Suppose a researcher has student-level data for students at a particular college. The gpa variable is student GPA. The variable hrs_sleep is average number of hours of sleep per night for each student. The variable broccoli is the average number of broccoli crowns the student eats per week. The variable male is a dummy variable for whether the student is male (=1) or female (=0). Finally, the remaining variables are dummy variables representing which geographic part of the U.S. the student is from. The researcher runs the two regressions below, and the results are as follow:

Suppose that you forgot to include the dummy midwest in model (2). What would be the interpretation of the coefficient estimate on northeast under this new specification? Explain.

(1) Gpa 0.114*** (0.00294) (2) Gpa 0.114*** (0.00294) Hrs sleep WWWWAADW Broccoli 0.0120*** (0.000598) 0.0120*** (0.000598) Male -0.250*** (0.0132) -0.250*** (0.0132) Midwest 0.0502*** 0.0017 (0.0197) (0.0176) Northeast 0.100*** (0.0183) 0.0515** (0.0204) West 0.0485*** (0.0185) South -0.0485*** (0.0185) cons N adj. R2 0.492*** 0.541*** (0.0428) (0.0434) 4733 4733 0.318 0.318 *p