l52 - Models for Group Comparisons Summary Since we are...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Models for Group Comparisons – Summary – Page 1 Models for Group Comparisons – Summary Since we are estimating and comparing several models, it will be helpful to list several of them all in one place. This handout summarizes how to do group comparisons both by running separate models for each group and by using interaction terms. We won’t go through this handout separately, but it may help you to keep everything straight. I. Pooled (Constrained) Model. Blacks and whites are combined into a single analysis, hence the coefficient estimates are constrained to be the same for both racial groups, i.e. the intercepts and the effect of education and job experience are the same for both groups. . use "http://www.nd.edu/~rwilliam/stats2/statafiles/blwh.dta" . reg income educ jobexp Source | SS df MS Number of obs = 500 -------------+------------------------------ F( 2, 497) = 1103.96 Model | 32798.4018 2 16399.2009 Prob > F = 0.0000 Residual | 7382.84742 497 14.8548238 R-squared = 0.8163 -------------+------------------------------ Adj R-squared = 0.8155 Total | 40181.2493 499 80.5235456 Root MSE = 3.8542 ------------------------------------------------------------------------------ income | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- educ | 1.94512 .0436998 44.51 0.000 1.859261 2.03098 jobexp | .7082212 .0343672 20.61 0.000 .6406983 .775744 _cons | -7.382935 .8027781 -9.20 0.000 -8.960192 -5.805678 ------------------------------------------------------------------------------ Hence, SSE c = 7382.84680, R 2 c = .81626, N = 500, K = 2, DFE c = 497. II. Unconstrained Models: Separate Models for each group. Here, we estimate separate models, first for whites, then blacks. This makes it possible for the intercepts and slope coefficients to freely differ across populations. This is equivalent to Model IIIC. Whites: . reg income educ jobexp if !black Source | SS df MS Number of obs = 400 -------------+------------------------------ F( 2, 397) = 620.07 Model | 18361.9894 2 9180.99472 Prob > F = 0.0000 Residual | 5878.16991 397 14.8064733 R-squared = 0.7575 -------------+------------------------------ Adj R-squared = 0.7563 Total | 24240.1594 399 60.7522791
Background image of page 1

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

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/29/2012 for the course SOC 63993 taught by Professor Richardwilliams during the Spring '11 term at Notre Dame.

Page1 / 4

l52 - Models for Group Comparisons Summary Since we are...

This preview shows document pages 1 - 2. Sign up to view the full document.

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