Question: Dummy variable for one observation. Suppose the data set consists of n observations, (y n , X n ) and an additional observation, (y s
Dummy variable for one observation. Suppose the data set consists of n observations, (yn, Xn) and an additional observation, (ys, x's). The full data set contains a dummy variable, d, that equals zero save for one (the last) observation. Then, the full data set is
![0 (Neue des) = [X] and you = [] n (Xn,s,dn,s)](https://dsd5zvtm8ll6.cloudfront.net/si.question.images/images/question_images/1651/0/4/6/3446268f7c871f071651046343843.jpg)
It is claimed in the text that in the full regression of yn,s on (Xn,s, dn,s) using all n+1 observations, the slopes on Xn,s, bn,s, and their estimated standard errors will be the same as those on Xn, bn in the short regression of yn on Xn, and the sum of squared residuals in the full regression will be the same as the sum of squared residuals in the short regression. That is, the last observation will be ignored. However, the R2 in the full regression will not be the same as the R2 in the short regression. Prove these results.
0 (Neue des) = [X] and you = [] n (Xn,s,dn,s)
Step by Step Solution
3.47 Rating (154 Votes )
There are 3 Steps involved in it
The proof is as follow i We have 1 and 2 means in which we have It is known that if using the substi... View full answer
Get step-by-step solutions from verified subject matter experts
