Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Daniel Stuart <daniel.stuart78@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: Semiparametric estimation of single-index models |
Date | Sun, 21 Oct 2012 19:57:53 -0400 |
Hi everyone, I am hoping to estimate a single-index model, E[y|x] = g(x'B), using one of the following semiparametric estimators discussed in Cameron and Trivedi's 2005 book "Microeconometrics: Methods and Applications", page 325-327: 1) the Density-Weighted Average Derivative (DWAD) estimator developed by Powell, Stock and Stoker (1989) 2) the Weighted Semiparametric Least-Squares (WSLS) estimator developed by Ichimura (1993), or, 3) the estimator developed by Klein and Spady (1993), that is not discussed in Cameron and Trivedi, but seems to be a good option and maximizes a quasi-likelihood function. I am hoping to implement any one of these in Stata, and was wondering if anyone has done this before, or has any tips. I haven't been able to find a user-written file that calculates the above estimators, so perhaps coding by hand is the way to go here. Thanks for any advice you have to offer, and please let me know if I can provide any other details. Thanks, Dan Stuart * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/