Exploring Data Generation, Visualisation, and Statistical Testing in R.
This project demonstrates how to perform statistical hypothesis testing and distribution fitting in R using simulated experimental datasets.
It focuses on:
- Generating synthetic datasets for two populations (mice and rats) with treatment effects.
- Visualising data distributions using density plots and boxplots.
- Checking normality assumptions with QQ plots and Shapiro-Wilk tests.
- Performing paired t-tests and non-parametric tests to evaluate treatment effects.
- Fitting and comparing multiple statistical distributions (Weibull, Lognormal, Gamma) to data.
The project serves as a hands-on example for researchers, students, or data enthusiasts interested in understanding statistical testing workflows in R.
Density Plots
Compare the "before" and "after" treatment distributions for mice and rats
Boxplots
Visual summary of weight changes due to treatment
Distribution Fitting
Comparison of fitted Weibull, Lognormal, and Gamma distributions for rats
- Ensure you have R installed (version 4.0+ recommended) and install the required packages:
install.packages(c("tidyverse", "fitdistrplus", "ggplot2"))- Clone this repository:
git clone https://github.com/YOUR_USERNAME/statistical-hypothesis-r.git
cd statistical-hypothesis-r
- Run the R script:
source("statistical_hypothesis_testing.R")
- Experiment!
Contributions, suggestions, and improvements are welcome! Feel free to open an issue or submit a pull request.
Arslonbek Ishanov - First-Class Data Science Graduate & AI/ML Enthusiast.
This project is licensed under the MIT License - see the LICENSE file for details.
Read the detailed report explaining the underlying theory, methodology, and results here.