Agenda-Setting Analysis

Rationale

Agenda-setting theory suggests that the media can influence which issues people consider important. First-level agenda-setting focuses on the salience of issues, or the extent to which an issue becomes important on the public’s agenda. In other words, the theory suggests that the amount of attention the media gives to an issue can influence how important audiences perceive that issue to be.

This analysis examines immigration as a possible example of first-level agenda-setting. The data come from 600 frequent Fox News or CNN viewers. The respondents were asked to identify the most important problem facing the United States at the time of the survey. The variable Immigration indicates whether the respondent identified immigration as the most important problem.

The information provided for this study indicates that Fox News devoted consistently more coverage to immigration than CNN during the months leading up to the survey. If media coverage contributes to the salience of an issue among audiences, then immigration may be more likely to be identified as the most important problem by people who primarily watch Fox News.

Hypothesis

The hypothesis is that the proportion of viewers who identify immigration as the most important problem facing the United States will differ depending on their preferred news network.

More specifically, viewers who prefer Fox News are expected to identify immigration as the top issue at a higher rate than viewers who prefer CNN.

Variables & Method

The independent variable (IV) is PreferredNetwork, which identifies whether a respondent usually watches Fox News or CNN.

The dependent variable (DV) is Immigration, which identifies whether immigration was or was not the issue the respondent named as the most important problem facing the United States. Respondents coded as 1 Top issue identified immigration as the most important problem, while respondents coded as 2 Not top issue identified another issue as the most important problem.

A chi-square test of independence was used because both variables are categorical. The test examines whether there is a statistically significant association between a respondent’s preferred news network and whether that respondent identifies immigration as the top issue.

The analysis first cross-tabulated the two variables to compare the percentages of CNN and Fox viewers who identified immigration as the top issue. A stacked column chart was also created to visually display the distribution of responses. Finally, a chi-square test of independence was conducted using R to determine whether the relationship between preferred network and identifying immigration as the top issue was statistically significant.

Crosstabulation

Crosstabulation of Immigration by Preferred Network
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%)

Distribution of Responses

Results & Discussion

The crosstabulation shows a difference between CNN and Fox viewers in the percentage who identified immigration as the most important problem facing the United States. Among CNN viewers, 35 respondents, or 11.7%, identified immigration as the top issue, while 265 respondents, or 88.3%, identified another issue. Among Fox viewers, 115 respondents, or 38.3%, identified immigration as the top issue, while 185 respondents, or 61.7%, identified another issue.

Chi-squared Test Results
Test of Independence between Immigration and Preferred Network
Test	Chi-squared Statistic	Degrees of Freedom	p-value
Chi-squared Test of Independence	55.476	1	0.000

The chi-square test of independence found a statistically significant association between preferred news network and whether respondents identified immigration as the top issue, χ²(1) = 55.476, p < .001.

The results are consistent with the hypothesis. Immigration was identified as the top issue by a larger proportion of Fox viewers than CNN viewers. Specifically, 38.3% of Fox viewers identified immigration as the top issue compared with 11.7% of CNN viewers.

These findings are also consistent with the first-level agenda-setting perspective described in the rationale. Fox News had devoted more coverage to immigration than CNN during the months leading up to the survey, and Fox viewers were more likely to identify immigration as the most important problem. This pattern is consistent with the idea that differences in media attention can be associated with differences in the salience of an issue among audiences.

However, the results should not be interpreted as proof that watching Fox News caused respondents to consider immigration more important. The data show an association between preferred network and identifying immigration as the top issue, but a chi-square test by itself cannot establish causation. Other differences between people who prefer CNN and people who prefer Fox News could also contribute to the relationship.

Overall, the analysis found a statistically significant relationship between preferred news network and whether immigration was identified as the top issue. The results are consistent with the expectations of first-level agenda-setting theory, while the observational nature of the data means that the findings should be interpreted as an association rather than proof of a causal media effect.

Code

The following code was used to conduct the analysis in R.

# Install packages if needed
if (!require("tidyverse")) install.packages("tidyverse")
if (!require("gmodels")) install.packages("gmodels")
if (!require("gt")) install.packages("gt")

# Load packages
library(tidyverse)
library(gmodels)
library(gt)

# Read the data
mydata <- read.csv("https://drkblake.com/wp-content/uploads/2023/09/TopIssue.csv")

# Define variables
mydata$DV <- mydata$Immigration
mydata$IV <- mydata$PreferredNetwork

# Create stacked bar graph
graph <- ggplot(mydata, aes(x = IV, fill = DV)) +
  geom_bar(colour = "black") +
  scale_fill_brewer(palette = "Paired") +
  labs(
    title = "Immigration as a Top Issue by Preferred News Network",
    x = "Preferred News Network",
    y = "Number of Viewers",
    fill = "Immigration"
  )

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

# Format crosstabulation
crosstab_table <- crosstab %>%
  gt(rowname_col = "DV") %>%
  tab_header(
    title = "Crosstabulation of Immigration by Preferred Network",
    subtitle = "Counts and (Column Percentages)"
  ) %>%
  cols_label(
    DV = "Immigration"
  )

# Run chi-square test
options(scipen = 999)
chitestresults <- chisq.test(mydata$DV, mydata$IV)

# Create chi-square results table
chitest_summary <- tibble(
  Test = "Chi-squared Test of Independence",
  Chi_sq = as.numeric(chitestresults$statistic),
  df = as.numeric(chitestresults$parameter),
  p = chitestresults$p.value
)

# Format chi-square results
chitest_table <- chitest_summary %>%
  gt() %>%
  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 Immigration and Preferred Network"
  ) %>%
  cols_label(
    Test = "Test",
    Chi_sq = "Chi-squared Statistic",
    df = "Degrees of Freedom",
    p = "p-value"
  )