STA 522 Project 1: Survey Sampling Analysis

Overview

This project analyzes U.S. college characteristics using stratified random sampling methodology. Two main research questions are addressed:

1. Problem 1: Estimating total undergraduate enrollment across U.S. institutions
2. Problem 2: Estimating the proportion of colleges offering undergraduate Statistics majors

Data Sources

• Most-Recent-Cohorts-Institution_05192025.csv - Institution-level data
• Most-Recent-Cohorts-Field-of-Study.csv - Program-level data
• College Scorecard: https://collegescorecard.ed.gov/

Methodology

• Sampling Design: Stratified random sampling (n=100)
• Stratification: Public/Private × 2-year/4-year (4 strata)
• Allocation: Proportional allocation
• Estimation: Design-based estimators with 95% confidence intervals

Files

• project1.Rmd - R Markdown source file with analysis and documentation
• project1.pdf - Compiled report

Rendering

To compile the R Markdown file to PDF:

Rscript -e "rmarkdown::render('project1.Rmd', output_format = 'pdf_document')"

Or simply:

Rscript -e "rmarkdown::render('project1.Rmd')"

Requirements

• R packages: dplyr, ggplot2, tidyr, gridExtra
• LaTeX distribution (for PDF output)

Author

Zhihao Chen, Zixiao Tan Date: 2025-10-14