This project examines just how different the media coverage is between two competing entities in the national Motorsports world - NASCAR and Indycar. Using agenda-setting theory, the study will compare the amount of news coverage, weekly, that was devoted to each organization.
Agenda-setting theory suggests that anything receiving more attention in the news media will be a more prominent figure in peoples minds.
Motorsports has given me the opportunity to combine my passion into an examination into the differences between two racing series I love very much and the disparity in coverage.
This study compares the weekly volume of online news coverage devoted to NASCAR and IndyCar using data collected through MediaCloud.
Does the media give more attention to NASCAR or IndyCar?
NASCAR will receive a greater average volume of weekly news coverage than IndyCar during the period analyzed.
The independent variable are the racing series, NASCAR or IndyCar.
The dependent variable is weekly news coverage volume. It was measured by using MediaCloud data for each week during the majority of the season.
The analysis uses MediaCloud data collected from January 4, 2026, through October 10, 2026. Weekly observations cover Sunday through Saturday. The two racing series are compared using matching weekly observations.
A paired-samples t-test will determine whether the average difference in weekly coverage between NASCAR and IndyCar is statistically more or less.
## [1] 40## # A tibble: 6 × 4
## week V2 V1 PairDifferences
## <date> <int> <int> <int>
## 1 2026-01-04 69 293 -224
## 2 2026-01-11 74 369 -295
## 3 2026-01-18 74 319 -245
## 4 2026-01-25 94 340 -246
## 5 2026-02-01 42 241 -199
## 6 2026-02-08 39 418 -379## week V2 V1 PairDifferences
## Min. :2026-01-04 Min. : 10.00 Min. :147.0 Min. :-534.0
## 1st Qu.:2026-03-13 1st Qu.: 41.75 1st Qu.:232.0 1st Qu.:-239.2
## Median :2026-05-20 Median : 66.00 Median :275.0 Median :-198.5
## Mean :2026-05-20 Mean : 80.47 Mean :287.7 Mean :-207.2
## 3rd Qu.:2026-07-27 3rd Qu.: 82.25 3rd Qu.:319.5 3rd Qu.:-161.8
## Max. :2026-10-04 Max. :298.00 Max. :832.0 Max. : -21.0## week V2 V1 PairDifferences
## 0 0 0 0| Weekly News Coverage Descriptive Statistics | |||||
| Racing Series | Number of Weeks | Mean Weekly Stories | Standard Deviation | Minimum | Maximum |
|---|---|---|---|---|---|
| IndyCar | 40 | 80.47 | 69.85 | 10.00 | 298.00 |
| NASCAR | 40 | 287.73 | 110.02 | 147.00 | 832.00 |
| Paired Difference Statistics | |
| Statistic | Value |
|---|---|
| Mean Paired Difference | −207.25 |
| Standard Deviation of Paired Differences | 88.90 |
##
## Shapiro-Wilk normality test
##
## data: mydata$PairDifferences
## W = 0.91326, p-value = 0.004756##
## Paired t-test
##
## data: mydata$V2 and mydata$V1
## t = -14.744, df = 39, p-value < 0.00000000000000022
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
## -235.6818 -178.8182
## sample estimates:
## mean difference
## -207.25| Paired-Samples T-Test Results | |||||||
| Mean Difference | t Statistic | p-value | Degrees of Freedom | Lower 95% CI | Upper 95% CI | method | alternative |
|---|---|---|---|---|---|---|---|
| −207.25 | −14.74 | 1.548 × 10−17 | 39.00 | −235.68 | −178.82 | Paired t-test | two.sided |
##
## Wilcoxon signed rank test with continuity correction
##
## data: mydata$V2 and mydata$V1
## V = 0, p-value = 0.00000003706
## alternative hypothesis: true location shift is not equal to 0The analysis examined 40 matching weekly observations of NASCAR and IndyCar news coverage from January 4, 2026, through October 10, 2026.
NASCAR received an average of 287.70 online news stories per week, while IndyCar received an average of 80.47 stories per week.
The mean paired difference was -207.25 stories, calculated by subtracting NASCAR coverage from IndyCar coverage. This indicates that NASCAR received just around 207 more online news stories per week than IndyCar.
The paired-samples t-test found a rather significant difference in weekly news coverage between the two racing series, t(39) = -14.74, p < .001.
The Shapiro-Wilk test was also rather significant (W = 0.913, p = .005). Because of this, the Wilcoxon signed-rank test was also conducted. The Wilcoxon test also found a significant difference between the two racing series (V = 0, p < .001).
Both tests indicate that NASCAR received significantly more weekly news coverage than IndyCar during the period analyzed.
The results support the hypothesis that NASCAR receives a greater average volume of weekly news coverage than IndyCar.
The findings show a clear definitive difference in the amount of news coverage that is devoted to the two organizations. NASCAR received much more media coverage than IndyCar.
# Import the NASCAR and IndyCar datasets
nascar_data <- read.csv(
"/Users/dawsonelliott/NASCAR/Indycar/NASCAR.csv"
) |>
mutate(week = as.Date(week))
indycar_data <- read.csv(
"/Users/dawsonelliott/NASCAR/Indycar/IndyCar.csv"
) |>
mutate(week = as.Date(week))
# Combine the datasets into long format
weekly_counts <- bind_rows(
nascar_data |>
mutate(topic = "NASCAR"),
indycar_data |>
mutate(topic = "IndyCar")
) |>
select(week, topic, stories) |>
arrange(week, topic)
# Reshape the data into wide format
weekly_counts_wide <- weekly_counts |>
pivot_wider(
names_from = topic,
values_from = stories
) |>
arrange(week)
# Prepare the paired observations
mydata <- weekly_counts_wide |>
rename(
V1 = NASCAR,
V2 = IndyCar
) |>
mutate(
PairDifferences = V2 - V1
)
# Calculate descriptive statistics
weekly_counts |>
group_by(topic) |>
summarise(
Weeks = n(),
Mean = mean(stories),
Standard_Deviation = sd(stories),
Minimum = min(stories),
Maximum = max(stories)
)
# Calculate paired difference statistics
mean(mydata$PairDifferences)
sd(mydata$PairDifferences)
# Test normality
shapiro.test(mydata$PairDifferences)
# Conduct paired-samples t-test
paired_test <- t.test(
mydata$V2,
mydata$V1,
paired = TRUE
)
paired_test
# Conduct supplemental Wilcoxon signed-rank test
wilcox.test(
mydata$V2,
mydata$V1,
paired = TRUE,
exact = FALSE
)