1 Master Economics and Public Policy Ecole Polytechnique

1 Master Economics and Public Policy Ecole Polytechnique – ENSAE - Sciences Po Academic year 2009 -2010 Quantitative sociology Basics on GLM on stata 11 louis. chauvel@sciences-po. fr

2 What do we do today? Ø Overview on General Linar Model What’s this? => generalization of many kinds of regressions Syntax => glm vardep listofvarindep [fweight=weightvar] if (condition), family(xxx) link(yyy) comparison of models, etc. => estimates store mod / estimates stats mod for the bics Ø On STATA 11: same as regression and logit : for categorical indep var and for interactions

3 Ø Categorical independent variables no more “ xi: ” To change the reference category = fvset base 2 gender Ø Expression of interactions “ # ” for interaction without fist order variables “ ## ” for interaction AND fist order variables

link() family() | id logit probit clog pow opower nbinomial loglog logc -----+---------------------------------Gaussian | x x x inv. Gau. | x x x binomial | x x x x x Poisson | x x x neg. bin. | x x gamma | x x x Link function glm option --------------------identity link(identity) log link(log) logit link(logit) probit link(probit) complementary log-log link(cloglog) odds power link(opower #) power link(power #) negative binomial link(nbinomial) log-log link(loglog) log-complement link(logc) Family glm option --------------------Gaussian(normal) family(gaussian) inverse Gaussian family(igaussian) Bernoulli/binomial family(binomial) Poisson family(poisson) negative binomial family(nbinomial) gamma family(gamma) 4