With thanks as usual to Kit Baum, a new program underid by myself and Frank Windmeijer is now available on SSC.
underid provides postestimation tests of under- and over-identification after linear IV estimation, including static and dynamic panel data models. Supported estimators: ivregress, ivreg2, xtivreg, xtivreg2, xtabond2, xtdpdgmm, xthtaylor.
Tests available include classical (unrobust) and robust tests, including Anderson's canonical correlations test, Cragg-Donald, Kleibergen-Paap, and GMM-based tests (both 2-step GMM and CUE). The Sanderson-Windmeijer test of specific endogenous regressors is also supported.
A detailed description of the tests implemented is in the underid help file; for the econometric nitty-gritty, see Frank's paper here: https://ideas.repec.org/p/bri/uobdis/18-696.html
Related Posts with New program -underid- available on SSC
Why Multivariate L1 distance from Coarsened Exact Matching (CEM) is so high compared to Univariate imbalance for each matching covariate?I was looking at a paper (link here) by Blackwell et al. (2010) on CEM in Stata. In one example usin…
Clustering variablesHello everyone, I acutally have a problem with clustering and building the mean. My dataset contai…
Extracting month value from timestampI am working with survey data and there is a variable called "timestamp". Here is an observation fro…
Confirmatory factor analysis with high-frequency longitudinal dataDoes anybody know of a Stata program that can do confirmatory factor analysis in longitudinal data o…
Zero inflated negative binomial regression vs negative binomial regressionHello everyone, I am running an analysis to see if serum cholesterol together with sex, DBP, and Ag…
Subscribe to:
Post Comments (Atom)
0 Response to New program -underid- available on SSC
Post a Comment