Crosstab of content type by gender

Performance posts made up 69% of posts by males, compared to only 37% of posts by females. Thus, males were more likely than females to post performance content. Among females, nearly half (47.9%) of posts were endorsement posts. By contrast, endorsement posts made up only 16.7 percent of posts by males. So, females were more likely than males to post endorsement content. A chi-square test found the difference statistically significant.

# ------------------------------
# Setup: Install and load packages
# ------------------------------
if (!require("tidyverse")) install.packages("tidyverse")   # Data wrangling & plotting
if (!require("gmodels")) install.packages("gmodels")       # Crosstabs
if (!require("gt")) install.packages("gt")                 # Table formatting

library(tidyverse)
library(gmodels)
library(gt)

# ------------------------------
# Load the data
# ------------------------------
# Replace "YOURFILENAME.csv" with your dataset name
mydata <- read.csv("NewData.csv") #Edit

################################################
# Content type by gender
################################################

# ------------------------------
# Define Dependent (DV) and Independent (IV) variables
# ------------------------------
# Replace YOURDVNAME and YOURIVNAME with actual column names in your data
mydata$DV <- mydata$Content.Type #Edit
mydata$IV <- mydata$Gender #Edit

mydata <- mydata %>% 
  mutate(DV = case_when(
    Content.Type == 1 ~ "Performance",
    Content.Type == 2 ~ "Personal",
    Content.Type == 3 ~ "Endorsement",
    TRUE ~ "Error"
  ))

# ------------------------------
# Visualization: Stacked bar chart of IV by DV
# ------------------------------
graph <- ggplot(mydata, aes(x = IV, fill = DV)) +
  geom_bar(colour = "black") +
  scale_fill_brewer(palette = "Paired") +
  labs(
    title = "Content Type by Gender",
    x = "Independent Variable",
    y = "Count",
    fill = "Dependent Variable"
  )

#Show the graph
graph

# ------------------------------
# Crosstabulation of DV by IV (DV = rows, IV = columns)
# ------------------------------

crosstab <- mydata %>%
  count(DV, IV) %>%
  group_by(IV) %>%
  mutate(RowPct = 100 * n / sum(n)) %>%
  ungroup() %>%
  mutate(Cell = paste0(n, "\n(", round(RowPct, 1), "%)")) %>%
  select(DV, IV, Cell) %>%
  pivot_wider(names_from = IV, values_from = Cell)

# Format into gt table
crosstab_table <- crosstab %>%
  gt(rowname_col = "DV") %>%
  tab_header(
    title = "Content Type by Gender",
    subtitle = "Counts and (Column Percentages)"
  ) %>%
  cols_label(
    DV = "Dependent Variable"
  )

# Show the polished crosstab table
crosstab_table
Content Type by Gender
Counts and (Column Percentages)
F M
Endorsement 35 (47.9%) 21 (16.7%)
Performance 27 (37%) 87 (69%)
Personal 11 (15.1%) 18 (14.3%)
 
# ------------------------------
# Chi-squared test of independence
# ------------------------------
options(scipen = 999)  # Prevents scientific notation
chitestresults <- chisq.test(mydata$DV, mydata$IV)

# ------------------------------
# Format Chi-squared test results into a table
# ------------------------------
chitest_summary <- tibble(
  Test   = "Chi-squared Test of Independence",
  Chi_sq = chitestresults$statistic,
  df     = chitestresults$parameter,
  p      = chitestresults$p.value
)

chitest_table <- chitest_summary %>%
  gt() %>%
  # Round χ² and p-value to 3 decimals, df to integer
  fmt_number(columns = c(Chi_sq, p), decimals = 3) %>%
  fmt_number(columns = df, decimals = 0) %>%
  tab_header(
    title = "Chi-squared Test Results",
    subtitle = "Test of Independence between DV and IV"
  ) %>%
  cols_label(
    Test   = "Test",
    Chi_sq = "Chi-squared Statistic",
    df     = "Degrees of Freedom",
    p      = "p-value"
  )

# Show the formatted results table
chitest_table
Chi-squared Test Results
Test of Independence between DV and IV
Test Chi-squared Statistic Degrees of Freedom p-value
Chi-squared Test of Independence 24.383 2 0.000

Crosstab of collaboration by gender

Collaboration occurred in 79.4% of posts by males, compared to only 63% of posts by females. The difference was, again, significant, according to a chi-square test. Thus, posts by males were significantly more likely to feature collaboration than were posts by females.

################################################
# Collaboration by gender
################################################

# ------------------------------
# Define Dependent (DV) and Independent (IV) variables
# ------------------------------
# Replace YOURDVNAME and YOURIVNAME with actual column names in your data
mydata$DV <- mydata$Collaboration #Edit
mydata$IV <- mydata$Gender #Edit

mydata <- mydata %>% 
  mutate(DV = case_when(
    Collaboration == 0 ~ "No",
    Collaboration == 1 ~ "Yes",
    TRUE ~ "Error"
  ))

# ------------------------------
# Visualization: Stacked bar chart of IV by DV
# ------------------------------
graph <- ggplot(mydata, aes(x = IV, fill = DV)) +
  geom_bar(colour = "black") +
  scale_fill_brewer(palette = "Paired") +
  labs(
    title = "Collaboration by Gender",
    x = "Independent Variable",
    y = "Count",
    fill = "Dependent Variable"
  )

#Show the graph
graph

# ------------------------------
# Crosstabulation of DV by IV (DV = rows, IV = columns)
# ------------------------------

crosstab <- mydata %>%
  count(DV, IV) %>%
  group_by(IV) %>%
  mutate(RowPct = 100 * n / sum(n)) %>%
  ungroup() %>%
  mutate(Cell = paste0(n, "\n(", round(RowPct, 1), "%)")) %>%
  select(DV, IV, Cell) %>%
  pivot_wider(names_from = IV, values_from = Cell)

# Format into gt table
crosstab_table <- crosstab %>%
  gt(rowname_col = "DV") %>%
  tab_header(
    title = "Collaboration by Gender",
    subtitle = "Counts and (Column Percentages)"
  ) %>%
  cols_label(
    DV = "Dependent Variable"
  )

# Show the polished crosstab table
crosstab_table
Collaboration by Gender
Counts and (Column Percentages)
F M
No 27 (37%) 26 (20.6%)
Yes 46 (63%) 100 (79.4%)
 
# ------------------------------
# Chi-squared test of independence
# ------------------------------
options(scipen = 999)  # Prevents scientific notation
chitestresults <- chisq.test(mydata$DV, mydata$IV)

# ------------------------------
# Format Chi-squared test results into a table
# ------------------------------
chitest_summary <- tibble(
  Test   = "Chi-squared Test of Independence",
  Chi_sq = chitestresults$statistic,
  df     = chitestresults$parameter,
  p      = chitestresults$p.value
)

chitest_table <- chitest_summary %>%
  gt() %>%
  # Round χ² and p-value to 3 decimals, df to integer
  fmt_number(columns = c(Chi_sq, p), decimals = 3) %>%
  fmt_number(columns = df, decimals = 0) %>%
  tab_header(
    title = "Chi-squared Test Results",
    subtitle = "Test of Independence between DV and IV"
  ) %>%
  cols_label(
    Test   = "Test",
    Chi_sq = "Chi-squared Statistic",
    df     = "Degrees of Freedom",
    p      = "p-value"
  )

# Show the formatted results table
chitest_table
Chi-squared Test Results
Test of Independence between DV and IV
Test Chi-squared Statistic Degrees of Freedom p-value
Chi-squared Test of Independence 5.515 1 0.019