# Week 11: Regression recap and applications

# Key concepts

- Dependent and independent variable (missing reference)
- Slope (regression coefficient) and intercept (missing reference)
- Goodness of fit and outliers (missing reference)
- Residual variation and standard error of the estimate (missing reference)
- Coefficient of determination r-squared (missing reference)
- Standard error of the slope (missing reference)
- Assumptions of linear regression (missing reference)
- Errors Normally distributed
- Homoskedasticity
- Errors are independent of each other
- Independent and dependent variables must be interval variables
- Linear relationship between variables

- Ordinary least squares (OLS) (Allison, 1999)
- Partial slope (regression coefficients) (missing reference)
- Multiple coefficient of determination R-squared (missing reference)
- Adjusted R-squared (missing reference)
- Dummy variable regression (missing reference)
- Additional regression assumptions (missing reference)
- Model is specified correctly
- Low multi-collinearity

- Polynomial curve fitting (missing reference)

# Before class

Review the key concepts from previous two weeks. Prepare xxx.

# In class

- Concepts review section.
- Lecture on applications with real examples.
- “Fake with GPT”