In this article, I derive a score test for the equality of one or more parameters across groups of observations following estimation of a single-index model. The test has a wide array of applications and nests Pearson's chi-squared test as a particular case. The postestimation command scoregrp implements the test and works with logit, logistic, probit, poisson, or regress (see [R] logit, [R] logistic, [R] probit, [R] poisson, and [R] regress). Finally, I show some applications of the test.
BoosD. D.1992. On generalized score tests. American Statistician46: 327–333.
2.
DemidenkoE.2004. Mixed Models: Theory and Applications.New York: Wiley.
3.
FearsT. R., BenichouJ., and GailM. H.1996. A reminder of the fallibility of the Wald statistic. American Statistician50: 226–227.
4.
GodfreyL. G.1981. On the invariance of the Lagrange multiplier test with respect to certain changes in the alternative hypothesis. Econometrica49: 1443–1455.
5.
TsiatisA. A.1980. A note on a goodness-of-fit test for the logistic regression model. Biometrika67: 250–251.
