section9 - Statistics 104 – Spring 2011 Section #9 Topics...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Statistics 104 – Spring 2011 Section #9 Topics for Section Inference for Regression Omnibus F-test, t-test for a specific β Interpretation of coefficients Model selection Practice Problems An investigator was interested to see if one can predict how a state voted in the 2008 presidential election. She thinks the following attributes might be related to how a state voted. Y = McCain vote percentage, X 1 = % college graduates, X 2 = per capita Gross State Product (GSP), X 3 = % smokers, X 4 = % heavy drinkers The investigator collects data from all 50 states. She first looks at correlations between all variables. . corr mccain college gsp smokers drinkers (obs=50) | mccain~e college gsp smokers drinkers-------------+--------------------------------------------- mccainvote | 1.0000 college | -0.6113 1.0000 gsp | -0.3054 0.6236 1.0000 smokers | 0.3310 -0.6382 -0.2696 1.0000 drinkers | -0.5829 0.3845 0.2783 -0.3299 1.0000 a. Which of the X variables will have the most significant simple linear regression fit with McCain voting percentage? The investigator then looks at all the simple regressions, listed at the end of the handout. b. Which variable seems to be the strongest predictor of McCain voting percentage? Why? Of course, the investigator doesn't care about these individual regressions: she is interested in the “best predictive model” using all these variables combined. She starts with the full model below. . regress mccain smokers gsp college drinkers Source | SS df MS Number of obs = 50-------------+------------------------------ F( 4, 45) = 13.90 Model | .240159486 4 .060039871 Prob > F = 0.0000 Residual | .194426058 45 .004320579 R-squared = 0.5526-------------+------------------------------ Adj R-squared = 0.5128 Total | .434585544 49 .008869093 Root MSE = .06573------------------------------------------------------------------------------ mccainvote | Coef. Std. Err. t P>|t| [95% Conf. Interval]-------------+----------------------------------------------------------------...
View Full Document

This note was uploaded on 03/27/2012 for the course STATS 104 taught by Professor Michaelparzen during the Fall '11 term at Harvard.

Page1 / 4

section9 - Statistics 104 – Spring 2011 Section #9 Topics...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online