SSRN Author: Shengwu ShangShengwu Shang SSRN Content
http://www.ssrn.com/author=2354396
http://www.ssrn.com/rss/en-usFri, 24 Mar 2017 02:37:40 GMTeditor@ssrn.com (Editor)Fri, 24 Mar 2017 02:37:40 GMTwebmaster@ssrn.com (WebMaster)SSRN RSS Generator 1.0REVISION: Interaction Terms in Poisson and Log Linear Regression ModelsThis paper develops a difference-in-semielasticities (DIS) interpretation for the coefficients of dichotomous variable interaction terms in nonlinear models with exponential conditional mean functions, including but not limited to Poisson, Negative Binomial, and log linear models. We show why these interaction term coefficients cannot be interpreted as a DIS or semielasticity in the same manner as continuous coefficients, which has been overlooked by some empirical researchers. Then we show how interaction terms can be easily transformed into a DIS and derive the asymptotic distribution of this estimator. We illustrate the discrepancy between the interaction term coefficient and the DIS using an empirical example evaluating the relationship between employment, private health insurance and physician office visits. Our results can be applied in treatment effect models when the outcome variable is logged and the dichotomous variables indicating treatment participation and the ...
http://www.ssrn.com/abstract=2559413
http://www.ssrn.com/1491496.htmlWed, 27 Apr 2016 17:33:03 GMTREVISION: On Estimating Partial Effects after RetransformationThis paper makes several contributions to the literature on the retransformation problem. First, we derive the asymptotic distribution of the exponential sieve estimator, which has been previously unavailable in the literature. Second, we develop an average structural function type of average partial effect (APE), which applies to the Duan-type retransformation problem even though the independence between the underlying error and covariates is violated. Third, we consider the conditional average partial effect (CAPE), which allows for endogenous explanatory variables and is computationally simpler than existing nonparametric estimators currently available. Finally, we present two non-trivial applications of CAPE estimator. The first is to the average treatment effect in a nonlinear model; the second is to establish the estimator of interaction effect of two dummy variables on the level of dependent variable in the log linear model. Both applications provide new and useful tools for ...
http://www.ssrn.com/abstract=2763307
http://www.ssrn.com/1487656.htmlThu, 14 Apr 2016 22:54:17 GMTREVISION: On Estimating Partial Effects after RetransformationThis paper makes several contributions to the literature on there transformation problem. First, we derive the asymptotic distribution of the exponential sieve estimator, which has been previously unavailable in the literature. Second, we develop an average structural function type of average partial effect (APE), which applies to the Duan-type retransformation problem even though the independence between the underlying error and covariates is violated. Third, we consider the conditional average partial effect (CAPE), which allows for endogenous explanatory variables and is computationally simpler than existing nonparametric estimators currently available. Finally, we present two non-trivial applications of CAPE estimator. The first is to the average treatment effect in a nonlinear model; the second is to establish the estimator of interaction effect of two dummy variables on the level of dependent variable in the log linear model. Both applications provide new and useful tools for ...
http://www.ssrn.com/abstract=2763307
http://www.ssrn.com/1487340.htmlWed, 13 Apr 2016 21:52:24 GMT