Today we covered multiple linear regression. Multiple linear regression is just the same process as single linear regression but we are adding more predictors. The thing about interpreting the coefficients is that you now have to hold all other predictors constant to see how much the response variable changes with a one unit increase in the chosen predictor.
We learned that R-squared is called the coefficient of determination. R-squared does not change when we add another predictor. The new Adjusted R-squared that we learned about is basically R^2 but it gets penalized for more predictor variables.
Another thing we talked about was the F-test. The biggest thing I learned was about the degrees of freedom and what each one does. The degrees of freedom 1 represents the spread left and right and the degrees of freedom 2 represents the spread up and down. If we had an increasing df 1 and decreasing df 2 we would see a shift right and down.
To finish we talked about indicator variables which I have learned as dummy variables. They are not hard, all it is is giving a number value to categorical variables. This way we can use them in our multiple linear regression.