Quantcast
Browsing all 1125 articles
Browse latest View live

Re: Unit-root tests in Stata

Thank you for the interesting article! Would it maybe be possible to provide some guidance for panel unit-root tests?

View Article


Re: Unit-root tests in Stata

Hi JM,I will keep this in mind for future blog posts.Thanks

View Article


Re: Flexible discrete choice modeling using a multinomial probit model, part 1

I am working on a model of demand for alternative transportation modes. So your discussion has been extremely helpful. I look forward to the second part. Thanks.

View Article

Re: Flexible discrete choice modeling using a multinomial probit model, part 1

Glad to hear that it's helpful. Thanks for the comment!

View Article

Re: Using dates and times from other software

To go from R to Stata dates you should add tC(01jan1970) instead of subtract. This post got me to where i need to be, though, so thank you!

View Article


Re: Unit-root tests in Stata

A discussion on unit root tests with structural breaks would also be very helpful.

View Article

Re: Statalist

I am having a problem with logit using categorical variables. I am using Stata 13.1 for Windows. I have a dog breed variable and I would like to compare each breed against all remaining dogs but I can...

View Article

Re: Tests of forecast accuracy and forecast encompassing

Very interesting post Ashish, thank you. Would this also be applicable in a panel data context? If so, then P would again be the number of out-of-sample observations or it would be N*(number of OOS...

View Article


Re: Measures of effect size in Stata 13

You will probably have to update your Stata 12 to 13. I also tried reading the dataset in version 12 to no avail.

View Article


Re: Unit-root tests in Stata

Thanks for this interesting post. While reading it I was wondering about the potential problems with real-life data when the trend is not so obvious in the time-series plot (like in figure 1). Here,...

View Article

Re: Unit-root tests in Stata

Hi Roberto,If there is no clear trend then I would test the alternative hypothesis of stationary around a constant mean instead of a time trend.In the post, I included a trend term because I was...

View Article

Re: Comparing predictions after arima with manual computations

Does this also come up in AR models (without the MA component)?

View Article

Re: Doctors versus policy analysts: Estimating the effect of interest

Dear mr Drukker, can you also provide the syntax to create the simulated data set needed to run the examples that you discuss?

View Article


Re: Doctors versus policy analysts: Estimating the effect of interest

David -- why did you do this w a manually calculated interaction term, (it), ra ther than w Stata's interaction notation?

View Article

Re: Introduction to treatment effects in Stata: Part 1

I realize this post is over a year old but it seems like it might need some editing. I have loaded the data from cattaneo2.dta and ran a basic logistic regression to estimate the probability of...

View Article


Re: Probability differences and odds ratios measure conditional-on-covariate...

Dear Mr Drukker, can you please provide the (simulated) data so we, as readers of your great blog, can exercise your examples too (or the syntax with which the data can be simulated)?

View Article

Re: Effects of nonlinear models with interactions of discrete and continuous...

Great article. If I have to dummy variables (say black/white and Male/female) and my dependent variable is a dummy, how do I check if the interaction term is significant? I can do that by generating a...

View Article


Re: Understanding matrices intuitively, part 1

This is a great blog post, you've really helped me gain insight into both abstract (matrix multiplication) and applied (linear regression) concepts. Much appreciated!

View Article

Re: Effects of nonlinear models with interactions of discrete and continuous...

Hello Martin,Sorry for the late reply, I had not seen the comment. Notice, that in my example I had a binary outcome (married) and two binary variables (pdivorce) and (divorce). You do not need to...

View Article

Re: Bayesian binary item response theory models using bayesmh

Nice presentation at the Stata conference Nikolay. Definitely cool to get a bit more explanation of things and see other uses of the techniques.

View Article
Browsing all 1125 articles
Browse latest View live