# ------------------------------
# Setup: Install and load packages
# ------------------------------
if (!require("tidyverse")) install.packages("tidyverse") # Data wrangling & plotting
## Loading required package: tidyverse
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.2.1 ✔ readr 2.2.0
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.3 ✔ tibble 3.3.1
## ✔ lubridate 1.9.5 ✔ tidyr 1.3.2
## ✔ purrr 1.2.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
if (!require("gmodels")) install.packages("gmodels") # Crosstabs
## Loading required package: gmodels
if (!require("gt")) install.packages("gt") # Table formatting
## Loading required package: gt
library(tidyverse)
library(gmodels)
library(gt)
# ------------------------------
# Load the data
# ------------------------------
# Replace "YOURFILENAME.csv" with your dataset name
mydata <- read.csv("Topissue.csv") #Edit
# ------------------------------
# Define Dependent (DV) and Independent (IV) variables
# ------------------------------
# Replace YOURDVNAME and YOURIVNAME with actual column names in your data
mydata$DV <- mydata$Immigration #Edit
mydata$IV <- mydata$PreferredNetwork #Edit
# ------------------------------
# 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 = "Distribution of DV by IV",
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 = "Crosstabulation of DV by IV",
subtitle = "Counts and (Column Percentages)"
) %>%
cols_label(
DV = "Dependent Variable"
)
# Show the polished crosstab table
crosstab_table
| Crosstabulation of DV by IV | ||
| Counts and (Column Percentages) | ||
| CNN | Fox | |
|---|---|---|
| 1 Top issue | 35 (11.7%) | 115 (38.3%) |
| 2 Not top issue | 265 (88.3%) | 185 (61.7%) |
# ------------------------------
# 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 | 55.476 | 1 | 0.000 |
Week 4
IV = Network
DV = Issues