17/11/2024 12:53PM
Chapter 3- Multiple Regression Analysis:
Estimation solutions
why is multiple regression analysis more amenable to ceteris paribus analysis? -
Answers✓✓You can explicitly control for many other factors that simultaneously affect the
dependent variable
In a multiple regression how is u related to x1 and x2? - Answers✓✓The expected value is 0.
For any values of x1 and x2 in the population the average of the unobserved factors is equal to
0.
how are the OLS estimates chosen? - Answers✓✓To minimise the sum of squared residuals
What properties do OLS fitted values have which is extension from single variables? -
Answers✓✓1) sample average of residuals is 0
2) the sample covariance between each independent variable and the OLS residuals is 0
3) the estimated point is always on the OLS regression line
What is the Frisch Waugh theorem? - Answers✓✓the general algebraic result that provides
multiple regression analysis with its 'partialling out' interpretation
What is the explained sum of squares? - Answers✓✓The total sample variation of the fitted
values in a multiple regression model
if a independent variable is added what happens to the r2? - Answers✓✓it never decreases and
will usually increase by a little bit even if there is no effect. this makes it a poor tool for
deciding whether one variable or several variables should be added to the model.