Chess Statistical Analysis
Analyzed a Kaggle chess dataset in R to investigate relationships between player ratings, time controls, and game length using statistical hypothesis testing.
Overview
A statistical analysis of chess games using R, completed for Purdue University’s STAT 355 course.
The project investigates how player ratings and time controls relate to the number of moves played in a chess game.
Research Questions
- Do different rating groups play similar numbers of moves in 10-minute games?
- Does the number of moves per game increase with player rating?
- Do 10+0 and 5+5 games have similar numbers of moves?
Methods
- Exploratory Data Analysis: Examined rating distributions and game lengths using histograms, descriptive statistics, and Q-Q plots.
- Analysis of Variance (ANOVA): Investigated differences across player rating groups.
- Correlation Testing: Examined the relationship between player rating and game length.
- Two-Sample t-Test: Compared game lengths between 10+0 and 5+5 time controls.
Source
The repository contains the R analysis script, Kaggle dataset, and complete statistical report.