Table 2. Race and gender implicit bias levels

Attempting to recreate Table 2 for means and SDs (excluding t-values, and p-values):

Table 2 data: calculating every variable separately and manually

Load relevant packages

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──

## ✓ ggplot2 3.3.4     ✓ purrr   0.3.4
## ✓ tibble  3.1.2     ✓ dplyr   1.0.7
## ✓ tidyr   1.1.3     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(dplyr)

Calculating mean (and SD) baseline Race bias

BaselineRace <- cleandata %>% #creating new data "BaselineRace" from "cleandata"
  select(base_IAT_race) %>% #select variable "base_IAT_race" from "cleandata"
  summarise(BaselineRaceMean = mean(base_IAT_race), BaselineRaceSD = sd(base_IAT_race)) #calculate mean and SD for selected variable

## Error in select(., base_IAT_race): object 'cleandata' not found

print(BaselineRace)

## Error in print(BaselineRace): object 'BaselineRace' not found

Calculating mean (and SD) baseline gender bias

BaselineGender <- cleandata %>% #creating new data "BaselineRace" from "cleandata"
  select(base_IAT_gen) %>% #select variable "base_IAT_gen" from "cleandata"
  summarise(BaselineGenderMean = mean(base_IAT_gen), BaselineGenderSD = sd(base_IAT_gen)) #calculate mean and SD for selected variable

## Error in select(., base_IAT_gen): object 'cleandata' not found

print(BaselineGender)

## Error in print(BaselineGender): object 'BaselineGender' not found

Calculating prenap race bias

PrenapRace <- cleandata %>% #creating new data "PrenapRace" from "cleandata"
  select(pre_IAT_race) %>% #select variable "pre_IAT_race" from "cleandata"
  summarise(PrenapRaceMean = mean(pre_IAT_race), PrenapRaceSD = sd(pre_IAT_race)) #calculate mean and SD for selected variable

## Error in select(., pre_IAT_race): object 'cleandata' not found

print(PrenapRace)

## Error in print(PrenapRace): object 'PrenapRace' not found

Calculating prenap gender bias

PrenapGender <- cleandata %>% #creating new data "PrenapGender" from "cleandata"
  select(pre_IAT_gen) %>% #select variable "PrenapGender" from "cleandata"
  summarise(Prenapgendermean = mean(pre_IAT_gen), PrenapRaceSD = sd(pre_IAT_gen)) #calculate mean and SD for selected variable

## Error in select(., pre_IAT_gen): object 'cleandata' not found

print(PrenapGender)

## Error in print(PrenapGender): object 'PrenapGender' not found

Table 2 data: simplified code to calculate all the means and SDS for race and gender IATs

Credits to Julia for finding this hack

implicitbiaslevels <- cleandata %>% 
  select(base_IAT_race, base_IAT_gen, pre_IAT_race, pre_IAT_gen) #Selecting these variables from the     "cleandata" dataset to create new data "implicitbiaslevels"

## Error in select(., base_IAT_race, base_IAT_gen, pre_IAT_race, pre_IAT_gen): object 'cleandata' not found

#now I'm going to calculate the mean and sd of all of these variables:

implicitbiaslevels <- implicitbiaslevels %>% 
  summarise(across(contains("IAT"), list(mean = mean, sd = sd))) #captures and calculates the means and SDs of each variable that contains "IAT" within its variable name. Lists the calculated means and sds for each variable under the label "mean" and "sd".

## Error in summarise(., across(contains("IAT"), list(mean = mean, sd = sd))): object 'implicitbiaslevels' not found

#now the data "implicitbiaslevels" has the means and SDs for each of the variables previously selected, instead of having to separately code for each mean and SD needed and then having to create a new dataframe.

Recreate Table 2

Load needed packages. We are using gt() package again because all the research we have done has indicated that this package is the simplest to format and use.

library(gt)
library(glue)

## 
## Attaching package: 'glue'

## The following object is masked from 'package:dplyr':
## 
##     collapse

#Tried to recreate Table 2 using simplified code and dataset "implicitbiaslevels". We were hoping that this simplified code could be used to quickly and simply recreate the table. 
implicitbiaslevels %>% 
  gt() %>% 
  tab_header(
    title = "Table 2: Race and Gender Implicit Bias Levels") %>% #title
  tab_source_note("Implicit bias values are the average D600 score for each timepoint") %>% #creates source note in the table footer
  fmt_number(columns = vars(mean1, mean2,  SD1, SD2), decimals = 2) %>% #formats values to 2 decimal places
      #vars() function used to select variables to input into the columns
  tab_spanner(
    label = "Baseline", #Spanner Column label 
    columns = c(mean1, SD1) #selects variables "mean1" and "SD1" for the 2 columns underneath the spanner column label "Baseline"
  ) %>% 
  tab_spanner(
    label = "Prenap", #Spanner Column label 
    columns = c(mean2, SD2) #selects variables "mean2" and "SD2" for the 2 columns underneath the spanner column label "Prenap"
  ) %>% 
  tab_row_group( 
    label = "Race", #label for row group 
    rows = 1  #1 row for this row group 
  ) %>% 
  tab_row_group(
    label = "Gender", #label for row group
    rows = 2 #2 rows for this row group 
  )

## Error in dplyr::group_vars(data): object 'implicitbiaslevels' not found

print(implicitbiaslevels)

## Error in print(implicitbiaslevels): object 'implicitbiaslevels' not found

#Works but does not let the mean be inputted alone - needs to be identified as separate columns, stub labels also don't sit flush but look more like a subheader

Manually inputting the data:

#Since using the simplified dataset "implicitbiaslevels" didn't work, I tried inserting/formatting the same values differently by creating a new dataframe with different labels. 
#values are taken from the "implicitbiaslevels" data. 
table2 <- tibble( #3 columns
  Variables = c("base_IAT_race", "base_IAT_gen", "pre_IAT_race", "pre_IAT_gen"), #new variable names 
  Mean = c(0.619, 0.494, 0.202, 0.311), 
  SD = c(0.442, 0.362, 0.563, 0.375)
)

print(table2)

## # A tibble: 4 x 3
##   Variables      Mean    SD
##   <chr>         <dbl> <dbl>
## 1 base_IAT_race 0.619 0.442
## 2 base_IAT_gen  0.494 0.362
## 3 pre_IAT_race  0.202 0.563
## 4 pre_IAT_gen   0.311 0.375

Recreate Table 2 using manually-inputed data "table2"

table2 %>% 
  gt( #use gt() package to create table
    rowname_col = "Race", "Gender" #gave the 2 row names "Race" and "Gender"
  ) %>% 
  tab_header(
    title = "Table 2: Race and Gender Implicit Bias Levels") %>% #title for the table
  tab_source_note("Implicit bias values are the average D600 score for each timepoint") %>% #creates source note in the table footer
  fmt_number(columns = vars(Mean, SD, Mean, SD), decimals = 2) %>% #formats values to 2 decimal places
      #vars() function used to select variables to input into the columns
  tab_spanner(
    label = "Baseline", #Spanner column label
    columns = c(base_IAT_race, base_IAT_gen) #selects variables "base_IAT_race" and "base_IAT_gen" for the 2 columns underneath the spanner column label "Baseline"
  ) %>% 
  tab_spanner(
    label = "Prenap", #Spanner column label 
    columns = c(pre_IAT_race, pre_IAT_gen) #selects variables "pre_IAT_race" and "pre_IAT_gen" for the 2 columns underneath the spanner column label "Prenap"
  )

## Warning: `columns = vars(...)` has been deprecated in gt 0.3.0:
## * please use `columns = c(...)` instead

## Warning: `columns = vars(...)` has been deprecated in gt 0.3.0:
## * please use `columns = c(...)` instead

## Error: Can't subset columns that don't exist.
## x Column `base_IAT_race` doesn't exist.

#Keeps giving this error: "Error: Can't subset columns that don't exist. x Column `Mean` doesn't exist."

Create new dataframe "table_2"

#Tried formatting values into a new dataframe to more closely match the table that we are trying to reproduce. Values are taken from the same "implicitbiaslevels" data as before. 
table_2 <- tibble( #4 different columns 
  mean1 = c(0.6186929, 0.4943818),
  mean2 = c(0.2023364, 0.3109984),
  SD1 = c(0.4423884, 0.36228),
  SD2 = c(0.5633004, 0.3748071)
)
print(table_2)

## # A tibble: 2 x 4
##   mean1 mean2   SD1   SD2
##   <dbl> <dbl> <dbl> <dbl>
## 1 0.619 0.202 0.442 0.563
## 2 0.494 0.311 0.362 0.375

Recreate Table 2 using "table_2" dataframe

table_2 %>% 
  gt() %>% #use gt() package to create table
  tab_header( #format table header
    title = "Table 2: Race and Gender Implicit Bias Levels") %>% #title of table 
  tab_source_note("Implicit bias values are the average D600 score for each timepoint") %>% #creates source note in the table footer
  fmt_number(columns = vars(mean1, mean2,  SD1, SD2), decimals = 2) %>% #formats values to 2 decimal places
      #vars() function used to select variables to input into the columns
  tab_spanner( 
    label = "Baseline", #Spanner column label 
    columns = c(mean1, SD1) #selects variables "mean1" and "SD1" for the 2 columns underneath the spanner column label "Baseline"
  ) %>% 
  tab_spanner(
    label = "Prenap", #Spanner column label 
    columns = c(mean2, SD2) #selects variables "mean2" and "SD2" for the 2 columns underneath the spanner column label "Prenap"
  ) %>% 
  tab_row_group( 
    label = "Race", #Row group label
    rows = 1 #1 rows underneath this row group  
  ) %>% 
  tab_row_group(
    label = "Gender", #Row group label
    rows = 2 #2 rows underneath this row group 
  )

## Warning: `columns = vars(...)` has been deprecated in gt 0.3.0:
## * please use `columns = c(...)` instead

## Warning: `columns = vars(...)` has been deprecated in gt 0.3.0:
## * please use `columns = c(...)` instead

Table 2: Race and Gender Implicit Bias Levels
Baseline		Prenap
mean1	SD1	mean2	SD2
Gender
0.49	0.36	0.31	0.37
Race
0.62	0.44	0.20	0.56
Implicit bias values are the average D600 score for each timepoint

print(table_2)

## # A tibble: 2 x 4
##   mean1 mean2   SD1   SD2
##   <dbl> <dbl> <dbl> <dbl>
## 1 0.619 0.202 0.442 0.563
## 2 0.494 0.311 0.362 0.375

#Format is now finally showing as is seen in original paper
#However, outputted column names as "mean1", "SD1", "mean2", "SD2", which is not identical to what is seen in the paper
#Need to figure out how to change these tab names to "Mean" and "SD"

#Used same code as before but getting rid of tab_row_group() function (that was used to label the group row names) and 
#Also, instead using cols_label() function to label the group columns
table_2 %>% 
  gt() %>% #use gt() package 
  tab_header(
    title = "Table 2: Race and Gender Implicit Bias Levels") %>% #table title 
  tab_source_note("Implicit bias values are the average D600 score for each timepoint") %>% #creates source note in the table footer
  fmt_number(columns = vars(mean1, mean2,  SD1, SD2), decimals = 2) %>% #formats values to 2 decimal places
      #vars() function used to select variables to input into the columns
  tab_spanner(
    label = "Baseline",
    columns = c(mean1, SD1)
  ) %>% 
  tab_spanner(
    label = "Prenap",
    columns = c(mean2, SD2)
  ) %>% 
  cols_label(mean1 = "mean", mean2 = "mean", SD1 = "SD", SD2 = "SD", label = " ") #changed column labels

## Warning: `columns = vars(...)` has been deprecated in gt 0.3.0:
## * please use `columns = c(...)` instead

## Warning: `columns = vars(...)` has been deprecated in gt 0.3.0:
## * please use `columns = c(...)` instead

## Error in cols_label(., mean1 = "mean", mean2 = "mean", SD1 = "SD", SD2 = "SD", : All column names provided must exist in the input `data` table.

#Kept giving error: "Error in cols_label(., mean1 = "mean", mean2 = "mean", SD1 = "SD", SD2 = "SD", : All column names provided must exist in the input `data` table."

Thus tried creating new dataframe with labels

table2_label <- tibble(
  label = c("Race", "Gender"),
  mean1 = c(0.6186929, 0.4943818),
  mean2 = c(0.2023364, 0.3109984),
  SD1 = c(0.4423884, 0.36228),
  SD2 = c(0.5633004, 0.3748071)
)
print(table2_label)

## # A tibble: 2 x 5
##   label  mean1 mean2   SD1   SD2
##   <chr>  <dbl> <dbl> <dbl> <dbl>
## 1 Race   0.619 0.202 0.442 0.563
## 2 Gender 0.494 0.311 0.362 0.375

Now, tried using the same code as previously but with new dataframe:

table2_label %>% 
  gt() %>% 
  tab_header(
    title = "Table 2. Race and gender implicit bias levels") %>% 
  tab_source_note("Implicit bias values are the average D600 score for each timepoint") %>% #creates source note in the table footer
  fmt_number(columns = vars(mean1, mean2,  SD1, SD2), decimals = 2) %>% #formats values to 2 decimal places
      #vars() function used to select variables to input into the columns
  tab_spanner(
    label = "Baseline", #Spanner column label 
    columns = c(mean1, SD1) #selects variables "mean1" and "SD1" for the 2 columns underneath the spanner column label "Baseline"
  ) %>% 
  tab_spanner(
    label = "Prenap", #Spanner column label 
    columns = c(mean2, SD2) #selects variables "mean2" and "SD2" for the 2 columns underneath the spanner column label "Prenap"
  ) %>% 
  cols_label(mean1 = "Mean", mean2 = "Mean", SD1 = "SD", SD2 = "SD", label = " ") #changes the column labels for each one

## Warning: `columns = vars(...)` has been deprecated in gt 0.3.0:
## * please use `columns = c(...)` instead

## Warning: `columns = vars(...)` has been deprecated in gt 0.3.0:
## * please use `columns = c(...)` instead

Table 2. Race and gender implicit bias levels
	Baseline		Prenap
	Mean	SD	Mean	SD
Race	0.62	0.44	0.20	0.56
Gender	0.49	0.36	0.31	0.37
Implicit bias values are the average D600 score for each timepoint

#originalvariablename = "New column name"


print(table2_label)

## # A tibble: 2 x 5
##   label  mean1 mean2   SD1   SD2
##   <chr>  <dbl> <dbl> <dbl> <dbl>
## 1 Race   0.619 0.202 0.442 0.563
## 2 Gender 0.494 0.311 0.362 0.375

#Everything looks perfect!

Table 2

Jade Gurtala

28/06/2021

Table 2. Race and gender implicit bias levels

Table 2 data: calculating every variable separately and manually

Table 2 data: simplified code to calculate all the means and SDS for race and gender IATs

Recreate Table 2