Regression Analysis Guide

Walk me through a complete regression analysis for my dataset. Explain everything in plain language alongside the code.

What I am trying to predict: [DEPENDENT VARIABLE, e.g., sales revenue, customer churn, house price]
Factors I think influence it: [INDEPENDENT VARIABLES, e.g., advertising spend, season, customer age, location]
Dataset size: [NUMBER OF ROWS]
Tool: [PYTHON / R / EXCEL]

Provide a step-by-step guide:

1. Data preparation:
   - How to check if my data is ready for regression
   - Tests for multicollinearity, normality, and outliers
   - Code for each check with interpretation of results

2. Model selection:
   - Should I use linear, logistic, or another type of regression? Explain why based on my variables.
   - Code to build the model

3. Model evaluation:
   - R-squared: what it means in plain English for my case
   - P-values: which variables actually matter and which do not
   - Residual analysis: how to check if the model is valid
   - Code for all evaluation metrics

4. Interpretation:
   - Explain what each coefficient means in business terms (not just math)
   - Example: "For every $1,000 increase in ad spend, sales increase by approximately $X"

5. Common pitfalls:
   - What could make my results misleading
   - How to handle categorical variables
   - When to add interaction terms

6. Next steps: What to do if the model is not good enough