map(describe) %>% 
  do.call(rbind, .) %>%
  data.frame() %>%
  select(n, mean , se) %>%
  rownames_to_column() %>%
  separate(rowname, c("vax_status_retarget_4", "variable"), sep = "\\.") %>%
  filter(variable != "vax_status_retarget_4*") %>%
  pivot_longer(cols = c("n", "mean", "se")) %>%
  mutate(column = paste(vax_status_retarget_4, name, sep = "_")) %>%
  select(column, variable, value) %>%
  pivot_wider(names_from = column) %>%
  kable(digits = 3,caption = "Summary Statistics for Trust Variables by Vaccination Dose", 
        col.names = c("", "N", "Mean", "SE", "N", "Mean", "SE", "N", "Mean", "SE", "N", "Mean", "SE")) %>%
  kable_styling(bootstrap_options = c("striped", "hover")) %>%
  add_header_above(c(" " = 1, "Unvaccinated" = 3, "1 dose" = 3, "2 doses" = 3, "3 doses" = 3))

Summary Statistics for Trust Variables by Vaccination Dose

	Unvaccinated			1 dose			2 doses			3 doses
	N	Mean	SE	N	Mean	SE	N	Mean	SE	N	Mean	SE
doctor	291	3.629	0.079	231	4.026	0.079	376	4.008	0.066	188	4.037	0.095
family	292	3.192	0.085	231	3.281	0.094	376	3.410	0.072	188	3.356	0.110
friends	292	2.226	0.068	231	2.502	0.082	376	2.598	0.066	188	2.723	0.102
Ministers/Religious Leaders	292	2.705	0.084	231	2.740	0.091	376	2.819	0.074	188	2.867	0.102
Community Leaders	292	2.260	0.074	231	2.481	0.083	376	2.646	0.068	188	2.676	0.099
Local Health Clinic Worker	292	3.134	0.076	231	3.684	0.084	376	3.949	0.059	188	3.835	0.096
Community-Based Organizations	292	2.760	0.071	231	3.039	0.086	376	3.279	0.068	188	3.059	0.100
Department of Health	292	3.295	0.088	231	3.913	0.089	376	4.045	0.065	188	3.931	0.103
WHO	292	3.767	0.085	231	4.091	0.088	376	4.269	0.063	188	4.064	0.102
African scientists	292	3.075	0.078	231	3.424	0.094	376	3.503	0.069	188	3.415	0.102
International Scientists	292	3.188	0.082	231	3.662	0.090	376	3.662	0.069	188	3.516	0.108
International NGOs	291	2.993	0.078	231	3.234	0.089	376	3.465	0.065	188	3.117	0.106
Local News/Media	292	2.455	0.073	231	2.779	0.091	376	3.029	0.069	188	2.888	0.102
International News/Media	292	2.723	0.075	231	3.017	0.090	376	3.184	0.071	188	3.101	0.101

Summary Statistics by Country

df_retarget %>%
  select(country_answer, doctor, family, friends, `Ministers/Religious Leaders` = minister_religious_leader, `Community Leaders` = community_leader, `Local Health Clinic Worker` = clinic_worker, `Community-Based Organizations` = community_based_org, `Department of Health` = health_department, WHO, `African scientists` = african_scientist, `International Scientists` = international_scientist, `International NGOs` = international_ngo, `Local News/Media` = local_news_media, `International News/Media` = international_news_media) %>% 
  split(.$country_answer) %>% 
  map(describe) %>% 
  do.call(rbind, .) %>%
  data.frame() %>%
  select(n, mean , se) %>%
  rownames_to_column() %>%
  separate(rowname, c("country_answer", "variable"), sep = "\\.") %>%
  filter(variable != "country_answer*") %>%
  pivot_longer(cols = c("n", "mean", "se")) %>%
  mutate(column = paste(country_answer, name, sep = "_")) %>%
  select(column, variable, value) %>%
  pivot_wider(names_from = column) %>%
  kable(digits = 3,caption = "Summary Statistics for Trust Variables by Country", 
        col.names = c("", "N", "Mean", "SE", "N", "Mean", "SE", "N", "Mean", "SE", "N", "Mean", "SE")) %>%
  kable_styling(bootstrap_options = c("striped", "hover")) %>%
  add_header_above(c(" " = 1, "South Africa" = 3, "Kenya" = 3, "Nigeria" = 3, "Ghana" = 3))

Summary Statistics for Trust Variables by Country

	South Africa			Kenya			Nigeria			Ghana
	N	Mean	SE	N	Mean	SE	N	Mean	SE	N	Mean	SE
doctor	435	3.667	0.073	408	3.652	0.075	334	3.793	0.075	425	3.786	0.066
family	429	3.086	0.074	405	3.264	0.071	331	3.387	0.080	415	3.010	0.073
friends	423	2.156	0.061	404	2.522	0.064	329	2.581	0.069	412	2.447	0.066
Ministers/Religious Leaders	421	2.373	0.069	403	2.826	0.070	328	2.963	0.077	409	2.658	0.074
Community Leaders	418	2.165	0.064	402	2.724	0.064	326	2.442	0.074	407	2.514	0.068
Local Health Clinic Worker	417	3.585	0.070	402	3.557	0.068	324	3.373	0.076	401	3.449	0.069
Community-Based Organizations	414	2.819	0.069	401	3.182	0.068	320	2.878	0.073	396	2.861	0.068
Department of Health	411	3.545	0.078	401	3.626	0.073	320	3.747	0.082	394	3.647	0.075
WHO	409	3.592	0.081	400	3.902	0.072	319	4.163	0.073	393	3.858	0.075
African scientists	409	3.042	0.078	399	3.043	0.070	317	3.334	0.079	392	3.332	0.071
International Scientists	407	2.943	0.076	399	3.328	0.072	314	3.640	0.078	389	3.440	0.075
International NGOs	404	2.703	0.070	398	3.234	0.070	313	3.383	0.072	385	3.132	0.071
Local News/Media	401	2.476	0.070	397	2.844	0.069	312	2.753	0.076	386	2.821	0.070
International News/Media	399	2.536	0.068	396	3.008	0.069	312	3.106	0.076	386	3.010	0.071

• This table also located here

Sorting Questions

Questions: Tell me more about what YOU believe by telling me how much you agree or disagree with the statements you’re about to read.

• 1 = I Disagree Strongly
• 2 = I Disagree
• 3 = I’m Unsure
• 4 = I Agree
• 5 = I Agree Strongly

## clean data
df_retarget$covid_is_a_problem[!df_retarget$covid_is_a_problem %in% c("1","2","3","4","5")] = NA
df_retarget$covid_is_a_problem = strtoi(df_retarget$covid_is_a_problem)
df_retarget$covid_is_problem_my_country[!df_retarget$covid_is_problem_my_country %in% c("1","2","3","4","5")] = NA
df_retarget$covid_is_problem_my_country = strtoi(df_retarget$covid_is_problem_my_country)
df_retarget$vax_is_safe[!df_retarget$vax_is_safe %in% c("1","2","3","4","5")] = NA
df_retarget$vax_is_safe = strtoi(df_retarget$vax_is_safe)
df_retarget$vax_prevent_sick_death[!df_retarget$vax_prevent_sick_death %in% c("1","2","3","4","5")] = NA
df_retarget$vax_prevent_sick_death = strtoi(df_retarget$vax_prevent_sick_death)
df_retarget$need_vax_for_protection[!df_retarget$need_vax_for_protection %in% c("1","2","3","4","5")] = NA
df_retarget$need_vax_for_protection = strtoi(df_retarget$need_vax_for_protection)
df_retarget$vax_safer_covid[!df_retarget$vax_safer_covid %in% c("1","2","3","4","5")] = NA
df_retarget$vax_safer_covid = strtoi(df_retarget$vax_safer_covid)
df_retarget$developer_want_to_help[!df_retarget$developer_want_to_help %in% c("1","2","3","4","5")] = NA
df_retarget$developer_want_to_help = strtoi(df_retarget$developer_want_to_help)
df_retarget$health_worker_want_to_help[!df_retarget$health_worker_want_to_help %in% c("1","2","3","4","5")] = NA
df_retarget$health_worker_want_to_help = strtoi(df_retarget$health_worker_want_to_help)
df_retarget$gov_want_to_help[!df_retarget$gov_want_to_help %in% c("1","2","3","4","5")] = NA
df_retarget$gov_want_to_help = strtoi(df_retarget$gov_want_to_help)
df_retarget$important_to_protect_myself[!df_retarget$important_to_protect_myself %in% c("1","2","3","4","5")] = NA
df_retarget$important_to_protect_myself = strtoi(df_retarget$important_to_protect_myself)
df_retarget$important_to_protect_other[!df_retarget$important_to_protect_other %in% c("1","2","3","4","5")] = NA
df_retarget$important_to_protect_other = strtoi(df_retarget$important_to_protect_other)
df_retarget$vax_moral[!df_retarget$vax_moral %in% c("1","2","3","4","5")] = NA
df_retarget$vax_moral = strtoi(df_retarget$vax_moral)
df_retarget$worry_short_term_side_effect[!df_retarget$worry_short_term_side_effect %in% c("1","2","3","4","5")] = NA
df_retarget$worry_short_term_side_effect = strtoi(df_retarget$worry_short_term_side_effect)
df_retarget$worry_long_term_side_effect[!df_retarget$worry_long_term_side_effect %in% c("1","2","3","4","5")] = NA
df_retarget$worry_long_term_side_effect = strtoi(df_retarget$worry_long_term_side_effect)
df_retarget$covid_is_real[!df_retarget$covid_is_real %in% c("1","2","3","4","5")] = NA
df_retarget$covid_is_real = strtoi(df_retarget$covid_is_real)
df_retarget$probably_exposed[!df_retarget$probably_exposed %in% c("1","2","3","4","5")] = NA
df_retarget$probably_exposed = strtoi(df_retarget$probably_exposed)
df_retarget$afraid_needle[!df_retarget$afraid_needle %in% c("1","2","3","4","5")] = NA
df_retarget$afraid_needle = strtoi(df_retarget$afraid_needle)
df_retarget$deeply_religious[!df_retarget$deeply_religious %in% c("1","2","3","4","5")] = NA
df_retarget$deeply_religious = strtoi(df_retarget$deeply_religious)
df_retarget$important_moral[!df_retarget$important_moral %in% c("1","2","3","4","5")] = NA
df_retarget$important_moral = strtoi(df_retarget$important_moral)
df_retarget$fit_in_group_importance[!df_retarget$fit_in_group_importance %in% c("1","2","3","4","5")] = NA
df_retarget$fit_in_group_importance = strtoi(df_retarget$fit_in_group_importance)
df_retarget$responsible_importance[!df_retarget$responsible_importance %in% c("1","2","3","4","5")] = NA
df_retarget$responsible_importance = strtoi(df_retarget$responsible_importance)

Summary Statistics

df_retarget %>%
  #select_if(is.numeric) %>%
  select(covid_is_a_problem, covid_is_problem_my_country,vax_is_safe,vax_prevent_sick_death, need_vax_for_protection,vax_safer_covid,developer_want_to_help,health_worker_want_to_help,gov_want_to_help,important_to_protect_myself,important_to_protect_other,vax_moral,worry_short_term_side_effect,worry_long_term_side_effect,covid_is_real,probably_exposed,afraid_needle,deeply_religious,important_moral,fit_in_group_importance,responsible_importance) %>%
  describe(quant = c(.25,.75) ) %>%
  select(n, mean, sd, se, min, min, first_quartile = Q0.25, median, third_quartile = Q0.75, max) %>%
  clean_names(case = "title") %>%
  rename(SD = Sd, SE = Se) %>%
  kable(caption = "Summary Statistics for 'Sorting Questions'", digits = 3)%>%
  kable_styling(bootstrap_options = c("striped", "hover"))

Summary Statistics for ‘Sorting Questions’

	N	Mean	SD	SE	Min	First Quartile	Median	Third Quartile	Max
covid_is_a_problem	1137	3.170	1.213	0.036	1	2	3.0	4	5
covid_is_problem_my_country	1134	3.061	1.364	0.041	1	2	3.0	4	5
vax_is_safe	1131	3.515	1.218	0.036	1	3	4.0	4	5
vax_prevent_sick_death	1129	3.345	1.227	0.037	1	3	3.0	4	5
need_vax_for_protection	1128	3.922	1.211	0.036	1	4	4.0	5	5
vax_safer_covid	1125	4.054	1.150	0.034	1	4	4.0	5	5
developer_want_to_help	1122	3.860	1.119	0.033	1	3	4.0	5	5
health_worker_want_to_help	1121	4.046	1.012	0.030	1	4	4.0	5	5
gov_want_to_help	1122	3.955	1.052	0.031	1	4	4.0	5	5
important_to_protect_myself	1116	4.404	0.915	0.027	1	4	5.0	5	5
important_to_protect_other	1112	4.374	0.900	0.027	1	4	5.0	5	5
vax_moral	1112	3.410	1.192	0.036	1	3	4.0	4	5
worry_short_term_side_effect	1108	3.540	1.172	0.035	1	3	4.0	4	5
worry_long_term_side_effect	1106	3.788	1.183	0.036	1	3	4.0	5	5
covid_is_real	1104	4.125	1.110	0.033	1	4	4.5	5	5
probably_exposed	1103	2.583	1.241	0.037	1	1	3.0	3	5
afraid_needle	1100	2.783	1.459	0.044	1	1	2.0	4	5
deeply_religious	1097	3.549	1.280	0.039	1	2	4.0	5	5
important_moral	1094	4.102	1.020	0.031	1	4	4.0	5	5
fit_in_group_importance	1094	3.431	1.325	0.040	1	2	4.0	4	5
responsible_importance	1091	4.163	1.021	0.031	1	4	4.0	5	5

Variable Descriptions:

• covid_is_a_problem: People are still dying from COVID
• covid_is_problem_my_country: COVID is a problem in [my country]
• vax_is_safe: I think the COVID vaccines are safe
• vax_prevent_sick_death: COVID vaccines help prevent serious sickness and death
• need_vax_for_protection: You need a vaccine for protection from sickness (not because you are sick)
• vax_safer_covid: Getting the vaccine is much safer than getting COVID
• developer_want_to_help: I think the people who developed the vaccine wanted to help people
• health_worker_want_to_help: I think my local healthcare workers want me to be healthy and well
• gov_want_to_help: I think my government’s department of health workers want me to be healthy and well
• important_to_protect_myself: It is important to me that I protect myself from the effects of COVID
• important_to_protect_other: It is important to me that I protect others from the effects of COVID
• vax_moral: Getting vaccinated is a moral issue
• worry_short_term_side_effect: I worry about short-term side effects of the COVID vaccine
• worry_long_term_side_effect: I worry about long-term side effects of the COVID vaccine
• covid_is_real: COVID has killed millions of people worldwide
• probably_exposed: I will probably be exposed to someone with COVID over the next year
• afraid_needle: I am very afraid of needles
• deeply_religious: I am a deeply religious person
• important_moral: It is important to me that I be a moral person
• fit_in_group_importance: It is important to me to feel like I “fit in” in with my group
• responsible_importance: It is important to me to feel like I am a responsible member of my community

Summary Statistics by Vaccination Status

df_retarget %>%
  select(vax_status_retarget, covid_is_a_problem, covid_is_problem_my_country,vax_is_safe,vax_prevent_sick_death, need_vax_for_protection,vax_safer_covid,developer_want_to_help,health_worker_want_to_help,gov_want_to_help,important_to_protect_myself,important_to_protect_other,vax_moral,worry_short_term_side_effect,worry_long_term_side_effect,covid_is_real,probably_exposed,afraid_needle,deeply_religious,important_moral,fit_in_group_importance,responsible_importance) %>% 
  split(.$vax_status_retarget) %>% 
  map(describe) %>% 
  do.call(rbind, .) %>%
  data.frame() %>%
  select(n, mean , se) %>%
  rownames_to_column() %>%
  separate(rowname, c("vax_status_retarget", "variable"), sep = "\\.") %>%
  filter(variable != "vax_status_retarget*") %>%
  pivot_longer(cols = c("n", "mean", "se")) %>%
  mutate(column = paste(vax_status_retarget, name, sep = "_")) %>%
  select(column, variable, value) %>%
  pivot_wider(names_from = column) %>%
  mutate(difference = `1_mean` - `0_mean`) %>%
  kable(digits = 3,caption = "Summary Statistics for Trust Variables by Vaccination Status", 
        col.names = c("", "N", "Mean", "SE", "N", "Mean", "SE", "Mean Difference")) %>%
  kable_styling(bootstrap_options = c("striped", "hover"))%>%
  add_header_above(c(" " = 1, "Unvaccinated" = 3, "Vaccinated" = 3, "Difference" = 1))

Summary Statistics for Trust Variables by Vaccination Status

	Unvaccinated			Vaccinated			Difference
	N	Mean	SE	N	Mean	SE	Mean Difference
covid_is_a_problem	292	2.911	0.070	795	3.278	0.043	0.367
covid_is_problem_my_country	292	2.798	0.081	795	3.153	0.048	0.356
vax_is_safe	292	2.853	0.071	794	3.761	0.040	0.908
vax_prevent_sick_death	292	2.863	0.071	794	3.540	0.042	0.677
need_vax_for_protection	292	3.503	0.079	795	4.093	0.039	0.590
vax_safer_covid	292	3.493	0.075	795	4.263	0.036	0.770
developer_want_to_help	292	3.486	0.071	795	3.990	0.038	0.504
health_worker_want_to_help	292	3.712	0.066	794	4.173	0.033	0.460
gov_want_to_help	292	3.562	0.067	795	4.113	0.034	0.552
important_to_protect_myself	292	4.209	0.059	793	4.484	0.030	0.275
important_to_protect_other	292	4.182	0.059	793	4.456	0.030	0.275
vax_moral	292	2.990	0.072	794	3.567	0.041	0.577
worry_short_term_side_effect	292	3.661	0.072	794	3.499	0.041	-0.162
worry_long_term_side_effect	292	3.825	0.074	794	3.775	0.041	-0.051
covid_is_real	292	3.925	0.071	795	4.206	0.038	0.282
probably_exposed	292	2.274	0.071	795	2.694	0.044	0.420
afraid_needle	292	2.842	0.087	794	2.757	0.051	-0.086
deeply_religious	292	3.387	0.075	793	3.609	0.045	0.222
important_moral	292	4.010	0.063	794	4.136	0.035	0.126
fit_in_group_importance	292	3.161	0.080	795	3.526	0.046	0.365
responsible_importance	292	3.942	0.066	795	4.242	0.034	0.300

Variable Descriptions:

• covid_is_a_problem: People are still dying from COVID
• covid_is_problem_my_country: COVID is a problem in [my country]
• vax_is_safe: I think the COVID vaccines are safe
• vax_prevent_sick_death: COVID vaccines help prevent serious sickness and death
• need_vax_for_protection: You need a vaccine for protection from sickness (not because you are sick)
• vax_safer_covid: Getting the vaccine is much safer than getting COVID
• developer_want_to_help: I think the people who developed the vaccine wanted to help people
• health_worker_want_to_help: I think my local healthcare workers want me to be healthy and well
• gov_want_to_help: I think my government’s department of health workers want me to be healthy and well
• important_to_protect_myself: It is important to me that I protect myself from the effects of COVID
• important_to_protect_other: It is important to me that I protect others from the effects of COVID
• vax_moral: Getting vaccinated is a moral issue
• worry_short_term_side_effect: I worry about short-term side effects of the COVID vaccine
• worry_long_term_side_effect: I worry about long-term side effects of the COVID vaccine
• covid_is_real: COVID has killed millions of people worldwide
• probably_exposed: I will probably be exposed to someone with COVID over the next year
• afraid_needle: I am very afraid of needles
• deeply_religious: I am a deeply religious person
• important_moral: It is important to me that I be a moral person
• fit_in_group_importance: It is important to me to feel like I “fit in” in with my group
• responsible_importance: It is important to me to feel like I am a responsible member of my community

Summary Statistics by Vaccination Dose

df_retarget %>%
  select(vax_status_retarget_4,covid_is_a_problem,covid_is_problem_my_country,vax_is_safe,vax_prevent_sick_death, need_vax_for_protection,vax_safer_covid,developer_want_to_help,health_worker_want_to_help,gov_want_to_help,important_to_protect_myself,important_to_protect_other,vax_moral,worry_short_term_side_effect,worry_long_term_side_effect,covid_is_real,probably_exposed,afraid_needle,deeply_religious,important_moral,fit_in_group_importance,responsible_importance) %>% 
  split(.$vax_status_retarget_4) %>% 
  map(describe) %>% 
  do.call(rbind, .) %>%
  data.frame() %>%
  select(n, mean , se) %>%
  rownames_to_column() %>%
  separate(rowname, c("vax_status_retarget_4", "variable"), sep = "\\.") %>%
  filter(variable != "vax_status_retarget_4*") %>%
  pivot_longer(cols = c("n", "mean", "se")) %>%
  mutate(column = paste(vax_status_retarget_4, name, sep = "_")) %>%
  select(column, variable, value) %>%
  pivot_wider(names_from = column) %>%
  kable(digits = 3,caption = "Summary Statistics for Trust Variables by Vaccination Dose", 
        col.names = c("", "N", "Mean", "SE", "N", "Mean", "SE", "N", "Mean", "SE", "N", "Mean", "SE")) %>%
  kable_styling(bootstrap_options = c("striped", "hover")) %>%
  add_header_above(c(" " = 1, "Unvaccinated" = 3, "1 dose" = 3, "2 doses" = 3, "3 doses" = 3))

Summary Statistics for Trust Variables by Vaccination Dose

	Unvaccinated			1 dose			2 doses			3 doses
	N	Mean	SE	N	Mean	SE	N	Mean	SE	N	Mean	SE
covid_is_a_problem	292	2.911	0.070	231	3.186	0.079	376	3.303	0.060	188	3.340	0.095
covid_is_problem_my_country	292	2.798	0.081	231	3.095	0.092	376	3.144	0.065	188	3.245	0.106
vax_is_safe	292	2.853	0.071	231	3.550	0.079	375	3.877	0.052	188	3.787	0.088
vax_prevent_sick_death	292	2.863	0.071	231	3.385	0.083	375	3.525	0.059	188	3.761	0.081
need_vax_for_protection	292	3.503	0.079	231	3.866	0.081	376	4.178	0.052	188	4.202	0.080
vax_safer_covid	292	3.493	0.075	231	4.065	0.075	376	4.348	0.048	188	4.335	0.075
developer_want_to_help	292	3.486	0.071	231	3.866	0.075	376	4.101	0.048	188	3.920	0.086
health_worker_want_to_help	292	3.712	0.066	231	4.000	0.070	375	4.224	0.045	188	4.282	0.063
gov_want_to_help	292	3.562	0.067	231	3.970	0.072	376	4.162	0.044	188	4.191	0.073
important_to_protect_myself	292	4.209	0.059	230	4.339	0.063	375	4.539	0.040	188	4.553	0.063
important_to_protect_other	292	4.182	0.059	230	4.309	0.064	375	4.515	0.038	188	4.521	0.058
vax_moral	292	2.990	0.072	230	3.465	0.078	376	3.556	0.057	188	3.713	0.086
worry_short_term_side_effect	292	3.661	0.072	230	3.383	0.078	376	3.508	0.057	188	3.622	0.085
worry_long_term_side_effect	292	3.825	0.074	230	3.726	0.079	376	3.798	0.057	188	3.787	0.089
covid_is_real	292	3.925	0.071	231	4.134	0.072	376	4.215	0.053	188	4.277	0.077
probably_exposed	292	2.274	0.071	231	2.602	0.083	376	2.638	0.061	188	2.920	0.094
afraid_needle	292	2.842	0.087	231	2.745	0.097	375	2.675	0.070	188	2.936	0.115
deeply_religious	292	3.387	0.075	230	3.330	0.085	375	3.653	0.064	188	3.862	0.093
important_moral	292	4.010	0.063	230	4.000	0.071	376	4.173	0.048	188	4.229	0.074
fit_in_group_importance	292	3.161	0.080	231	3.312	0.088	376	3.606	0.064	188	3.628	0.098
responsible_importance	292	3.942	0.066	231	4.065	0.070	376	4.306	0.047	188	4.330	0.067

Variable Descriptions:

• covid_is_a_problem: People are still dying from COVID
• covid_is_problem_my_country: COVID is a problem in [my country]
• vax_is_safe: I think the COVID vaccines are safe
• vax_prevent_sick_death: COVID vaccines help prevent serious sickness and death
• need_vax_for_protection: You need a vaccine for protection from sickness (not because you are sick)
• vax_safer_covid: Getting the vaccine is much safer than getting COVID
• developer_want_to_help: I think the people who developed the vaccine wanted to help people
• health_worker_want_to_help: I think my local healthcare workers want me to be healthy and well
• gov_want_to_help: I think my government’s department of health workers want me to be healthy and well
• important_to_protect_myself: It is important to me that I protect myself from the effects of COVID
• important_to_protect_other: It is important to me that I protect others from the effects of COVID
• vax_moral: Getting vaccinated is a moral issue
• worry_short_term_side_effect: I worry about short-term side effects of the COVID vaccine
• worry_long_term_side_effect: I worry about long-term side effects of the COVID vaccine
• covid_is_real: COVID has killed millions of people worldwide
• probably_exposed: I will probably be exposed to someone with COVID over the next year
• afraid_needle: I am very afraid of needles
• deeply_religious: I am a deeply religious person
• important_moral: It is important to me that I be a moral person
• fit_in_group_importance: It is important to me to feel like I “fit in” in with my group
• responsible_importance: It is important to me to feel like I am a responsible member of my community

Summary Statistics by Country

df_retarget %>%
  select(country_answer,covid_is_a_problem,covid_is_problem_my_country,vax_is_safe,vax_prevent_sick_death, need_vax_for_protection,vax_safer_covid,developer_want_to_help,health_worker_want_to_help,gov_want_to_help,important_to_protect_myself,important_to_protect_other,vax_moral,worry_short_term_side_effect,worry_long_term_side_effect,covid_is_real,probably_exposed,afraid_needle,deeply_religious,important_moral,fit_in_group_importance,responsible_importance) %>% 
  split(.$country_answer) %>% 
  map(describe) %>% 
  do.call(rbind, .) %>%
  data.frame() %>%
  select(n, mean , se) %>%
  rownames_to_column() %>%
  separate(rowname, c("country_answer", "variable"), sep = "\\.") %>%
  filter(variable != "country_answer*") %>%
  pivot_longer(cols = c("n", "mean", "se")) %>%
  mutate(column = paste(country_answer, name, sep = "_")) %>%
  select(column, variable, value) %>%
  pivot_wider(names_from = column) %>%
  kable(digits = 3,caption = "Summary Statistics for Trust Variables by Country", 
        col.names = c("", "N", "Mean", "SE", "N", "Mean", "SE", "N", "Mean", "SE", "N", "Mean", "SE")) %>%
  kable_styling(bootstrap_options = c("striped", "hover")) %>%
  add_header_above(c(" " = 1, "South Africa" = 3, "Kenya" = 3, "Nigeria" = 3, "Ghana" = 3))

Summary Statistics for Trust Variables by Country

	South Africa			Kenya			Nigeria			Ghana
	N	Mean	SE	N	Mean	SE	N	Mean	SE	N	Mean	SE
covid_is_a_problem	280	3.086	0.077	333	3.261	0.066	259	3.266	0.068	265	3.049	0.076
covid_is_problem_my_country	280	3.257	0.088	333	3.207	0.073	259	2.865	0.082	262	2.859	0.080
vax_is_safe	278	3.144	0.082	333	3.670	0.062	258	3.663	0.071	262	3.565	0.071
vax_prevent_sick_death	276	3.163	0.080	333	3.492	0.067	258	3.457	0.071	262	3.240	0.071
need_vax_for_protection	275	3.644	0.082	333	3.991	0.067	258	4.016	0.068	262	4.034	0.068
vax_safer_covid	274	3.715	0.081	332	4.187	0.056	258	4.143	0.065	261	4.153	0.070
developer_want_to_help	273	3.516	0.081	331	3.915	0.057	258	4.186	0.056	260	3.827	0.066
health_worker_want_to_help	272	3.812	0.074	331	4.085	0.053	258	4.140	0.059	260	4.150	0.052
gov_want_to_help	273	3.711	0.075	331	4.066	0.056	258	4.004	0.058	260	4.023	0.059
important_to_protect_myself	269	4.223	0.069	330	4.388	0.052	258	4.469	0.048	259	4.548	0.043
important_to_protect_other	268	4.157	0.068	329	4.426	0.049	258	4.453	0.045	257	4.455	0.050
vax_moral	268	3.340	0.073	329	3.474	0.067	258	3.554	0.069	257	3.257	0.076
worry_short_term_side_effect	265	3.551	0.079	329	3.456	0.061	258	3.609	0.070	256	3.566	0.073
worry_long_term_side_effect	265	3.913	0.074	328	3.796	0.062	257	3.584	0.078	256	3.852	0.072
covid_is_real	264	4.064	0.073	328	4.061	0.059	257	4.132	0.068	255	4.263	0.068
probably_exposed	264	2.883	0.080	328	2.604	0.066	257	2.268	0.075	254	2.563	0.075
afraid_needle	262	2.832	0.097	328	2.713	0.078	257	2.774	0.091	253	2.830	0.089
deeply_religious	261	3.398	0.087	327	3.560	0.071	257	3.619	0.072	252	3.619	0.080
important_moral	261	3.904	0.074	327	4.156	0.056	257	4.233	0.054	249	4.104	0.061
fit_in_group_importance	261	2.981	0.092	327	3.511	0.069	257	3.514	0.082	249	3.711	0.073
responsible_importance	261	3.969	0.070	326	4.181	0.058	257	4.206	0.058	247	4.300	0.058

Variable Descriptions:

• covid_is_a_problem: People are still dying from COVID
• covid_is_problem_my_country: COVID is a problem in [my country]
• vax_is_safe: I think the COVID vaccines are safe
• vax_prevent_sick_death: COVID vaccines help prevent serious sickness and death
• need_vax_for_protection: You need a vaccine for protection from sickness (not because you are sick)
• vax_safer_covid: Getting the vaccine is much safer than getting COVID
• developer_want_to_help: I think the people who developed the vaccine wanted to help people
• health_worker_want_to_help: I think my local healthcare workers want me to be healthy and well
• gov_want_to_help: I think my government’s department of health workers want me to be healthy and well
• important_to_protect_myself: It is important to me that I protect myself from the effects of COVID
• important_to_protect_other: It is important to me that I protect others from the effects of COVID
• vax_moral: Getting vaccinated is a moral issue
• worry_short_term_side_effect: I worry about short-term side effects of the COVID vaccine
• worry_long_term_side_effect: I worry about long-term side effects of the COVID vaccine
• covid_is_real: COVID has killed millions of people worldwide
• probably_exposed: I will probably be exposed to someone with COVID over the next year
• afraid_needle: I am very afraid of needles
• deeply_religious: I am a deeply religious person
• important_moral: It is important to me that I be a moral person
• fit_in_group_importance: It is important to me to feel like I “fit in” in with my group
• responsible_importance: It is important to me to feel like I am a responsible member of my community

Vaccination Status/Attitudes

1. Vaccine doses recieved

df_retarget$num_dose[!df_retarget$num_dose %in% c("0", "1","2","3")] = NA
df_retarget$num_dose = strtoi(df_retarget$num_dose)
df_retarget$num_dose = as.factor(df_retarget$num_dose)
dose = df_retarget %>% filter(!is.na(num_dose))
dose_plot <- dose %>% count(num_dose) %>% mutate(percentage = n / nrow(dose))
ggplot(dose_plot, aes(x = fct_inorder(num_dose), y = n, fill = num_dose)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Vaccine doses recieved (n = ", sum(dose_plot$n), ")"),
          subtitle = "How many COVID vaccine doses have you recieved?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "Vaccine doses recieved", y = "count")

df_retarget %>%
  drop_na(country_answer, num_dose) %>%
  count(country_answer, num_dose) %>%
  mutate(
    num_dose = case_when(
      num_dose == 0 ~ "unvaccinated",
      num_dose == 1 ~ "1 dose",
      num_dose == 2 ~ "2 doses",
      num_dose == 3 ~ "3 doses",
    ),
    #`Analysis 3 - impediment theme` = `Analysis 3 - impediment theme` %>% str_to_sentence()
  ) %>%
  drop_na(country_answer, num_dose) %>%
  arrange(country_answer) %>%
  mutate(num_dose = fct_inorder(num_dose)) %>%
  ggplot(aes(country_answer, n, fill = num_dose)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "country",
    y = "Count",
    fill = "",
    title = "Distribution of vaccine doses recieved by country"
  )

2. Get a COVID vaccine/booster next year

df_retarget$vax_next_year[!df_retarget$vax_next_year %in% c("1","2","3","4","5")] = NA
df_retarget$vax_next_year = strtoi(df_retarget$vax_next_year)
df_retarget$vax_next_year = as.factor(df_retarget$vax_next_year)
vax_future = df_retarget %>% filter(!is.na(vax_next_year))
vax_future_plot <- vax_future %>% count(vax_next_year) %>% mutate(percentage = n / nrow(vax_future))
ggplot(vax_future_plot, aes(x = fct_inorder(vax_next_year), y = n, fill = vax_next_year)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("How likely to get a COVID vaccine/booster next year (n = ", sum(dose_plot$n), ")"),
          subtitle = "How likely are you to get a COVID vaccine/booster next year?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "how likely to get a vaccine/booster", y = "count")

df_retarget %>%
  mutate(
    vax_status_retarget = case_when(
      vax_status_retarget == 0 ~ "unvaccinated",
      vax_status_retarget == 1 ~ "vaccinated"
    )
  ) %>%
  drop_na(vax_status_retarget, vax_next_year) %>%
  count(vax_status_retarget, vax_next_year) %>%
  mutate(
    vax_next_year = case_when(
      vax_next_year == 1 ~ "1 = very unlikely",
      vax_next_year == 2 ~ "2 = somewhat unlikely",
      vax_next_year == 3 ~ "3 = unsure",
      vax_next_year == 4 ~ "4 = probably will",
      vax_next_year == 5 ~ "5 = definitely will",
    ),
    #`Analysis 3 - impediment theme` = `Analysis 3 - impediment theme` %>% str_to_sentence()
  ) %>%
  arrange(vax_status_retarget) %>%
  mutate(vax_next_year = fct_inorder(vax_next_year)) %>%
  ggplot(aes(vax_status_retarget, n, fill = vax_next_year)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "vaccination status",
    y = "Count",
    fill = "",
    title = "Distribution of likelihood by vaccination status"
  )

df_retarget %>%
  drop_na(country_answer, vax_next_year) %>%
  count(country_answer, vax_next_year) %>%
  mutate(
    vax_next_year = case_when(
      vax_next_year == 1 ~ "1 = very unlikely",
      vax_next_year == 2 ~ "2 = somewhat unlikely",
      vax_next_year == 3 ~ "3 = unsure",
      vax_next_year == 4 ~ "4 = probably will",
      vax_next_year == 5 ~ "5 = definitely will",
    ),
    #`Analysis 3 - impediment theme` = `Analysis 3 - impediment theme` %>% str_to_sentence()
  ) %>%
  arrange(country_answer) %>%
  mutate(vax_next_year = fct_inorder(vax_next_year)) %>%
  drop_na(country_answer, vax_next_year) %>%
  ggplot(aes(country_answer, n, fill = vax_next_year)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "country",
    y = "Count",
    fill = "",
    title = "Distribution of likelihood by country"
  )

3. Recieved any other vaccines

df_retarget$receive_other_vax[!df_retarget$receive_other_vax %in% c("yes","no")] = NA
df_retarget$receive_other_vax = as.factor(df_retarget$receive_other_vax)
other_vax = df_retarget %>% filter(!is.na(receive_other_vax))
other_vax_plot <- other_vax %>% count(receive_other_vax) %>% mutate(percentage = n / nrow(other_vax))
ggplot(other_vax_plot, aes(x = fct_inorder(receive_other_vax), y = n, fill = receive_other_vax)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Recieved any other vaccines (n = ", sum(dose_plot$n), ")"),
          subtitle = "Have you ever recieved any other vaccines?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "recieved other vaccines", y = "count")

df_retarget %>%
  mutate(
    vax_status_retarget = case_when(
      vax_status_retarget == 0 ~ "unvaccinated",
      vax_status_retarget == 1 ~ "vaccinated"
    )
  ) %>%
  drop_na(vax_status_retarget, receive_other_vax) %>%
  count(vax_status_retarget, receive_other_vax) %>%
  # mutate(
  #   receive_other_vax = case_when(
  #     vax_next_year == 1 ~ "1 = very unlikely",
  #     vax_next_year == 2 ~ "2 = somewhat unlikely",
  #     vax_next_year == 3 ~ "3 = unsure",
  #     vax_next_year == 4 ~ "4 = probably will",
  #     vax_next_year == 5 ~ "5 = definitely will",
  #   ),
  #   #`Analysis 3 - impediment theme` = `Analysis 3 - impediment theme` %>% str_to_sentence()
  # ) %>%
  arrange(vax_status_retarget) %>%
  mutate(receive_other_vax = fct_inorder(receive_other_vax)) %>%
  ggplot(aes(vax_status_retarget, n, fill = receive_other_vax)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "vaccination status",
    y = "Count",
    fill = "Recieved any other vaccines?",
    title = "Distribution of have or have not recieved any other vaccines by vaccination status"
  )

df_retarget %>%
  drop_na(country_answer, receive_other_vax) %>%
  count(country_answer, receive_other_vax) %>%
  arrange(country_answer) %>%
  #mutate(receive_other_vax = fct_inorder(receive_other_vax)) %>%
  ggplot(aes(country_answer, n, fill = receive_other_vax)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "country",
    y = "Count",
    fill = "Recieved any other vaccines?",
    title = "Distribution of have or have not recieved any other vaccines by country"
  )

Access Questions

1. Time to travel to the closest vaccination site

df_retarget$time_to_get_vax[!df_retarget$time_to_get_vax %in% c("Less than 20 min","20-60 min", "1-2 hrs", "2+ hrs")] = NA
df_retarget$time_to_get_vax = factor(df_retarget$time_to_get_vax, levels=c("Less than 20 min","20-60 min", "1-2 hrs", "2+ hrs"))
time_get_vax = df_retarget %>% filter(!is.na(time_to_get_vax))
time_get_vax_plot <- time_get_vax %>% count(time_to_get_vax) %>% mutate(percentage = n / nrow(time_get_vax))
ggplot(time_get_vax_plot, aes(x = (time_to_get_vax), y = n, fill = time_to_get_vax)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Time to travel to the closest vaccination site (n = ", sum(dose_plot$n), ")"),
          subtitle = "How long do you think it would take you to travel to the closest vaccination site?\nHow long did it take you to travel to the place where you recieved the vaccine?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "Time needed", y = "count")

df_retarget %>%
  mutate(
    vax_status_retarget = case_when(
      vax_status_retarget == 0 ~ "unvaccinated",
      vax_status_retarget == 1 ~ "vaccinated"
    )
  ) %>%
  drop_na(vax_status_retarget, time_to_get_vax) %>%
  count(vax_status_retarget, time_to_get_vax) %>%
  # mutate(
  #   receive_other_vax = case_when(
  #     vax_next_year == 1 ~ "1 = very unlikely",
  #     vax_next_year == 2 ~ "2 = somewhat unlikely",
  #     vax_next_year == 3 ~ "3 = unsure",
  #     vax_next_year == 4 ~ "4 = probably will",
  #     vax_next_year == 5 ~ "5 = definitely will",
  #   ),
  #   #`Analysis 3 - impediment theme` = `Analysis 3 - impediment theme` %>% str_to_sentence()
  # ) %>%
  arrange(vax_status_retarget) %>%
  #mutate(time_to_get_vax = fct_inorder(time_to_get_vax)) %>%
  ggplot(aes(vax_status_retarget, n, fill = time_to_get_vax)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "vaccination status",
    y = "Count",
    fill = "Time needed",
    title = "Distribution of Time to travel to the closest vaccination site by vaccination status"
  )

df_retarget %>%
  drop_na(country_answer, time_to_get_vax) %>%
  count(country_answer, time_to_get_vax) %>%
  arrange(country_answer) %>%
  #mutate(time_to_get_vax = fct_inorder(time_to_get_vax)) %>%
  ggplot(aes(country_answer, n, fill = time_to_get_vax)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "country",
    y = "Count",
    fill = "Time needed",
    title = "Distribution of Time to travel to the closest vaccination site by country"
  )

df_retarget %>%
  mutate(
    vax_status_retarget = case_when(
      vax_status_retarget == 0 ~ "unvaccinated",
      vax_status_retarget == 1 ~ "vaccinated"
    )
  ) %>%
  filter(vax_status_retarget == "unvaccinated") %>%
  drop_na(country_answer, time_to_get_vax) %>%
  count(country_answer, time_to_get_vax) %>%
  arrange(country_answer) %>%
  #mutate(time_to_get_vax = fct_inorder(time_to_get_vax)) %>%
  ggplot(aes(country_answer, n, fill = time_to_get_vax)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "country",
    y = "Count",
    fill = "Time needed",
    title = "Distribution of Time to travel to the closest vaccination site by country (Unvaccinated)"
  )

2. Waiting time on vaccination site

df_retarget$wait_time[!df_retarget$wait_time %in% c("Less than 20 min","20-60 min", "1-2 hrs", "2+ hrs")] = NA
df_retarget$wait_time = factor(df_retarget$wait_time, levels=c("Less than 20 min","20-60 min", "1-2 hrs", "2+ hrs"))
time_get_vax = df_retarget %>% filter(!is.na(wait_time))
time_get_vax_plot <- time_get_vax %>% count(wait_time) %>% mutate(percentage = n / nrow(time_get_vax))
ggplot(time_get_vax_plot, aes(x = (wait_time), y = n, fill = wait_time)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Waiting time on vaccination site (n = ", sum(dose_plot$n), ")"),
          subtitle = "How long do you think you would wait to get the vaccine once you reach the vaccination site?\nHow long did you wait once you arrived at the vaccination site?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "Time needed", y = "count")

df_retarget %>%
  mutate(
    vax_status_retarget = case_when(
      vax_status_retarget == 0 ~ "unvaccinated",
      vax_status_retarget == 1 ~ "vaccinated"
    )
  ) %>%
  drop_na(vax_status_retarget, wait_time) %>%
  count(vax_status_retarget, wait_time) %>%
  arrange(vax_status_retarget) %>%
  ggplot(aes(vax_status_retarget, n, fill = wait_time)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "vaccination status",
    y = "Count",
    fill = "Time needed",
    title = "Distribution of Waiting time on vaccination site by vaccination status"
  )

df_retarget %>%
  drop_na(country_answer, wait_time) %>%
  count(country_answer, wait_time) %>%
  arrange(country_answer) %>%
  ggplot(aes(country_answer, n, fill = wait_time)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "country",
    y = "Count",
    fill = "Time needed",
    title = "Distribution of Waiting time on vaccination site by country"
  )

3. How to get to the closest vaccination site?

df_retarget$transportation_vax[!df_retarget$transportation_vax %in% c("walking","bicyle", "bus", "car", "train", "other", "Don't know")] = NA
df_retarget$transportation_vax = factor(df_retarget$transportation_vax, levels=c("walking","bicyle", "bus", "car", "train", "other", "Don't know"))
transportation_get_vax = df_retarget %>% filter(!is.na(transportation_vax))
transportation_get_vax_plot <- transportation_get_vax %>% count(transportation_vax) %>% mutate(percentage = n / nrow(transportation_get_vax))
ggplot(transportation_get_vax_plot, aes(x = (transportation_vax), y = n, fill = transportation_vax)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Transportation to vaccination site (n = ", sum(dose_plot$n), ")"),
          subtitle = "How do you think you would you get to your closest vaccination site?\nHow did you get there?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "transportation", y = "count")

df_retarget %>%
  mutate(
    vax_status_retarget = case_when(
      vax_status_retarget == 0 ~ "unvaccinated",
      vax_status_retarget == 1 ~ "vaccinated"
    )
  ) %>%
  drop_na(vax_status_retarget, transportation_vax) %>%
  count(vax_status_retarget, transportation_vax) %>%
  arrange(vax_status_retarget) %>%
  ggplot(aes(vax_status_retarget, n, fill = transportation_vax)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "vaccination status",
    y = "Count",
    fill = "",
    title = "Distribution of Transportation to vaccination site by vaccination status"
  )

df_retarget %>%
  drop_na(country_answer, transportation_vax) %>%
  count(country_answer, transportation_vax) %>%
  arrange(country_answer) %>%
  ggplot(aes(country_answer, n, fill = transportation_vax)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "country",
    y = "Count",
    fill = "",
    title = "Distribution of Transportation to vaccination site by country"
  )

4. Need an appointment or Not

df_retarget$need_appointment[!df_retarget$need_appointment %in% c("yes","no")] = NA
df_retarget$need_appointment = factor(df_retarget$need_appointment, levels=c("yes","no"))
appointment = df_retarget %>% filter(!is.na(need_appointment))
appointment_plot <- appointment %>% count(need_appointment) %>% mutate(percentage = n / nrow(appointment))
ggplot(appointment_plot, aes(x = (need_appointment), y = n, fill = need_appointment)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Need an appointment or Not (n = ", sum(dose_plot$n), ")"),
          subtitle = "Do you think you would need an appointment?\nDid you need an appointment?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "appointment needed", y = "count")

df_retarget %>%
  mutate(
    vax_status_retarget = case_when(
      vax_status_retarget == 0 ~ "unvaccinated",
      vax_status_retarget == 1 ~ "vaccinated"
    )
  ) %>%
  drop_na(vax_status_retarget, need_appointment) %>%
  count(vax_status_retarget, need_appointment) %>%
  arrange(vax_status_retarget) %>%
  ggplot(aes(vax_status_retarget, n, fill = need_appointment)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "vaccination status",
    y = "Count",
    fill = "appointment needed",
    title = "Distribution of appointment needed by vaccination status"
  )

df_retarget %>%
  drop_na(country_answer, need_appointment) %>%
  count(country_answer, need_appointment) %>%
  arrange(country_answer) %>%
  ggplot(aes(country_answer, n, fill = need_appointment)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "country",
    y = "Count",
    fill = "appointment needed",
    title = "Distribution of appointment needed to vaccination site by country"
  )

5. Need to pay or Not (excluding travel cost)

Note: only vaccinated people been asked for multiple choice question

df_retarget$vax_cost[!df_retarget$vax_cost %in% c("yes","no")] = NA
df_retarget$vax_cost = factor(df_retarget$vax_cost, levels=c("yes","no"))
cost = df_retarget %>% filter(!is.na(vax_cost))
cost_plot <- cost %>% count(vax_cost) %>% mutate(percentage = n / nrow(cost))
ggplot(cost_plot, aes(x = (vax_cost), y = n, fill = vax_cost)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Have to pay to get the vaccine (n = ", sum(dose_plot$n), ")"),
          subtitle = "Did you have to pay anything to get the vaccine (excluding travel cost)?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "payment needed", y = "count")

df_retarget %>%
  drop_na(country_answer, vax_cost) %>%
  count(country_answer, vax_cost) %>%
  arrange(country_answer) %>%
  ggplot(aes(country_answer, n, fill = vax_cost)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "country",
    y = "Count",
    fill = "payment needed",
    title = "Distribution of payment needed by country"
  )

6. Would like to back to the same place for another dose

Note: only vaccinated people been asked

df_retarget$go_back_another_dose[!df_retarget$go_back_another_dose %in% c("yes","no")] = NA
df_retarget$go_back_another_dose = factor(df_retarget$go_back_another_dose, levels=c("yes","no"))
go_back = df_retarget %>% filter(!is.na(go_back_another_dose))
go_back_plot <- go_back %>% count(go_back_another_dose) %>% mutate(percentage = n / nrow(go_back))
ggplot(go_back_plot, aes(x = (go_back_another_dose), y = n, fill = go_back_another_dose)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Would like to go back for another dose (n = ", sum(dose_plot$n), ")"),
          subtitle = "Would you go back to the same place if you wanted another dose?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "would like to go back", y = "count")

df_retarget %>%
  drop_na(country_answer, go_back_another_dose) %>%
  count(country_answer, go_back_another_dose) %>%
  arrange(country_answer) %>%
  ggplot(aes(country_answer, n, fill = go_back_another_dose)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "country",
    y = "Count",
    fill = "likelihood",
    title = "Distribution of likelihood to go back for another dose by country"
  )

7. Day of the week preferred to get vaccine

df_retarget$prefer_day[!df_retarget$prefer_day %in% c("Su","M", "Tu", "W", "Th", "F", "S")] = NA
df_retarget$prefer_day = factor(df_retarget$prefer_day, levels=c("Su","M", "Tu", "W", "Th", "F", "S"))
prefer_day_vax = df_retarget %>% filter(!is.na(prefer_day))
prefer_day_vax_plot <- prefer_day_vax %>% count(prefer_day) %>% mutate(percentage = n / nrow(prefer_day_vax))
ggplot(prefer_day_vax_plot, aes(x = (prefer_day), y = n, fill = prefer_day)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Preferred day of week to get vaccine (n = ", sum(dose_plot$n), ")"),
          subtitle = "If you wanted to get vaccinated, what day of the week would be ideal for you?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "Day", y = "count")

df_retarget %>%
  mutate(
    vax_status_retarget = case_when(
      vax_status_retarget == 0 ~ "unvaccinated",
      vax_status_retarget == 1 ~ "vaccinated"
    )
  ) %>%
  drop_na(vax_status_retarget, prefer_day) %>%
  count(vax_status_retarget, prefer_day) %>%
  arrange(vax_status_retarget) %>%
  ggplot(aes(vax_status_retarget, n, fill = prefer_day)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "vaccination status",
    y = "Count",
    fill = "Time needed",
    title = "Distribution of Preferred day of week to get vaccine by vaccination status"
  )

df_retarget %>%
  drop_na(country_answer, prefer_day) %>%
  count(country_answer, prefer_day) %>%
  arrange(country_answer) %>%
  ggplot(aes(country_answer, n, fill = prefer_day)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "country",
    y = "Count",
    fill = "Preferred day of week",
    title = "Distribution of Preferred day of week to get vaccine by country"
  )

Demographics

Continuous Demographic Variables

Starred variables have a corresponding variable, with the suffix _num (ie education_num) that provides a numeric ordering of the variables. This order is listed in parenthesis.

Variable	Description
gender*	male (0) or female (1)
age	integer 18 to 99
education*	< high school (1), high school (2), some college (3), 2-year degree (4), 4-year degree (5), graduate degree (6), other, prefer not to say
location*	rural(1), suburban (2), urban(3), other, prefer not to say
religiosity*	not very religious (1), somewhat religious (2), very religious (3), other, prefer not to say
white	1 if the participant is a white or caucasian, 0 if not
ethnicity	asian or indian, black or african, coloured, white or caucasian, other, prefer not to say

## clean demographic data
numeric_cols <- function(df){
  out <- df %>%
    mutate(
      age = as.numeric(ifelse(demog_age %in% paste(18:99), demog_age, "")),
      gender_num = case_when(
        gender == "female" ~ 1,
        gender == "male" ~ 0
        ),
      education_num = case_when(
        demog_education == "< High school" ~ 1,
        demog_education == "High school" ~ 2,
        demog_education == "Some college" ~ 3,
        demog_education == "2-year degree" ~ 4,
        demog_education == "4-year degree" ~ 5,
        demog_education == "Graduate degree" ~ 6,
      ),
      religiosity_num = case_when(
        religiosity == "Not very religious" ~ 1,
        religiosity == "Somewhat religious" ~ 2,
        religiosity == "Very religious" ~ 3,
      ),
      location_num = case_when(
        location == "Rural" ~ 1,
        location == "Suburban" ~ 2,
        location == "Urban" ~ 3,
      ),
      location =factor(location, levels = c("Urban", "Suburban", "Rural", "Prefer not to say")),
      white = ifelse(ethnicity == "White or Caucasian", 1, 0),
      ethnicity = factor(ethnicity, levels=c("Asian or Indian", 
                                                "Black or African", 
                                                "coloured", 
                                                "White or Caucasian", 
                                                "Other",
                                                "Prefer not to say")
    ))
    return(out)
}

df_retarget_num = numeric_cols(df_retarget)

df_retarget_num %>%
  select_if(is.numeric) %>%
  select(age, education = education_num, location=location_num, religiosity = religiosity_num, gender = gender_num, white) %>%
  describe(quant = c(.25,.75) ) %>%
  select(n, mean, sd, se, min, min, first_quartile = Q0.25, median, third_quartile = Q0.75, max) %>%
  clean_names(case = "title") %>%
  rename(SD = Sd, SE = Se) %>%
  kable(caption = "Summary Statistics for Continuous Demographic Variables", digits = 3)%>%
  kable_styling(bootstrap_options = c("striped", "hover"))

Summary Statistics for Continuous Demographic Variables

	N	Mean	SD	SE	Min	First Quartile	Median	Third Quartile	Max
age	1036	27.488	8.065	0.251	18	22	25	31.00	64
education	1006	3.112	1.582	0.050	1	2	3	4.75	6
location	1008	2.179	0.829	0.026	1	1	2	3.00	3
religiosity	958	2.374	0.724	0.023	1	2	3	3.00	3
gender	1747	0.386	0.487	0.012	0	0	0	1.00	1
white	1753	0.011	0.106	0.003	0	0	0	0.00	1

df_retarget_num$vax_status_retarget = as.numeric(df_retarget_num$vax_status_retarget)
df_retarget_num %>%
  select_if(is.numeric) %>%
  select(vax_status_retarget, age, education = education_num, location=location_num, religiosity = religiosity_num, gender = gender_num, white) %>%
  split(.$vax_status_retarget) %>% 
  map(describe) %>% 
  do.call(rbind, .) %>%
  data.frame() %>%
  select(n, mean , se) %>%
  rownames_to_column() %>%
  separate(rowname, c("vax_status_retarget", "variable"), sep = "\\.") %>%
  filter(variable != "vax_status_retarget") %>%
  pivot_longer(cols = c("n", "mean", "se")) %>%
  mutate(column = paste(vax_status_retarget, name, sep = "_")) %>%
  select(column, variable, value) %>%
  pivot_wider(names_from = column) %>%
  kable(digits = 3,caption = "Summary Statistics for Continuous Demographic Variables by Vaccination Status", 
        col.names = c("", "N", "Mean", "SE", "N", "Mean", "SE")) %>%
  kable_styling(bootstrap_options = c("striped", "hover"))%>%
  add_header_above(c(" " = 1, "Unvaccinated" = 3, "Vaccinated" = 3))

Summary Statistics for Continuous Demographic Variables by Vaccination Status

	Unvaccinated			Vaccinated
	N	Mean	SE	N	Mean	SE
age	283	25.947	0.486	753	28.068	0.290
education	277	3.047	0.096	729	3.137	0.058
location	265	2.208	0.049	722	2.166	0.031
religiosity	252	2.290	0.047	685	2.403	0.027
gender	291	0.323	0.027	793	0.372	0.017
white	292	0.021	0.008	795	0.018	0.005

df_retarget_num$vax_status_retarget_4 = as.numeric(df_retarget_num$vax_status_retarget_4)
df_retarget_num %>%
  select_if(is.numeric) %>%
  select(vax_status_retarget_4, age, education = education_num, location=location_num, religiosity = religiosity_num, gender = gender_num, white) %>%
  split(.$vax_status_retarget_4) %>% 
  map(describe) %>% 
  do.call(rbind, .) %>%
  data.frame() %>%
  select(n, mean , se) %>%
  rownames_to_column() %>%
  separate(rowname, c("vax_status_retarget_4", "variable"), sep = "\\.") %>%
  filter(variable != "vax_status_retarget_4") %>%
  pivot_longer(cols = c("n", "mean", "se")) %>%
  mutate(column = paste(vax_status_retarget_4, name, sep = "_")) %>%
  select(column, variable, value) %>%
  pivot_wider(names_from = column) %>%
  kable(digits = 3,caption = "Summary Statistics for Continuous Demographic Variables by Vaccination dose received", 
        col.names = c("", "N", "Mean", "SE", "N", "Mean", "SE", "N", "Mean", "SE", "N", "Mean", "SE")) %>%
  kable_styling(bootstrap_options = c("striped", "hover"))%>%
  add_header_above(c(" " = 1, "Unvaccinated" = 3, "1 dose" = 3, "2 doses" = 3, "3 doses" = 3))

Summary Statistics for Continuous Demographic Variables by Vaccination dose received

	Unvaccinated			1 dose			2 doses			3 doses
	N	Mean	SE	N	Mean	SE	N	Mean	SE	N	Mean	SE
age	283	25.947	0.486	220	26.686	0.463	356	28.225	0.420	177	29.469	0.674
education	277	3.047	0.096	216	3.032	0.108	342	3.173	0.083	171	3.199	0.125
location	265	2.208	0.049	210	2.167	0.058	345	2.139	0.045	167	2.222	0.066
religiosity	252	2.290	0.047	198	2.298	0.052	322	2.416	0.040	165	2.503	0.053
gender	291	0.323	0.027	230	0.348	0.031	375	0.395	0.025	188	0.356	0.035
white	292	0.021	0.008	231	0.035	0.012	376	0.008	0.005	188	0.016	0.009

df_retarget_num %>%
  select(country_answer, age, education = education_num, location=location_num, religiosity = religiosity_num, gender = gender_num, white) %>%
  split(.$country_answer) %>% 
  map(describe) %>% 
  do.call(rbind, .) %>%
  data.frame() %>%
  select(n, mean , se) %>%
  rownames_to_column() %>%
  separate(rowname, c("country_answer", "variable"), sep = "\\.") %>%
  filter(variable != "country_answer*") %>%
  pivot_longer(cols = c("n", "mean", "se")) %>%
  mutate(column = paste(country_answer, name, sep = "_")) %>%
  select(column, variable, value) %>%
  pivot_wider(names_from = column) %>%
  kable(digits = 3,caption = "Summary Statistics for Continuous Demographic Variables by country", 
        col.names = c("", "N", "Mean", "SE", "N", "Mean", "SE", "N", "Mean", "SE", "N", "Mean", "SE")) %>%
  kable_styling(bootstrap_options = c("striped", "hover"))%>%
  add_header_above(c(" " = 1, "South Africa" = 3, "Kenya" = 3, "Nigeria" = 3, "Ghana" = 3))

Summary Statistics for Continuous Demographic Variables by country

	South Africa			Kenya			Nigeria			Ghana
	N	Mean	SE	N	Mean	SE	N	Mean	SE	N	Mean	SE
age	244	31.344	0.628	313	26.856	0.377	249	24.896	0.427	230	27.065	0.503
education	232	2.328	0.080	312	3.462	0.086	241	3.523	0.110	221	2.995	0.104
location	237	2.169	0.055	320	2.075	0.045	243	2.366	0.049	208	2.130	0.061
religiosity	219	2.269	0.052	304	2.336	0.041	231	2.424	0.044	204	2.485	0.051
gender	503	0.571	0.022	427	0.326	0.023	347	0.343	0.026	470	0.277	0.021
white	507	0.026	0.007	428	0.002	0.002	347	0.012	0.006	471	0.004	0.003

Other Demographic Variables

1. Ethnicity

df_retarget$ethnicity[!df_retarget$ethnicity %in% c("Black or African","White or Caucasian", "Asian or Indian", "Other", "Prefer not to say")] = NA
df_retarget$ethnicity = factor(df_retarget$ethnicity, levels=c("Black or African","White or Caucasian", "Asian or Indian", "Other", "Prefer not to say"))
ethnicity_df = df_retarget %>% filter(!is.na(ethnicity))
ethnicity_df_plot <- ethnicity_df %>% count(ethnicity) %>% mutate(percentage = n / nrow(ethnicity_df))
ggplot(ethnicity_df_plot, aes(x = (ethnicity), y = n, fill = ethnicity)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Ethnicity (n = ", sum(dose_plot$n), ")"),
          subtitle = "Which best describes you?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "Religion", y = "count")

df_retarget %>%
  mutate(
    vax_status_retarget = case_when(
      vax_status_retarget == 0 ~ "unvaccinated",
      vax_status_retarget == 1 ~ "vaccinated"
    )
  ) %>%
  drop_na(vax_status_retarget, ethnicity) %>%
  count(vax_status_retarget, ethnicity) %>%
  arrange(vax_status_retarget) %>%
  ggplot(aes(vax_status_retarget, n, fill = ethnicity)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "ethnicity",
    y = "Count",
    fill = "ethnicity",
    title = "Distribution of ethnicity by vaccination status"
  )

df_retarget %>%
  drop_na(country_answer, ethnicity) %>%
  count(country_answer, ethnicity) %>%
  arrange(country_answer) %>%
  ggplot(aes(country_answer, n, fill = ethnicity)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "ethnicity",
    y = "Count",
    fill = "ethnicity",
    title = "Distribution of ethnicity by country"
  )

2. Religion

df_retarget$demog_religion[!df_retarget$demog_religion %in% c("Christianity","Islam", "African traditional", "Hinduism", "Judaism", "No religion", "Other", "Prefer not to say")] = NA
df_retarget$demog_religion = factor(df_retarget$demog_religion, levels=c("Christianity","Islam", "African traditional", "Hinduism", "Judaism", "No religion", "Other", "Prefer not to say"))
religion_df = df_retarget %>% filter(!is.na(demog_religion))
religion_df_plot <- religion_df %>% count(demog_religion) %>% mutate(percentage = n / nrow(religion_df))
ggplot(religion_df_plot, aes(x = (demog_religion), y = n, fill = demog_religion)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Religion (n = ", sum(dose_plot$n), ")"),
          subtitle = "What's your religion, if any?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "Religion", y = "count")

df_retarget %>%
  mutate(
    vax_status_retarget = case_when(
      vax_status_retarget == 0 ~ "unvaccinated",
      vax_status_retarget == 1 ~ "vaccinated"
    )
  ) %>%
  drop_na(vax_status_retarget, demog_religion) %>%
  count(vax_status_retarget, demog_religion) %>%
  arrange(vax_status_retarget) %>%
  ggplot(aes(vax_status_retarget, n, fill = demog_religion)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "Religion",
    y = "Count",
    fill = "Religion",
    title = "Distribution of Religion by vaccination status"
  )

df_retarget %>%
  drop_na(country_answer, demog_religion) %>%
  count(country_answer, demog_religion) %>%
  arrange(country_answer) %>%
  ggplot(aes(country_answer, n, fill = demog_religion)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "Religion",
    y = "Count",
    fill = "Religion",
    title = "Distribution of Religion by country"
  )

3. Income

South Africa

df_SA = df_retarget %>% filter(country_answer == "South Africa")
df_SA$demog_income[!df_SA$demog_income %in% c("< R5,000","R5,000 - R9,999", "R10,000 - R29,999", "R30,000 - R49,999", "R50,000 - R99,999", "> R100,000")] = NA
df_SA$demog_income = factor(df_SA$demog_income, levels=c("< R5,000","R5,000 - R9,999", "R10,000 - R29,999", "R30,000 - R49,999", "R50,000 - R99,999", "> R100,000"))
SA = df_SA %>% filter(!is.na(demog_income))
SA_plot <- SA %>% count(demog_income) %>% mutate(percentage = n / nrow(SA))
ggplot(SA_plot, aes(x = (demog_income), y = n, fill = demog_income)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Income - South Africa (n = ", sum(dose_plot$n), ")"),
          subtitle = "How much do you earn in a year?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "Income", y = "count")

Kenya

df_Kenya = df_retarget %>% filter(country_answer == "Kenya")
df_Kenya$demog_income[!df_Kenya$demog_income %in% c("< 50k KSh","50k KSh - 100k KSh", "100k KSh - 300k KSh", "300k KSh - 500k Ksh", "500k Ksh-1,000k KSh", "> 1,000k KSh")] = NA
df_Kenya$demog_income = factor(df_Kenya$demog_income, levels=c("< 50k KSh","50k KSh - 100k KSh", "100k KSh - 300k KSh", "300k KSh - 500k Ksh", "500k Ksh-1,000k KSh", "> 1,000k KSh"))
Kenya = df_Kenya %>% filter(!is.na(demog_income))
Kenya_plot <- Kenya %>% count(demog_income) %>% mutate(percentage = n / nrow(Kenya))
ggplot(Kenya_plot, aes(x = (demog_income), y = n, fill = demog_income)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Income - Kenya (n = ", sum(dose_plot$n), ")"),
          subtitle = "How much do you earn in a year?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "Income", y = "count")

Nigeria

df_Nigeria = df_retarget %>% filter(country_answer == "Nigeria")
df_Nigeria$demog_income[!df_Nigeria$demog_income %in% c("< 50,000₦","50,000 - 99,999₦", "100,000₦  - 299,999₦", "300,000₦  - 499,999₦", "500,000₦  - 999,999₦", "> 1,000,000₦")] = NA
df_Nigeria$demog_income = factor(df_Nigeria$demog_income, levels=c("< 50,000₦","50,000 - 99,999₦", "100,000₦  - 299,999₦", "300,000₦  - 499,999₦", "500,000₦  - 999,999₦", "> 1,000,000₦"))
Nigeria = df_Nigeria %>% filter(!is.na(demog_income))
Nigeria_plot <- Nigeria %>% count(demog_income) %>% mutate(percentage = n / nrow(Nigeria))
ggplot(Nigeria_plot, aes(x = (demog_income), y = n, fill = demog_income)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Income - Nigeria (n = ", sum(dose_plot$n), ")"),
          subtitle = "How much do you earn in a year?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "Income", y = "count")

Ghana

df_Ghana = df_retarget %>% filter(country_answer == "Ghana")
df_Ghana$demog_income[!df_Ghana$demog_income %in% c("< 5,000GH₵","5,000GH₵ - 9,999GH₵", "10,000GH₵ - 29,999GH", "30,000GH₵ - 49,999GH", "50,000GH₵-99,999GH₵", "> 100,000GH₵")] = NA
df_Ghana$demog_income = factor(df_Ghana$demog_income, levels=c("< 5,000GH₵","5,000GH₵ - 9,999GH₵", "10,000GH₵ - 29,999GH", "30,000GH₵ - 49,999GH", "50,000GH₵-99,999GH₵", "> 100,000GH₵"))
Ghana = df_Ghana %>% filter(!is.na(demog_income))
Ghana_plot <- Ghana %>% count(demog_income) %>% mutate(percentage = n / nrow(Ghana))
ggplot(Ghana_plot, aes(x = (demog_income), y = n, fill = demog_income)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Income - Ghana (n = ", sum(dose_plot$n), ")"),
          subtitle = "How much do you earn in a year?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "Income", y = "count")

Other Variables

1. Heard “herd immunity” OR Not

df_retarget$herd_immunity[!df_retarget$herd_immunity %in% c("yes","no")] = NA
df_retarget$herd_immunity = factor(df_retarget$herd_immunity, levels=c("yes","no"))
herd_immunity_df = df_retarget %>% filter(!is.na(herd_immunity))
herd_immunity_df_plot <- herd_immunity_df %>% count(herd_immunity) %>% mutate(percentage = n / nrow(herd_immunity_df))
ggplot(herd_immunity_df_plot, aes(x = (herd_immunity), y = n, fill = herd_immunity)) +
  geom_bar(stat = "identity") +
  geom_text(aes(label = paste0(n, " (", round(percentage * 100,2), "%)")), vjust = -0.25) +
  ggtitle(paste0("Heard 'herd immunity' OR Not (n = ", sum(dose_plot$n), ")"),
          subtitle = "Have you heard of 'herd immunity'?") +
  theme_bw() +
  theme(plot.title = element_text(face = "bold"), legend.position = "none") +
  labs(x = "appointment needed", y = "count")

df_retarget %>%
  mutate(
    vax_status_retarget = case_when(
      vax_status_retarget == 0 ~ "unvaccinated",
      vax_status_retarget == 1 ~ "vaccinated"
    )
  ) %>%
  drop_na(vax_status_retarget, herd_immunity) %>%
  count(vax_status_retarget, herd_immunity) %>%
  arrange(vax_status_retarget) %>%
  ggplot(aes(vax_status_retarget, n, fill = herd_immunity)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "vaccination status",
    y = "Count",
    fill = "Heard 'herd immunity'",
    title = "Distribution of Heard 'herd immunity' by vaccination status"
  )

df_retarget %>%
  drop_na(country_answer, herd_immunity) %>%
  count(country_answer, herd_immunity) %>%
  arrange(country_answer) %>%
  ggplot(aes(country_answer, n, fill = herd_immunity)) +
  geom_col(position = "dodge", alpha = 0.8, color="black") +
  theme_bw() +
  theme(legend.position = "bottom") +
  labs(
    x = "country",
    y = "Count",
    fill = "Heard 'herd immunity'",
    title = "Distribution of Heard 'herd immunity' by country"
  )