day10pr

# day10pr - 1 PADP 8120 Data Analysis and Sta¡s¡cal...

This preview shows pages 1–4. Sign up to view the full content.

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

View Full Document

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: 4/6/11 1 PADP 8120: Data Analysis and Sta¡s¡cal Modeling Regression Diagnos,cs PRACTICE Spring 2011 Angela Fer¡g, Ph.D. Graphing residuals reg faminc educhd predict r, resid sca¢er r educhd 4/6/11 2 Detec¡ng Non-Linearity Graphically drop if faminc>200000 twoway (scaFer faminc educhd) (l¢t faminc educhd) (lowess faminc educhd) Solu¡on • Polynomial terms: gen educsq=educhd*educhd reg faminc educhd educsq predict r2, residual scaFer r2 educhd • Log transforma¡on gen lvar1=log(var1) reg dvar lvar1 4/6/11 3 Detec¡ng Heteroskedas¡city Graphically . reg lfaminc educhd educsq agehd agesq black hisp femalehd marriedhd nkids hstat fstamps tanf Source | SS df MS Number of obs = 7467-------------+------------------------------ F( 12, 7454) = 492.51 Model | 3141.67977 12 261.806648 Prob > F = 0.0000 Residual | 3962.34271 7454 .531572674 R-squared = 0.4422-------------+------------------------------ Adj R-squared = 0.4413 Total | 7104.02248 7466 .951516539 Root MSE = .72909------------------------------------------------------------------------------ lfaminc | Coef. Std. Err. t P>|t| [95% Conf. Interval]-------------+---------------------------------------------------------------- educhd | .0434182 .0163782 2.65 0.008 .0113123 .0755242 educsq | .0017264 .0006707 2.57 0.010 .0004116 .0030411 agehd | .0654106 .0027722 23.60 0.000 .0599764 .0708449 agesq | -.0006251 .0000272 -22.98 0.000 -.0006784 -.0005718 black | -.18598 .019845 -9.37 0.000 -.2248818 -.1470782 hisp | -.0052076 .0345632 -0.15 0.880 -.0729613 .0625461 femalehd | -.1658746 .0242433 -6.84 0.000 -.2133983 -.118351 marriedhd | .5492764 .0235177 23.36 0.000 .5031751 .5953777 nkids | .0674659 .0082506 8.18 0.000 .0512923 .0836394 hstat | -.1007932 .0086367 -11.67 0.000 -.1177235 -.0838628 fstamps | -.5435868 .0286101 -19.00 0.000 -.5996706 -.487503 tanf | -.2624728 .0686072 -3.83 0.000 -.3969623 -.1279834 _cons | 8.324983 .1229927 67.69 0.000 8.083883 8.566084------------------------------------------------------------------------------ rvfplot, yline(0) (This plots the residuals versus F¢ed (predicted) values. If the spread varies by the x-axis, then there is heteroskedas¡city.) RV£plot 4/6/11...
View Full Document

## This note was uploaded on 01/18/2012 for the course PADP 8120 taught by Professor Fertig during the Summer '11 term at UGA.

### Page1 / 7

day10pr - 1 PADP 8120 Data Analysis and Sta¡s¡cal...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online