Video Game Sales Data Analysis Project (MAT234)

This repository contains my final project for the MAT234 course, which focuses on statistical analysis of video game sales data from 1997-2019. The project includes hypothesis testing, confidence interval construction, and regression analysis to explore trends and relationships in sales data.

Overview

This project analyzes video game sales data using statistical techniques. The dataset includes:

• Game titles
• Platforms (e.g., Xbox, PlayStation)
• Genres (e.g., Racing, Role-Playing, Platform)
• Regional sales (North America, Europe, Japan, and Others)
• Global sales figures

Objectives

1. Random sampling of video games by genre and region.
2. Calculation of sample and population statistics (mean, variance, standard deviation).
3. Construction of confidence intervals.
4. Hypothesis testing to evaluate sample mean estimations.
5. Regression analysis to identify relationships between sales in different regions.

Methodology

Steps Performed

1. Random Sampling:

   • Used Excel's RAND function to sample games from specific genres and the global dataset.

2. Statistical Analysis:

   • Computed sample and population statistics (mean, variance, standard deviation).
   • Constructed 95% and 97% confidence intervals.

3. Hypothesis Testing:

   • Formulated null and alternative hypotheses.
   • Calculated test statistics, critical values, and p-values.
   • Interpreted results to accept or reject hypotheses.

4. Regression Analysis:

   • Analyzed relationships between sales in different regions (e.g., North America vs. Europe).
   • Used scatter plots, regression lines, and r-values to determine trends.

Files

Included in This Repository

• MAT234_Final.xlsx: Contains all computations, visualizations, and analyses for the project. Key sheets include:
  • Global Video Game Sales
  • Platform Video Games
  • Racing Video Games
  • Role Playing Video Games

Results

• Comprehensive statistical analysis for global video game sales and specific genres.
• Insights into sales trends by region and genre.
• Regression analysis reveals significant relationships between regional sales data.

Tools Used

• Microsoft Excel: Data manipulation, computations, and visualizations.
• Statistical formulas: Used for hypothesis testing and confidence intervals.

License

This project is licensed under the GNU General Public License v3.0. This ensures the work remains open-source and is primarily intended for educational use. Commercial use is restricted unless derivative works are also open-source under the same terms.

Acknowledgments

This project was completed as part of the MAT234 course.