I Expanded this and Created an additional model in pt 2

This assignment analyzes what factors predict whether a home in the Ames dataset falls into the high-price category. Using dummy variables, the Linear Probability Model, and logistic regression, I examine how features such as living area, quality, garage capacity, central air, and neighborhood influence the probability of a home being high price. The models are compared, interpreted, and tested using a 75/25 train–test split to evaluate predictive performance and real-world applicability.

This assignment explores **housing price prediction and model interpretability** using the **Ames Housing Dataset** in R. The objective is to build, evaluate, and interpret a multiple linear regression model that predicts residential property sale prices based on structural, quality, and location-related variables. Through a series of analytical questions, the project covers the full regression workflow — from **data loading and preprocessing**, to **model building**, **assumption testing**, **validation**, and **prediction uncertainty**. The analysis applies fundamental statistical theory (BLUE: Best Linear Unbiased Estimator) while integrating practical, real-world reasoning to connect quantitative results with housing market behavior. Each section mirrors an applied data analytics process: - **A–B:** Prepare and fit a predictive model. - **C–D:** Identify key factors and assess statistical significance. - **E–G:** Evaluate model fit, test predictive accuracy, and interpret confidence and prediction intervals. The ultimate goal is to understand **how and why regression works**, not just how to run it — developing intuition for interpreting coefficients, evaluating significance, diagnosing assumptions, and communicating results meaningfully. This assignment demonstrates how data analytics and AI-assisted exploration can enhance evidence-based decision-making in **real estate valuation** and **economic modeling**.