World Happiness Report 2024: Statistical Analysis

This project applies fundamental hypothesis testing techniques—including T-test, Z-test, ANOVA, and Chi-Square—to analyze the World Happiness Report (2005-2023 data). The analysis is implemented in Python using Pandas, SciPy, and Statsmodels within Jupyter Notebooks.

This project utilizes uv for high-speed environment and package management.

Technologies Used

• Language: Python 3.12+
• Libraries: Pandas, SciPy, Statsmodels, Matplotlib/Seaborn
• Environment Manager: uv

Data Access

To comply with data redistribution policies and repository best practices, the dataset is not included in this repository.

1. Download: Obtain the World-happiness-report-updated_2024.csv file from Kaggle:
   • World Happiness Report 2024 (Kaggle)
2. Setup: Create a directory named data/raw in the project root and place the CSV file inside it.

Installation and Usage

This project uses uv for dependency management.

1. Clone the repository:

   git clone [https://github.com/yourusername/your-repo-name.git](https://github.com/yourusername/your-repo-name.git)
   cd your-repo-name

2. Sync the environment:

   uv sync

3. Run the notebooks:

   uv run jupyter lab

Project Structure

• notebooks/: Contains Jupyter Notebooks used for data cleaning and statistical analysis.
• data/raw/: Target directory for the raw CSV dataset (git-ignored).
• pyproject.toml / uv.lock: Dependency management files.
• LICENSE: MIT License.

Statistical Findings

The following results are based on the analysis of the 2023 data subset.

1. Independent Samples T-Test

• Objective: Compare happiness scores between selected G7 nations and major Asian powers.
• Result: Null hypothesis rejected ($p < 0.05$).
• Conclusion: There is a statistically significant difference in happiness scores between the two groups.

2. One-Sample Z-Test

• Objective: Determine if the global average happiness score in 2023 differs from a hypothesized mean of 6.0.
• Result: Null hypothesis rejected ($p < 0.05$).
• Conclusion: The global average happiness score is significantly different from 6.0.

3. Analysis of Variance (ANOVA)

• Objective: Compare mean happiness scores across three constructed regions: Europe, North America, and Asia.
• Result: Null hypothesis rejected ($p < 0.05$).
• Conclusion: There is a statistically significant difference in mean happiness scores between at least two of the regions analyzed.

4. Chi-Square Test of Independence

• Objective: Assess the relationship between a country's economic status (categorized as Rich/Poor) and its happiness level (categorized as Happy/Unhappy).
• Result: Null hypothesis rejected ($p < 0.05$).
• Conclusion: There is a significant association between economic status and happiness classification.

License

This project is licensed under the MIT License.