Exclusion

Library

library(formr)
library(dplyr)

## 
## Attache Paket: 'dplyr'

## Die folgenden Objekte sind maskiert von 'package:formr':
## 
##     first, last

## Die folgenden Objekte sind maskiert von 'package:stats':
## 
##     filter, lag

## Die folgenden Objekte sind maskiert von 'package:base':
## 
##     intersect, setdiff, setequal, union

Data

Load selected data based on 01_datawrangling

fulldata_selected_wrangled = read.csv(file = "fulldata_selected_wrangled.csv")[,-1]

Exclusion Process

data_included = fulldata_selected_wrangled

All participants younger than 18

From the initial dataset of respondents (N = 94,738), 26653 could not participate, because they were younger than 18 years of age.

data_included = fulldata_selected_wrangled %>%
  filter(age >= 18 |
         is.na(age))

nrow(data_included)

## [1] 68100

fulldata_selected_wrangled = data_included

The total number of responses was 68100.

All participants who do not identify as women

From the initial dataset of respondents (n = 68,100), we excluded 3221 participants because they did not identify as women (Men, Genderqueer/Nonbinary; None of the above; Prefer not to say; Other)

table(data_included$sex)

## 
## Genderqueer/Nonbinary                   Man     None of the above 
##                   840                  2055                    58 
##                 Other     Prefer not to say                 Woman 
##                    43                   225                 64879

data_included = data_included %>%
  filter((sex != "Man" &
         sex != "Genderqueer/Nonbinary" &
         sex != "None of the above" &
         sex != "Prefer not to say" &
         sex != "Other")  |
         is.na(sex))

table(data_included$sex)

## 
## Woman 
## 64879

table(is.na(data_included$sex))

## 
## FALSE 
## 64879

All participants who do not identify as heterosexual

From the initial dataset of respondents (n = 68,100), we excluded 13454 participants because they did not identify as heterosexual (Lesbian/Gay/Homosexual; Bisexual/Pansexual; Queer; Asexual; Prefer not to say; Other)

Consecutively, this means we excluded 11946 participants because they did not identify as heterosexual (Lesbian/Gay/Homosexual; Bisexual/Pansexual; Queer; Asexual; Prefer not to say; Other)

table(data_included$sexual_orientation)

## 
##                Asexual     Bisexual/Pansexual Lesbian/Gay/Homosexual 
##                    457                   8857                   1208 
##                  Other      Prefer not to say                  Queer 
##                    266                    584                    574 
##  Straight/Heterosexual 
##                  52933

data_included = data_included %>%
  filter((sexual_orientation != "Lesbian/Gay/Homosexual" & sexual_orientation != "Bisexual/Pansexual" &
         sexual_orientation != "Queer" & sexual_orientation != "Asexual" &
         sexual_orientation != "Prefer not to say" & sexual_orientation != "Other") |
         is.na(sexual_orientation))

table(data_included$sexual_orientation)

## 
## Straight/Heterosexual 
##                 52933

table(is.na(data_included$sexual_orientation)) 

## 
## FALSE 
## 52933

All participants who indicated being in a relationship

fulldata_selected_wrangled = fulldata_selected_wrangled %>%
  mutate(relationship_binary = ifelse(is.na(relationship), 0,
                                      ifelse(relationship %contains% "New (less than 1 month old) romantic and/or sexual relationship", 1,
                                             ifelse(relationship %contains% "Ongoing (longer than 1 month) uncommitted/non-exclusive romantic and/or sexual relationship", 1,
                                                    ifelse(relationship %contains% "Long-term committed/exclusive sexual relationship with one or more partners", 1,
                                                           ifelse(relationship %contains% "Other", 1, 0))))))
table(fulldata_selected_wrangled$relationship_binary)

## 
##     0     1 
## 24052 44048

data_included = data_included %>%
  mutate(relationship_binary = ifelse(is.na(relationship), 0,
                                      ifelse(relationship %contains% "New (less than 1 month old) romantic and/or sexual relationship", 1,
                                             ifelse(relationship %contains% "Ongoing (longer than 1 month) uncommitted/non-exclusive romantic and/or sexual relationship", 1,
                                                    ifelse(relationship %contains% "Long-term committed/exclusive sexual relationship with one or more partners", 1,
                                                           ifelse(relationship %contains% "Other", 1, 0))))))
table(data_included$relationship_binary)

## 
##     0     1 
## 18144 34789

From the initial dataset of respondents (n = 68,100), we excluded 4.4048^{4} participants because they indicated being in a relationship (New (less than 1 month old) romantic and/or sexual relationship ; Ongoing (longer than 1 month) uncommitted/non-exclusive romantic and/or sexual relationship; Long-term committed/exclusive sexual relationship with one or more partners) or participants where it was not sure whether they were currently single (Other).

Consecutively, we excluded 3.4789^{4} participants because they indicated being in a relationship (New (less than 1 month old) romantic and/or sexual relationship ; Ongoing (longer than 1 month) uncommitted/non-exclusive romantic and/or sexual relationship; Long-term committed/exclusive sexual relationship with one or more partners) or participants where it was not sure whether they were currently single (Other).

data_included = data_included %>% filter(relationship_binary == 0) %>%
  select(-relationship1, -relationship2, -relationship3, -relationship4, -relationship5, -relationship_binary)

All participants who did not specify their political orientation

From the initial dataset of respondents (n = 68,100), we excluded 15025 participants because they did not specify their political orientation.

Consecutively, we excluded 4329 participants because they did not specify their political orientation.

data_included = data_included %>%
  mutate(political_orientation = ifelse(political_orientation == "", NA, political_orientation))

table(is.na(data_included$political_orientation))

## 
## FALSE  TRUE 
## 13815  4329

data_included = data_included %>%
  filter(!is.na(political_orientation))

All participants who did not answer the survey seriously or chose not to answer the seriousness question

From the initial dataset of respondents (n = 68,100), we excluded 2070 participants because they indicated not answering the survey seriously (I did not answer seriously, please disregard my information; I choose not to answer)

Consecutively, we excluded 558 participants because they indicated not answering the survey seriously (I did not answer seriously, please disregard my information; I choose not to answer)

table(data_included$answer_accuracy)

## 
##                                              I choose not to answer. 
##                                                                  335 
##         I did not answer seriously; please disregard my information. 
##                                                                  223 
## I took the survey seriously; please use my information in the study. 
##                                                                12461

data_included = data_included %>%
  filter((answer_accuracy != "I did not answer seriously; please disregard my information." &
         answer_accuracy != "I choose not to answer.") |
         is.na(answer_accuracy))

We have 796 missings for answer_accuracy here. As mentioned in the preregistration, we included these participants in our analyses.

missings = data_included %>% filter(is.na(answer_accuracy))

Save Data

write.csv(data_included, file = "data_included.csv")