[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: AW: double hurlde models?

From   "Martin Weiss" <>
To   <>
Subject   Re: st: AW: double hurlde models?
Date   Mon, 16 Feb 2009 21:18:09 +0100


Just to make sure we answer your initial questions: -findit double hurdle model- does not point to any commands, so either this method is also known as something else, then try -findit-. Or this is indeed the only -program- out there. Either way, when I -which- the thing, it tells me that the latest version was released almost to the day six years ago...

Without a help file, it is hard to know how -dhurdle- goes about its business. A look at the ado code is always a way to get a handle on this problem. You say you are new to this, so I recommend -ssc d fedit- for your attention, in conjunction with your favorite text editor.

Another useful set of (advanced) tools is -help trace- and -help profiler-

----- Original Message ----- From: <>
To: <>
Sent: Monday, February 16, 2009 8:30 PM
Subject: Re: st: AW: double hurlde models?

Thanks Martin,

I dropped the files in the ado folder. The model ran, and the coefficients make sense. It doesn't appear to like -margeff- or -mfx- as post-estimation commands though (I get an error: "unrecognized command: dhurd_p").

For others interested, I recently found STATA code for Box-Cox double hurdle models in Moffatt,P.G. (2005) "Hurdle models of loan default." Journal of the Operational Research Society 56(Special Issue), 1063–1071. I haven't looked at it closely yet, but this may be helpful as well.

Thanks again.

Jason Franken

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index