Example 7.1: Hourly Wage Equation Average wage for women

Transcription

1 1 Stata Textbook Examples Introductory Econometrics: A Modern Approach by Jeffrey M. Wooldridge (1st & 2nd eds.) Chapter 7 - Multiple Regression Analysis with Qualitative Information: Binary (or Dummy) Variables Example 7.1: Hourly Wage Equation use reg wage female educ exper tenure F( 4, 521) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE = wage Coef. Std. Err. t P> t [95% Conf. Interval] female educ exper tenure _cons reg wage female F( 1, 524) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE = wage Coef. Std. Err. t P> t [95% Conf. Interval] female _cons Average wage for women lincom female+_cons ( 1) female + _cons = 0.0 wage Coef. Std. Err. t P> t [95% Conf. Interval] (1) Example 7.2: Effects of Computer Ownership on College GPA use reg colgpa PC hsgpa ACT Source SS df MS Number of obs = F( 3, 137) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE =.33253

2 2 colgpa Coef. Std. Err. t P> t [95% Conf. Interval] PC hsgpa ACT _cons reg colgpa PC Source SS df MS Number of obs = F( 1, 139) = 7.31 Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE = colgpa Coef. Std. Err. t P> t [95% Conf. Interval] PC _cons Example 7.3: Effects of Training Grants on Hours of Training in 1988 use reg hrsemp grant lsales lemploy if year==1988 Source SS df MS Number of obs = F( 3, 101) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE = hrsemp Coef. Std. Err. t P> t [95% Conf. Interval] grant lsales lemploy _cons Example 7.4: Housing Price Regression use reg lprice llotsize lsqrft bdrms colonial Source SS df MS Number of obs = F( 4, 83) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE = lprice Coef. Std. Err. t P> t [95% Conf. Interval] llotsize lsqrft bdrms colonial _cons

3 3 Example 7.5: Log Hourly Wage Equation use reg lwage female educ exper expersq tenure tenursq F( 6, 519) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE = female educ exper expersq tenure tenursq _cons Difference between woman's and man's wage di exp(_b[female]*1) Example 7.6: Log Hourly Wage Equation use gen male = (!female) gen single = (~married) gen marrmale = (married & ~female) gen marrfem = (married & female) gen singfem = (female & ~married) gen singmale = (~female & ~married) reg lwage marrmale marrfem singfem educ exper expersq tenure tenursq F( 8, 517) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE = marrmale marrfem singfem educ exper expersq tenure tenursq

4 4 _cons Difference in lwage between married and single women lincom singfem-marrfem (1) reg lwage marrmale singmale singfem educ exper expersq tenure tenursq F( 8, 517) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE = marrmale singmale singfem educ exper expersq tenure tenursq _cons Example 7.7: Effects of Physical Attractiveness on Wage Dataset is not available Example 7.8: Effects of Law School Rankings on Starting Salaries use gen r61_100 = (rank>60 & rank<101) reg lsalary top10 r11_25 r26_40 r41_60 r61_100 LSAT GPA llibvol lcost Source SS df MS Number of obs = F( 9, 126) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE = top r11_ r26_ r41_ r61_ LSAT GPA llibvol lcost

5 5 _cons Difference in starting wage between top 10 below 100 school di exp(_[top10]*1) reg lsalary rank LSAT GPA llibvol lcost Source SS df MS Number of obs = F( 5, 130) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE = rank LSAT GPA llibvol lcost _cons Example 7.9: Effects of Computer Usage on Wages Dataset is not available Example 7.10: Log Hourly Wage Equation use gen femed = female*educ reg lwage female educ femed exper expersq tenure tenursq F( 7, 518) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE =.4001 female educ femed exper expersq tenure tenursq _cons reg lwage female educ exper expersq tenure tenursq F( 6, 519) = Model Prob > F = Residual R-squared = Adj R-squared =

6 6 Total Root MSE = female educ exper expersq tenure tenursq _cons Example 7.11: Effects of Race on Baseball Player Salaries use reg lsalary years gamesyr bavg hrunsyr rbisyr runsyr fldperc allstar black hispan blckpb hispph Source SS df MS Number of obs = F( 12, 317) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE = years gamesyr bavg hrunsyr rbisyr runsyr fldperc allstar black hispan blckpb hispph _cons Difference in lwage between black and white in cities with 10% of blacks lincom _b[black]+_b[blckpb]*10 ( 1) black blckpb = 0.0 (1) Difference in lwage between black and white in cities with 20% of blacks lincom _b[black]+_b[blckpb]*20 ( 1) black blckpb = 0.0 (1) City percentage of hispanic people when wages of hispanic and whites are equal

7 7 di _b[hispan]*-1/_b[hispph] Example 7.12: A Linear Probability Model of Arrests use gen arr86=(~narr86) reg arr86 pcnv avgsen tottime ptime86 qemp86 Source SS df MS Number of obs = F( 5, 2719) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE = pcnv avgsen tottime ptime qemp _cons Change in probability of arrest if pcnv increases by.5 lincom _b[pcnv]*.5 ( 1).5 pcnv = 0.0 (1) Change in probability of arrest if ptime86 increases by 6 lincom _b[ptime86]*6 ( 1) 6.0 ptime86 = 0.0 (1) Change in probability of arrest if ptime86 decreases by 12 lincom _b[_cons]- _b[ptime86]*12 ( 1) ptime86 + _cons = 0.0 (1) Change in probability of arrest if qemp86 increases by 4 lincom _b[qemp86]*4

8 8 ( 1) 4.0 qemp86 = 0.0 (1) reg arr86 pcnv avgsen tottime ptime86 qemp86 black hispan Source SS df MS Number of obs = F( 7, 2717) = Model Prob > F = Residual R-squared = Adj R-squared = Total Root MSE = pcnv avgsen tottime ptime qemp black hispan _cons This page prepared by Oleksandr Talavera (revised 8 Nov 2002) Send your questions/comments/suggestions to Kit Baum at baum@bc.edu These pages are maintained by the Faculty Micro Resource Center's GSA Program, a unit of Boston College Academic Technology Services