mirror of
https://github.com/kidwellj/trs_admissions_survey2021.git
synced 2024-10-31 22:22:21 +00:00
major rewriting
This commit is contained in:
Jeremy Kidwell (Theology and Religion)
parent
38da21b4b0
commit
0da6527adf
Binary file not shown.
Binary file not shown.
|
|
@ -6,23 +6,19 @@ output: html_document
|
|||
```{r setup, include=FALSE}
|
||||
knitr::opts_chunk$set(echo = TRUE)
|
||||
library(ggplot2)
|
||||
library(devtools)
|
||||
library(usethis)
|
||||
library(devtools)
|
||||
library(likert)
|
||||
# Load RColorBrewer
|
||||
# install.packages("RColorBrewer")
|
||||
library(RColorBrewer)
|
||||
library("stringr") # Load stringr package, used for wrapping label text in plots
|
||||
library(dplyr) # Used for filtering below
|
||||
library(scales) # Used for adding percentages to bar charts
|
||||
# library(kable) # Used for generating markdown tables
|
||||
library("readxl")
|
||||
library(haven)
|
||||
|
||||
# Define colour palettes for plots below
|
||||
coul3 <- brewer.pal(3, "RdYlBu") # Using RdYlBu range to generate 3 colour palette: https://colorbrewer2.org/#type=diverging&scheme=RdYlBu&n=5
|
||||
|
||||
TSR_data <- read.csv("./data/TSR data complete.csv")
|
||||
subject_data <- read.csv("./data/Subject data.csv")
|
||||
admissions_data <- read_excel("./data/TSR_data_numbers.xlsx", sheet = "Raw data - completes")
|
||||
|
||||
# Set up local workspace, as needed:
|
||||
|
||||
|
|
@ -38,6 +34,203 @@ if (dir.exists("figures") == FALSE) {
|
|||
if (dir.exists("derivedData") == FALSE) {
|
||||
dir.create("derivedData")
|
||||
}
|
||||
|
||||
# Refactor data
|
||||
q2_labels <- c("15 or under" = 1, "16" = 2, "17" = 3, "18" = 4, "19" = 5, "20" = 6, "21 or over" = 7, "Prefer not to say" = 8)
|
||||
admissions_data$Q2 <- labelled(admissions_data$Q2, q2_labels, label = "How old are you?")
|
||||
|
||||
admissions_data$Q3 <- labelled(admissions_data$Q3, c("Year 11/S4/Year 12(NI)" = 1, "Year 12/S5/Year 13(NI)" = 2, "Year 13/S6/Year 14(NI)" = 3, "I am currently on a gap year" = 4, "I am currently on an undergraduate/HE college course" = 5, "I am in full-time employment" = 6, "I am unemployed" = 7, "Other" = 8, "Prefer not to say" = 9), label = "Which of the following best describes your MOST RECENT year of study?")
|
||||
|
||||
admissions_data$Q4 <- labelled(admissions_data$Q4, c("Yes, definitely" = 1, "Yes, probably" = 2, "I haven’t ruled it out" = 3), label = "Are you considering or planning to go to university in the future?")
|
||||
|
||||
common_labels <- c(
|
||||
"Strongly agree" = 1,
|
||||
"Agree" = 2,
|
||||
"Neither/Nor" = 3,
|
||||
"Disagree" = 4,
|
||||
"Strongly disagree" = 5,
|
||||
"Prefer not to say" = 0
|
||||
)
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate_at(vars(starts_with("Q5_")), ~ labelled(., common_labels, label = "I have a good understanding of what this subject involves"))
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate_at(vars(starts_with("Q6_")), ~ labelled(., common_labels, label = "I would be interested in studying this subject at University"))
|
||||
|
||||
common_labels2 <- c(
|
||||
"Good employability prospects" = 1,
|
||||
NULL = 2,
|
||||
NULL = 3,
|
||||
NULL = 4,
|
||||
"Poor employability prospects" = 5,
|
||||
"Prefer not to say" = 0
|
||||
)
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate_at(vars(starts_with("Q7_")), ~ labelled(., common_labels2, label = "This subject has… employability prospects"))
|
||||
|
||||
admissions_data$Q8 <- labelled(admissions_data$Q8, c("Theology is a subject for religious people" = 1, NULL = 2, NULL = 3, NULL = 4, "Theology is a subject for religious and non-religious people" = 5, "Prefer not to say" = 0), label = "Thinking about Theology, please select an option on the scale from 1 to 5 which best represents your opinion")
|
||||
|
||||
admissions_data$Q9 <- labelled(admissions_data$Q9, c("Religion is a subject for religious people" = 1, NULL = 2, NULL = 3, NULL = 4, "Religion is a subject for religious and non-religious people" = 5, "Prefer not to say" = 0), label = "Thinking about Religion, please select an option on the scale from 1 to 5 which best represents your opinion")
|
||||
|
||||
common_labels3 <- c(
|
||||
"Psychology" = 1, "Arts" = 2, "Sociology" = 3, "Politics" = 4, "History" = 5, "Philosophy" = 6, "Ethics" = 7, "Archaeology" = 8, "Textual studies" = 9, "Literature" = 10, "Law" = 11, "Economics" = 12, "Science" = 13, "Prefer not to say" = 0)
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate_at(vars(starts_with("Q10_")), ~ labelled(., common_labels3, label = "I think that a theology degree would include..."))
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate_at(vars(starts_with("Q11_")), ~ labelled(., common_labels3, label = "I think that a religious studies degree would include..."))
|
||||
|
||||
common_labels4 <- c(
|
||||
"Politics" = 1, "History" = 2, "Ethics" = 3, "Theology" = 4, "Religion" = 5, "Law" = 6, "Economics" = 7, "Maths" = 8, "Logic" = 9, "Prefer not to say" = 0)
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate_at(vars(starts_with("Q12_")), ~ labelled(., common_labels4, label = "I think that a philosophy degree would include..."))
|
||||
|
||||
common_labels5 <- c("Yes" = 1, "No" = 2, "Prefer not to say" = 0)
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate_at(vars(starts_with("Q13")), ~ labelled(., common_labels5, label = "Are you currently studying A level Religious Studies, or intending to?"))
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate_at(vars(starts_with("Q14")), ~ labelled(., common_labels5, label = "Are you studying or did you previously study GCSE Religious Studies?"))
|
||||
|
||||
admissions_data$Q16 <- labelled(admissions_data$Q16, c("Male"=1, "Female"=2, "I identify my gender in another way"=3, "Prefer not to say"=4), label = "I identify my gender as…")
|
||||
|
||||
admissions_data$Q17 <- labelled(admissions_data$Q17, c("Arab"=1, "Indian"=2, "Pakistani"=3, "Bangladeshi"=4, "Chinese"=5, "Any other Asian background"=6, "Black - African"=7, "Black - Caribbean"=8, "Any other Black background"=9, "Mixed - White and Black Caribbean"=10, "Mixed - White and Black African"=11, "Mixed - White and Black Asian"=12, "Any other Mixed/Multiple Ethnic background"=13, "White - British"=14, "White - Irish"=15, "Gypsy or Irish Traveller"=16, "Any other White background"=17, "Other Ethnic group"=18, "Prefer not to say OR Other"=0), label = "What is your ethnic group?")
|
||||
|
||||
admissions_data$Q18 <- labelled(admissions_data$Q18, c("Agnostic"=1, "Atheist"=2, "Baha'i"=3, "Buddhist"=4, "Christian"=5, "Confucian"=6, "Jain"=7, "Jewish"=8, "Hindu"=9, "Indigenous Traditional Religious"=10, "Muslim"=11, "Pagan"=12, "Shinto"=13, "Sikh"=14, "Spiritual but not religious"=15, "Zoroastrian"=16, "No religion"=17, "Prefer not to say OR Other"=0), label = "What is your religion?")
|
||||
|
||||
# Create bins:
|
||||
|
||||
# For Q5 - understanding
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate(
|
||||
Q5_Theology = ifelse(Q5_Theology == 0, NA, Q5_Theology),
|
||||
understanding_theology_bin = case_when(
|
||||
Q5_Theology < 3 ~ "high",
|
||||
Q5_Theology > 3 ~ "low",
|
||||
Q5_Theology == 3 ~ "neutral",
|
||||
TRUE ~ NA
|
||||
) %>% factor(levels = c("low", "neutral", "high"))
|
||||
)
|
||||
# For Q5 - understanding
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate(
|
||||
Q5_Religious_Studies = ifelse(Q5_Religious_Studies == 0, NA, Q5_Religious_Studies),
|
||||
understanding_religion_bin = case_when(
|
||||
Q5_Religious_Studies < 3 ~ "high",
|
||||
Q5_Religious_Studies > 3 ~ "low",
|
||||
Q5_Religious_Studies == 3 ~ "neutral",
|
||||
TRUE ~ NA
|
||||
) %>% factor(levels = c("low", "neutral", "high"))
|
||||
)
|
||||
# For Q6 - interest
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate(
|
||||
Q6_Theology = ifelse(Q6_Theology == 0, NA, Q6_Theology),
|
||||
interest_theology_bin = case_when(
|
||||
Q6_Theology < 3 ~ "high",
|
||||
Q6_Theology > 3 ~ "low",
|
||||
Q6_Theology == 3 ~ "neutral",
|
||||
TRUE ~ NA
|
||||
) %>% factor(levels = c("low", "neutral", "high"))
|
||||
)
|
||||
|
||||
# For Q6 - interest
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate(
|
||||
Q6_Religious_Studies = ifelse(Q6_Religious_Studies == 0, NA, Q6_Religious_Studies),
|
||||
interest_religion_bin = case_when(
|
||||
Q6_Religious_Studies < 3 ~ "high",
|
||||
Q6_Religious_Studies > 3 ~ "low",
|
||||
Q6_Religious_Studies == 3 ~ "neutral",
|
||||
TRUE ~ NA
|
||||
) %>% factor(levels = c("low", "neutral", "high"))
|
||||
)
|
||||
|
||||
# For Q7 - employability prospects
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate(
|
||||
Q7_Theology = ifelse(Q7_Theology == 0, NA, Q7_Theology),
|
||||
employability_optimism_theology_bin = case_when(
|
||||
Q7_Theology < 3 ~ "high",
|
||||
Q7_Theology > 3 ~ "low",
|
||||
Q7_Theology == 3 ~ "neutral",
|
||||
TRUE ~ NA
|
||||
) %>% factor(levels = c("low", "neutral", "high"))
|
||||
)
|
||||
|
||||
# For Q7 - employability prospects
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate(
|
||||
Q7_Religious_Studies = ifelse(Q7_Religious_Studies == 0, NA, Q7_Religious_Studies),
|
||||
employability_optimism_religion_bin = case_when(
|
||||
Q7_Religious_Studies < 3 ~ "high",
|
||||
Q7_Religious_Studies > 3 ~ "low",
|
||||
Q7_Religious_Studies == 3 ~ "neutral",
|
||||
TRUE ~ NA
|
||||
) %>% factor(levels = c("low", "neutral", "high"))
|
||||
)
|
||||
|
||||
# For Q8 - employability prospects
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate(
|
||||
Q8 = ifelse(Q8 == 6, NA, Q8),
|
||||
theology_for_bin = case_when(
|
||||
Q8 < 3 ~ "religious",
|
||||
Q8 > 3 ~ "all_people",
|
||||
Q8 == 3 ~ "neutral",
|
||||
TRUE ~ NA
|
||||
) %>% factor(levels = c("all_people", "neutral", "religious"))
|
||||
)
|
||||
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate(
|
||||
Q9 = ifelse(Q9 == 6, NA, Q9),
|
||||
religion_for_bin = case_when(
|
||||
Q9 < 3 ~ "religious",
|
||||
Q9 > 3 ~ "all_people",
|
||||
Q9 == 3 ~ "neutral",
|
||||
TRUE ~ NA
|
||||
) %>% factor(levels = c("all_people", "neutral", "religious"))
|
||||
)
|
||||
|
||||
# Q17 non-white / white ethnicity bins
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate(
|
||||
Q17 = ifelse(Q17 == 0, NA, Q17),
|
||||
ethnicity_bin = case_when(
|
||||
Q17 > 13 | Q17 < 18 ~ "white",
|
||||
TRUE ~ "non-white"
|
||||
) %>% factor(levels = c("white", "non-white"))
|
||||
)
|
||||
|
||||
# Q18 non-religious / institutioal bins
|
||||
admissions_data <- admissions_data %>%
|
||||
mutate(
|
||||
Q18 = ifelse(Q18 == 0, NA, Q18),
|
||||
religion_bin = case_when(
|
||||
Q18 %in% c(1, 2, 5, 17) ~ "non-religious",
|
||||
TRUE ~ "religious"
|
||||
) %>% factor(levels = c("non-religious", "religious"))
|
||||
)
|
||||
|
||||
```
|
||||
|
||||
```{r correlations}
|
||||
Q5_data <- select(admissions_data, Q5_Philosophy:Q5_Business)
|
||||
cor(admissions_data$Q5_Philosophy, admissions_data$Q6_Philosophy)
|
||||
|
||||
```
|
||||
|
||||
# Basic demographic summary visualisations:
|
||||
|
|
@ -45,15 +238,21 @@ if (dir.exists("derivedData") == FALSE) {
|
|||
|
||||
# 1. Calculate for age of respondent:
|
||||
|
||||
# JK note: To keep things tidy, I've shifted the code here so that this isn't overwriting the dataset, but is instead operating off a separate df (same below)
|
||||
TSR_data_summaries_age <- factor(TSR_data$Age, levels = c(1, 2, 3, 4, 5, 6, 7, 8), labels = c("15 or under", "16", "17", "18", "19", "20", "21 or over", "Prefer not to say"))
|
||||
age_pie <- pie(table(TSR_data_summaries_age), col=coul3, cex = 0.8)
|
||||
age <- factor(admissions_data$Q2), levels = c(1, 2, 3, 4, 5, 6, 7, 8), labels = c("15 or under", "16", "17", "18", "19", "20", "21 or over", "Prefer not to say"))
|
||||
age_pie <- pie(table(admissions_data$Q2), col=coul3, cex = 0.8)
|
||||
# JK note: adding in a bar chart here, as according to the interwebs it's (apparently?) more accurate to visualise than bar charts
|
||||
data_summaries_age <- ggplot(TSR_data, aes(TSR_data_summaries_age)) + geom_bar()
|
||||
data_summaries_age + labs(title = "Respondent Age Distribution", x = "Age", y = "")
|
||||
|
||||
ggplot(admissions_data, aes(factor(Q2))) +
|
||||
geom_bar() +
|
||||
geom_text(stat = "count", aes(label = after_stat(count)), vjust = -0.5) +
|
||||
labs(title = "Respondent Age Distribution", x = "Age", y = "") +
|
||||
scale_x_discrete(labels = labels(q2_labels))
|
||||
|
||||
# save to png file for reports
|
||||
ggsave("figures/TSR_data_summaries_age.png")
|
||||
```
|
||||
|
||||
```{r}
|
||||
# 2. Calculate for year of study:
|
||||
|
||||
TSR_data_summaries_yos <- factor(TSR_data$MOSTRECENTyearofstudy, levels = c(1, 2, 3, 4, 5, 6, 7, 8, 9), labels = c("Year 11/S4/Year 12(NI)", "Year 12/S5/Year 13(NI)", "Year 13/S6/Year 14(NI)", "I am currently on a gap year", "I am currently on an undergraduate/HE college course", "I am in full-time employment", "I am unemployed", "Other", "Prefer not to say"))
|
||||
|
|
@ -62,7 +261,9 @@ data_summaries_yos <- ggplot(TSR_data, aes(TSR_data_summaries_yos)) + geom_bar()
|
|||
data_summaries_yos + labs(title = "Respondent Most Recent Year of Study", x = "", y = "")
|
||||
# save to png file for reports
|
||||
ggsave("figures/TSR_data_summaries_yos.png")
|
||||
```
|
||||
|
||||
```{r}
|
||||
# 3. Gender identity:
|
||||
|
||||
TSR_data_summaries_gender <- factor(TSR_data$Gender, levels = c(1, 2, 3, 4), labels = c("Male", "Female", "I identify my gender in another way", "Prefer not to say"))
|
||||
|
|
@ -214,7 +415,9 @@ employability_bar <- ggplot(employability_mean, aes(x = Subject, y = Employabili
|
|||
employability_bar + labs(title = "please rate ... employability prospects", x = "", y = "")
|
||||
# save to png file for reports
|
||||
ggsave("figures/TSR_data_subject_employability.png")
|
||||
```
|
||||
|
||||
```{r}
|
||||
### Likert Stacked Bar Chart ###
|
||||
|
||||
# Take selection of data re: understanding
|
||||
|
|
@ -274,10 +477,14 @@ str(Understanding_data)
|
|||
levels(Understanding_data)
|
||||
summary(Understanding_data)
|
||||
likert_test_understand <- likert(Understanding_data)
|
||||
Understanding_data <- Q5_data
|
||||
likert_test_understand <- likert(Q5_data)
|
||||
plot(likert_test_understand)
|
||||
# save to png file for reports
|
||||
ggsave("figures/understanding_likert.png")
|
||||
```
|
||||
|
||||
```{r}
|
||||
Interest_data <- TSR_data[, 18:29]
|
||||
# Convert each column to factors
|
||||
Interest_data$InterestinstudyingPhilosophy = factor(Interest_data$InterestinstudyingPhilosophy,
|
||||
|
|
|
|||
Loading…
Reference in a new issue