Estimation of marginal effects using margeff

被引:271
作者
Bartus, Tamas [1 ]
机构
[1] Corvinus Univ, Dept Sociol & Social Policy, Budapest, Hungary
关键词
st0086; margeff; mfx; average marginal effects; marginal effects at the mean; dummy variables; squared variables;
D O I
10.1177/1536867X0500500303
中图分类号
O1 [数学]; C [社会科学总论];
学科分类号
03 ; 0303 ; 0701 ; 070101 ;
摘要
This article describes the user-written program margeff, which enables the fast estimation of (average) marginal effects. Besides describing the program, this article offers a new discussion of some problems that are related to computation of marginal effects. I will argue that (1) marginal effects computed at means are not good approximations of average marginal effects, computed as means of marginal effects evaluated at each observations, if some of the parameter estimates are large; (2) both average marginal effects and marginal effects computed at means might produce wrong estimates for dummies that are part of a set of indicator variables indicating different categories of a single underlying variable; and (3) the use of marginal effects computed at means is preferred if some of the regressors are mathematical transformations of other regressors.
引用
收藏
页码:309 / 329
页数:21
相关论文
共 3 条
[1]  
Bockarjova M., 2000, SEM LAB MARK WORK WE
[2]  
Greene W. H., 1997, Econometric Analysis, V3rd ed.
[3]  
Long J., 1997, SCOTT REGRESSION MOD