library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.6
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.1     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.2.0     
## ── 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
usairports <- read.csv("usairports.csv")

dim(usairports)
## [1] 19615    14

Introduction

Research Question: Is airport ownership associated with whether an airport is open to public use in the United States?

This study uses the US Airports dataset, which contains information on 19,615 airports under Federal Aviation Administration (FAA) oversight across all U.S. regions. Each observation represents an individual airport, and the dataset includes variables related to location, ownership, operational use, and administrative classification. The key variables used in this analysis are ownership (public vs. private ownership) and use (public vs. private facility use), both of which are categorical variables.

The dataset was sourced from the FAA 5010 Airport Master Record, which provides authoritative and regularly updated information on airport facilities in the United States. This topic was chosen because airport accessibility plays a critical role in transportation infrastructure, economic development, and public safety. Understanding whether ownership type influences public accessibility helps reveal how institutional control relates to infrastructure availability.

Data Analysis

Before conducting the statistical analysis, the dataset was cleaned and prepared to focus on relevant variables. The analysis first selected the variables ownership and use, which directly relate to the research question. Observations with missing or ambiguous values were removed to ensure valid category counts. The categorical variables were then converted into factors to make them suitable for statistical testing. These steps ensure that the dataset meets the assumptions required for a Chi-Square Test of Independence

airport_clean <- usairports %>%
  select(ownership, use)
airport_clean <- airport_clean %>%
  drop_na()
airport_clean <- airport_clean %>%
  mutate(
    ownership = as.factor(ownership),
    use = as.factor(use)
  )
airport_table <- table(airport_clean$ownership, airport_clean$use)
airport_table
##     
##         PR    PU
##   CG     7     0
##   MA    86    10
##   MN    68     1
##   MR   124     9
##   PR 13494   949
##   PU   740  4127

Null Hypothesis (H₀): Airport ownership and airport use are independent. (There is no association between ownership type and public use.)

Alternative Hypothesis (H₁): Airport ownership and airport use are not independent. (There is an association between ownership type and public use.)

chisq.test(airport_table)$expected
## Warning in chisq.test(airport_table): Chi-squared approximation may be
## incorrect
##     
##                PR          PU
##   CG     5.181392    1.818608
##   MA    71.059087   24.940913
##   MN    51.073719   17.926281
##   MR    98.446444   34.553556
##   PR 10690.691665 3752.308335
##   PU  3602.547693 1264.452307
chi_result <- chisq.test(airport_table)
## Warning in chisq.test(airport_table): Chi-squared approximation may be
## incorrect
chi_result
## 
##  Pearson's Chi-squared test
## 
## data:  airport_table
## X-squared = 11646, df = 5, p-value < 2.2e-16
barplot(
  airport_table,
  beside = TRUE,
  legend = TRUE,
  xlab = "Airport Use",
  ylab = "Number of Airports",
  main = "Airport Ownership vs Public Use"
)

Interpretation of Results

The Chi-Square Test of Independence shows a statistically significant association between airport ownership and airport use (p-value < 0.05). Therefore, the null hypothesis is rejected. This result indicates that airport ownership type is not independent of whether an airport is open to public use. Publicly owned airports are substantially more likely to be open to the public, while privately owned airports are more likely to restrict access. This finding highlights how institutional ownership structures influence infrastructure accessibility in the U.S. aviation system.

Conclusion and Future Directions

This analysis examined whether airport ownership is associated with public access to airports in the United States. Using a Chi-Square Test of Independence on FAA airport data, the results showed a statistically significant relationship between ownership type and airport use. Publicly owned airports were far more likely to be open to public use, while privately owned airports were more likely to restrict access. These findings suggest that institutional ownership plays an important role in determining infrastructure accessibility, particularly in transportation systems that serve both economic and public safety functions.

The results of this study have practical implications for policymakers and transportation planners, as expanding public access to aviation infrastructure may depend on ownership structures. Future research could incorporate additional variables such as region, state, or certification type to explore geographic or regulatory patterns in airport accessibility. Further analysis could also examine how airport size, certification class, or proximity to urban centers influences public use, providing a more comprehensive understanding of how aviation infrastructure is distributed across the United States.