This project aims to develop and compare binomial logit and probit models to predict the likelihood of satisfaction based on the below variables:
- Income: Average monthly income per person in the household.
- Expenses: Average monthly expenses per person in the household.
- Sex: Gender of the head of the household,
- Cars: Number of cars in the household.
- Satisfaction: Satisfaction with the financial situation.
The dataset used in this project is fictional.
The project directory contains the following files:
household_dataset.csv: Contains the raw data used for analysis.logit_probit_code.Rmd: R Markdown file containing the R code for data analysis.logit_probit_code.html: HTML output of the R Markdown file, showcasing the analysis results.
To reproduce the analysis:
- Ensure you have R installed on your system.
- Clone this repository to your local machine.
- Open the logit_probit_code.Rmd file in RStudio or any compatible IDE.
- Run the R code chunks in the file to perform the analysis.
- The output report (logit_probit_code.html) can be generated by knit button.
The analysis includes descriptive statistics, conditional plot visualizations, model estimation (using both logit and probit models), goodness-of-fit comparison, prediction quality assessment, ROC curve analysis and interpretation of model coefficients.
This project is licensed under the MIT License - see the LICENSE file for details.