Re: probit or logit: ladies and gentlemen, pick your weapon
Enrique, I think the simulations for LPM would be of general interest. There's been quite a lot of discussion of the relevant merits of LPM and logit/probit. For example, see blog posts (and...
View ArticleRe: probit or logit: ladies and gentlemen, pick your weapon
Hello Stephen,Currently I am running some simulations comparing the results for marginal effects and treatment effects using the LPM when the true model is a probit and when the true model is a logit....
View ArticleRe: Export tables to Excel
I wrote an alpha version of a program that can export two-way tabulations to excel.Please check at: https://github.com/leoshibata/...
View ArticleRe: Retaining an Excel cell’s format when using putexcel
I wrote an alpha version of a program that can export two-way tabulations to excelPlease check at: https://github.com/leoshibata/...
View ArticleRe: Using Stata’s random-number generators, part 1
I think you can use runiformint(0,1) for that.
View ArticleRe: Programming an estimation command in Stata: Adding robust and...
Hey David,Just wanted to say thanks for putting these together. It brings a lot of otherwise abstract concepts into the concrete realm a bit more and is useful not only for understanding the...
View ArticleRe: Bayesian binary item response theory models using bayesmh
Hi Nikolay and Yulia,I wanted to try out using the example to specify a Rasch model, which seems correct (the parameter estimates are also reasonably close to those derived from jMetrik using the same...
View ArticleRe: Bayesian binary item response theory models using bayesmh
Dear Billy,See our answers to each of your questions below.1. Rasch modelYour specification of the Rasch model is correct. That is, for our math and science data example, a Rasch model can be specified...
View ArticleRe: Bayesian binary item response theory models using bayesmh
Hi Nikolay and Yulia,Awesome. I think we're talking about slightly different things with regards to #3. Here's an extremely brief explanation of the infit/outfit statistics from the Rasch perspective:...
View ArticleRe: Bayesian binary item response theory models using bayesmh
Hi Nikolay and Yulia,As a brief follow up regarding the Joint MLE and Infit/Outfit statistics, I put together a quick demonstration of some of the differences that I observed. The program is a wrapper...
View ArticleRe: Spotlight on irt
You can get Empirical Bayes modal or mean estimates of theta using:predict theta_modal, latent ebmodepredict theta_mean, latent ebmeanAfter fitting the model.
View ArticleRe: Spotlight on irt
You can find related literature in the SEM - or classical test theory - side of things. One of the concerns with longitudinal models (from the CTT perspective) is measurement invariance; in other...
View ArticleRe: Bayesian binary item response theory models using bayesmh
Dear Billy,As we have mentioned earlier, the bayesmh formulation of the Rasch model does estimate item-specific and person-specific parameters jointly. The Bayesian estimates of the parameters should...
View ArticleRe: Bayesian binary item response theory models using bayesmh
Hi Nikolay,Thanks again for the additional information. I thought there may have been more substantial differences between the marginal and joint MLE algorithms for estimating the item and person...
View ArticleRe: regress, probit, or logit?
Hi Enrique, my paper with Steven Durlauf and David Rivers, and my paper with Steven Durlauf and Chao Fu show the risks of using the linear probability model in real data (the death penalty). I am glad...
View ArticleRe: regress, probit, or logit?
Hi Salvador,They really can produce very different results. My simulations are very conservative in terms of the choices of covariates and this still showed up. I was a bit surprised to hear that there...
View ArticleRe: Introduction to treatment effects in Stata: Part 2
what did you mean by "the determinants of treatment status" and "the determinants of the outcome"?
View ArticleRe: Export tables to Excel
i have one doubt... is it possible to transfer stata 12 result into excel spreadsheet? i tried that but i cant....
View ArticleRe: Probit model with sample selection by mlexp
Don't know if anyone is going to see this but I am trying to replicate your code and get the following error when trying to implement the first mlexp command:variable _cons not foundr(111);I am using...
View Article