Results & Discussion

The box plot and chart below show the paired samples t-test for a significance between the two issues. The t-test shows that the value of 0.00, a value of less than 0.05 meaning that there is significance in the data. The average of climate change coverage is 4.12 and energy is 7.8. The Wilcox Signed Rank Test is unnecessarty due to the Paired Samples t-test being significant.

## Loading required package: gt

## Loading required package: gtExtras

## Loading required package: broom

## Table has no assigned ID, using random ID 'ddsgqbkjaq' to apply `gt::opt_css()`
## Avoid this message by assigning an ID: `gt(id = '')` or `gt_theme_538(quiet = TRUE)`

## Table has no assigned ID, using random ID 'dzghcpjdja' to apply `gt::opt_css()`
## Avoid this message by assigning an ID: `gt(id = '')` or `gt_theme_538(quiet = TRUE)`

## Table has no assigned ID, using random ID 'diqgquclqm' to apply `gt::opt_css()`
## Avoid this message by assigning an ID: `gt(id = '')` or `gt_theme_538(quiet = TRUE)`

## Table has no assigned ID, using random ID 'lzepwdatsu' to apply `gt::opt_css()`
## Avoid this message by assigning an ID: `gt(id = '')` or `gt_theme_538(quiet = TRUE)`

count	mean	sd	min	max
Descriptive Statistics: Pair Differences
40.000	3.675	4.660	−8.000	14.000

statistic	p.value	method
Normality Test (Shapiro-Wilk)
0.9801	0.6923	Shapiro-Wilk normality test
If the P.VALUE is 0.05 or less, the number of pairs is fewer than 40, and the distribution of pair differences shows obvious non-normality or outliers, consider using the Wilcoxon Signed Rank Test results instead of the Paired-Samples t-Test results.

statistic	parameter	p.value	conf.low	conf.high	method
Paired-Samples t-Test
4.9881	39	0.0000	2.1848	5.1652	Paired t-test

V1_Mean	V2_Mean	V1_SD	V2_SD
Group Means and SDs (t-Test)
4.125	7.800	2.989	3.911

# ============================================================
#  Setup: Install and Load Required Packages
# ============================================================
if (!require("tidyverse")) install.packages("tidyverse")
if (!require("plotly")) install.packages("plotly")
if (!require("gt")) install.packages("gt")
if (!require("gtExtras")) install.packages("gtExtras")
if (!require("broom")) install.packages("broom")

library(tidyverse)
library(plotly)
library(gt)
library(gtExtras)
library(broom)

options(scipen = 999)

# ============================================================
#  Data Import
# ============================================================
# Reshape to wide form

mydata <- Weekly_counts %>%
  pivot_wider(names_from = Topic, values_from = Count)
names(mydata) <- make.names(names(mydata))

# Specify the two variables involved
mydata$V1 <- mydata$Climate.Change # <== Customize this
mydata$V2 <- mydata$Energy # <== Customize this

# ============================================================
#  Compute Pair Differences
# ============================================================
mydata$PairDifferences <- mydata$V2 - mydata$V1

# ============================================================
#  Interactive Histogram of Pair Differences
# ============================================================
hist_plot <- plot_ly(
  data = mydata,
  x = ~PairDifferences,
  type = "histogram",
  marker = list(color = "#1f78b4", line = list(color = "black", width = 1))
) %>%
  layout(
    title = "Distribution of Pair Differences",
    xaxis = list(title = "Pair Differences"),
    yaxis = list(title = "Count"),
    shapes = list(
      list(
        type = "line",
        x0 = mean(mydata$PairDifferences, na.rm = TRUE),
        x1 = mean(mydata$PairDifferences, na.rm = TRUE),
        y0 = 0,
        y1 = max(table(mydata$PairDifferences)),
        line = list(color = "red", dash = "dash")
      )
    )
  )

# ============================================================
#  Descriptive Statistics
# ============================================================
desc_stats <- mydata %>%
  summarise(
    count = n(),
    mean = mean(PairDifferences, na.rm = TRUE),
    sd = sd(PairDifferences, na.rm = TRUE),
    min = min(PairDifferences, na.rm = TRUE),
    max = max(PairDifferences, na.rm = TRUE)
  )

desc_table <- desc_stats %>%
  gt() %>%
  gt_theme_538() %>%
  tab_header(title = "Descriptive Statistics: Pair Differences") %>%
  fmt_number(columns = where(is.numeric), decimals = 3)

# ============================================================
#  Normality Test (Shapiro-Wilk)
# ============================================================
shapiro_res <- shapiro.test(mydata$PairDifferences)
shapiro_table <- tidy(shapiro_res) %>%
  select(statistic, p.value, method) %>%
  gt() %>%
  gt_theme_538() %>%
  tab_header(title = "Normality Test (Shapiro-Wilk)") %>%
  fmt_number(columns = c(statistic, p.value), decimals = 4) %>%
  tab_source_note(
    source_note = "If the P.VALUE is 0.05 or less, the number of pairs is fewer than 40, and the distribution of pair differences shows obvious non-normality or outliers, consider using the Wilcoxon Signed Rank Test results instead of the Paired-Samples t-Test results."
  )

# ============================================================
#  Reshape Data for Repeated-Measures Plot
# ============================================================
df_long <- mydata %>%
  pivot_longer(cols = c(V1, V2),
               names_to = "Measure",
               values_to = "Value")

# ============================================================
#  Repeated-Measures Boxplot (Interactive, with Means)
# ============================================================
group_means <- df_long %>%
  group_by(Measure) %>%
  summarise(mean_value = mean(Value), .groups = "drop")

boxplot_measures <- plot_ly() %>%
  add_trace(
    data = df_long,
    x = ~Measure, y = ~Value,
    type = "box",
    boxpoints = "outliers",   
    marker = list(color = "red", size = 4),
    line = list(color = "black"),
    fillcolor = "royalblue",
    name = ""
  ) %>%
  add_trace(
    data = group_means,
    x = ~Measure, y = ~mean_value,
    type = "scatter", mode = "markers",
    marker = list(
      symbol = "diamond", size = 9,
      color = "black", line = list(color = "white", width = 1)
    ),
    text = ~paste0("Mean = ", round(mean_value, 2)),
    hoverinfo = "text",
    name = "Group Mean"
  ) %>%
  layout(
    title = "Boxplot of Repeated Measures (V1 vs V2) with Means",
    xaxis = list(title = "Measure"),
    yaxis = list(title = "Value"),
    showlegend = FALSE
  )

# ============================================================
#  Parametric Test (Paired-Samples t-Test)
# ============================================================
t_res <- t.test(mydata$V2, mydata$V1, paired = TRUE)
t_table <- tidy(t_res) %>%
  select(statistic, parameter, p.value, conf.low, conf.high, method) %>%
  gt() %>%
  gt_theme_538() %>%
  tab_header(title = "Paired-Samples t-Test") %>%
  fmt_number(columns = c(statistic, p.value, conf.low, conf.high), decimals = 4)

t_summary <- mydata %>%
  select(V1, V2) %>%
  summarise_all(list(Mean = mean, SD = sd)) %>%
  gt() %>%
  gt_theme_538() %>%
  tab_header(title = "Group Means and SDs (t-Test)") %>%
  fmt_number(columns = everything(), decimals = 3)

# ============================================================
#  Results Summary (in specified order)
# ============================================================
hist_plot
desc_table
shapiro_table
boxplot_measures
t_table
t_summary

Research Proposal Summary

Results & Discussion