In the last chapter we explored some high level data about religion in the UK. This was a census sample, which usually refers to an attempt to get as comprehensive a sample as possible. But this is actually fairly unusual in practice. Depending on how complex a subject is, and how representative we want our data to be, it's much more common to use selective sampling, that is survey responses at n=100 or n=1000 at a maximum. The advantage of a census sample is that you can explore how a wide range of other factors - particularly demographics - intersect with your question. And this can be really valuable in the study of religion, particularly as you will see as we go along that responses to some questions are more strongly correlated to things like economic status or educational attainment than they are to religious affiliation. It can be hard to tell if this is the case unless you have enough of a sample to break down into a number of different kinds of subsets. But census samples are complex and expensive to gather, so they're quite rare in practice.
For this chapter, I'm going to walk you through a data set that a colleague (Charles Ogunbode) and I collected in 2021. Another problem with smaller, more selective samples is that researchers can often undersample minoritised ethnic groups. This is particularly the case with climate change research. Until the time we conducted this research, there had not been a single study investigating the specific experiences of people of colour in relation to climate change in the UK. Past researchers had been content to work with large samples, and assumed that if they had done 1000 surveys and 50 of these were completed by people of colour, they could "tick" the box. But 5% is actually well below levels of representation in the UK generally, and even more sharply the case for specific communities. And if we bear in mind that non-white respondents are (of course!) a highly heterogenous group, we're even more behind in terms of collecting data that can improve our knowledge. Up until recently researchers just haven't been paying close enough attention to catch the significant neglect of the empirical field that this represents.
While I've framed my comments above in terms of climate change research, it is also the case that, especially in diverse societies like the USA, Canada, the UK etc., paying attention to non-majority groups and people and communities of colour automatically draws in a strongly religious sample. This is highlighted in one recent study done in the UK, the "[Black British Voices Report](https://www.cam.ac.uk/stories/black-british-voices-report)" in which the researchers observed that "84% of respondents described themselves as religious and/or spiritual". My comments above in terms of controlling for other factors remains important here - these same researchers also note that "despire their significant important to the lives of Black Britons, only 7% of survey respondents reported that their religion was more defining of their identity than their race".
We've decided to open up access to our data and I'm highlighting it in this book because it's a unique opportunitiy to explore a dataset that emphasises diversity from the start, and by extension, provides some really interesting ways to use data science techniques to explore religion in the UK.
The first thing to note here is that we've drawn in a different type of data file, this time from an `.sav` file, usully produced by the statistics software package SPSS. This uses a different R Library (I use `haven` for this). The upside is that in some cases where you have survey data with both a code and a value like "1" is eqivalent to "very much agree" this will preserve both in the R dataframe that is created. Now that you've loaded in data, you have a new R dataframe called "climate_experience_data" with a lot of columns with just under 1000 survey responses.
# How can you ask about religion?
One of the challenges we faced when running this study is how to gather responsible data from surveys regarding religious identity. We'll dive into this in depth as we do analysis and look at some of the agreements and conflicts in terms of respondent attribution. Just to set the stage, we used the following kinds of question to ask about religion and spirituality:
1. Question 56 asks respondents simply, "What is your religion?" and then provides a range of possible answers. We included follow-up questions regarding denomination for respondents who indicated they were "Christian" or "Muslim". For respondents who ticked "Christian" we asked, "What is your denomination?" nad for respondents who ticked "Muslim" we asked "Which of the following would you identify with?" and then left a range of possible options which could be ticked such as "Sunni," "Shia," "Sufi" etc.
This is one way of measuring religion, that is, to ask a person if they consider themselves formally affiliated with a particular group. This kind of question has some (serious) limitations, but we'll get to that in a moment.
We also asked respondents (Q57): "Regardless of whether you belong to a particular religion, how religious would you say you are?" and then provided a slider from 0 (not religious at all) to 10 (very religious).
We included some classic indicators about how often respondents go to worship (Q58): Apart from weddings, funerals and other special occasions, how often do you attend religious services? and (Q59): "Q59 Apart from when you are at religious services, how often do you pray?"
- More than once a week (1)
- Once a week (2)
- At least once a month (3)
- Only on special holy days (4)
- Never (5)
Each of these measures a particular kind of dimension, and it is interesting to note that sometimes there are stronger correlations between how often a person attends worship services (weekly versus once a year) and a particular view, than there is between their affiliation (if they are Christian or Pagan). We'll do some exploratory work shortly to see how this is the case in our sample. We also included a series of questions about spirituality in Q52 and used a nature relatedness scale Q51.
You'll find that many surveys will only use one of these forms of question and ignore the rest. I think this is a really bad idea as religious belonging, identity, and spirituality are far too complex to work off a single form of response. We can also test out how these different attributions relate to other demographic features, like interest in politics, economic attainment, etc.
Let's dive into the data and see how this all works out:
```{r}
# Load some new libraries used by functions below
library(RColorBrewer)
library(hrbrthemes) # Used for ipsum theme etc.
library(ggeasy) # used for easy_center_title() which is not strictly necessary, but tidier than theme(plot.title = element_text(hjust = 0.5))
# Define colour palettes
# TODO: confirm final colour scheme for charts and normalise across usage of different themes
coul3 <- brewer.pal(3, "RdYlBu") # Using RdYlBu range to generate 3 colour palette: https://colorbrewer2.org/#type=diverging&scheme=RdYlBu&n=5
# Importing code for colortools() now deprecated and removed from CRAN here. Some minor modifications to update code, but generally all credit here goes to Gaston Sanchez
setColors <- function(color, num) {
# convert to RGB
rgb_col = col2rgb(color)
# convert to HSV
hsv_col = rgb2hsv(rgb_col)[,1]
# get degree
hue = hsv_col[1]
sat = hsv_col[2]
val = hsv_col[3]
cols = seq(hue, hue + 1, by=1/num)
cols = cols[1:num]
cols[cols > 1] <- cols[cols > 1] - 1
# get colors with hsv
colors = hsv(cols, sat, val)
# transparency
if (substr(color, 1, 1) == "#" && nchar(color) == 9)
df$response <- fct_recode(df$response, "More than once a week" = "1", "Once a week" = "2", "At least once a month" = "3", "Only on special holy days" = "4", "Never" = "5")
df %>%
# we need to get the data including facet info in long format, so we use pivot_longer()
df$response <- fct_recode(df$response, "More than once a week" = "1", "Once a week" = "2", "At least once a month" = "3", "Only on special holy days" = "4", "Never" = "5")
df %>%
# we need to get the data including facet info in long format, so we use pivot_longer()
## code if a specific palette is needed for matching
fill = wheel(ochre, num = as.integer(count(q6_data[1])))
# make plot
q6_data_plot <- ggplot(q6_data, aes(x = n, y = response, fill = fill)) +
geom_col(colour = "white") +
## add percentage labels
geom_text(aes(label = perc),
## make labels left-aligned and white
hjust = 1, colour = "black", size=4) + # use nudge_x = 30, to shift position
## reduce spacing between labels and bars
scale_fill_identity(guide = "none") +
## get rid of all elements except y axis labels + adjust plot margin
theme_ipsum_rc() +
theme(plot.margin = margin(rep(15, 4))) +
easy_center_title() +
# with thanks for helpful info on doing wrap here: https://stackoverflow.com/questions/21878974/wrap-long-axis-labels-via-labeller-label-wrap-in-ggplot2
