For this assignment, I have decided to use the “What Do Men Think It Means To Be A Man?” data set. I will be looking at the raw responses.
Each row represents one respondent and each column is the question that they answered, and the row content contains their answers to the question.
The article related to the data set was written by Ella Koeze and Anna Maria Barry Jester. It reports on a survey of 1,615 American men, and talks about how their perception on masculinity changed after the #MeToo movement.
My subset of the data frame
I found it interesting that some respondent of the respondent deemed themselves as “Very masculine”, and so I would like to know more about the subgroup of people that answered the first question this way.
I will be keeping the following column:
#Load the csv file
response <- read_csv("raw-responses.csv")## New names:
## Rows: 1615 Columns: 98
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (96): StartDate, EndDate, q0001, q0002, q0004_0001, q0004_0002, q0004_00... dbl
## (2): ...1, weight
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `` -> `...1`#Looking at the initial table
response## # A tibble: 1,615 × 98
## ...1 StartDate EndDate q0001 q0002 q0004_0001 q0004_0002 q0004_0003
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 1 5/10/18 4:01 5/10/18 4:06 Some… Some… Not selec… Not selec… Not selec…
## 2 2 5/10/18 6:30 5/10/18 6:53 Some… Some… Father or… Not selec… Not selec…
## 3 3 5/10/18 7:02 5/10/18 7:09 Very… Not … Father or… Not selec… Not selec…
## 4 4 5/10/18 7:27 5/10/18 7:31 Very… Not … Father or… Mother or… Other fam…
## 5 5 5/10/18 7:35 5/10/18 7:42 Very… Very… Not selec… Not selec… Other fam…
## 6 6 5/10/18 8:25 5/10/18 8:34 Very… Some… Father or… Not selec… Not selec…
## 7 7 5/10/18 8:29 5/10/18 8:41 Some… Not … Father or… Mother or… Other fam…
## 8 8 5/10/18 10:04 5/10/18 10:… Some… Some… Father or… Not selec… Not selec…
## 9 9 5/10/18 11:00 5/10/18 11:… Very… Not … Father or… Not selec… Not selec…
## 10 10 5/11/18 12:36 5/11/18 12:… Some… Some… Father or… Not selec… Not selec…
## # ℹ 1,605 more rows
## # ℹ 90 more variables: q0004_0004 <chr>, q0004_0005 <chr>, q0004_0006 <chr>,
## # q0005 <chr>, q0007_0001 <chr>, q0007_0002 <chr>, q0007_0003 <chr>,
## # q0007_0004 <chr>, q0007_0005 <chr>, q0007_0006 <chr>, q0007_0007 <chr>,
## # q0007_0008 <chr>, q0007_0009 <chr>, q0007_0010 <chr>, q0007_0011 <chr>,
## # q0008_0001 <chr>, q0008_0002 <chr>, q0008_0003 <chr>, q0008_0004 <chr>,
## # q0008_0005 <chr>, q0008_0006 <chr>, q0008_0007 <chr>, q0008_0008 <chr>, …#Only keeping the questions that I want to observe
cl <- response[, c("q0001","q0002","q0026","q0029","age3")]#Adding an index to distinguish each respondents
cl$respondent_id <- seq.int(nrow(cl))#Rename columns
cl <- rename(cl,
masculinity_lvl = q0001 ,
masculinity_importance = q0002,
sex_orientation = q0026,
highest_ed = q0029,
age_group = age3
)#Modify column content
cl$masculinity_lvl <- gsub("masculine", "", cl$masculinity_lvl, ignore.case = TRUE)
cl$masculinity_importance <- gsub("important", "", cl$masculinity_importance, ignore.case = TRUE)#Only filter out my desired rows
cl_v <- cl %>%
mutate(across(where(is.character), trimws))
cl_v <- cl_v %>%
filter(masculinity_lvl == "Very")cl_v## # A tibble: 612 × 6
## masculinity_lvl masculinity_importance sex_orientation highest_ed age_group
## <chr> <chr> <chr> <chr> <chr>
## 1 Very Not too Straight College gra… 35 - 64
## 2 Very Not too No answer Some college 65 and up
## 3 Very Very Straight College gra… 35 - 64
## 4 Very Somewhat Straight Post gradua… 65 and up
## 5 Very Not at all Straight Some college 35 - 64
## 6 Very Somewhat Straight College gra… 35 - 64
## 7 Very Somewhat Straight College gra… 35 - 64
## 8 Very Very Straight Some college 18 - 34
## 9 Very Somewhat Straight College gra… 65 and up
## 10 Very Somewhat Straight College gra… 35 - 64
## # ℹ 602 more rows
## # ℹ 1 more variable: respondent_id <int>From this selected article, I intend to explore the data to see if there is a strong correlation with the respondent putting “Very masculine” and one of the other variables that I have kept in the table. This is to see if a specific background can be attributed to a person’s image of their masculinity.