Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: hireg help

From   Richard Williams <>
Subject   Re: st: hireg help
Date   Fri, 18 May 2007 23:13:42 -0500

At 10:15 AM 5/18/2007, Austin Nichols wrote:

After a quick look, -hireg- seems to have some minor mistakes in the
code--e.g. it reports obs not used when option -nomiss- is specified
without reference to [if] and [in] restrictions--but I cannot easily
see the source of your reported error.
After fiddling around I think I see the problem. I created some fake data and Megan's command worked fine in Stata 9.2 but I replicated her problem in Stata 8.2. It turns out that in Stata 9.2., string expressions can be 244 characters long, but in some versions of 8.2 they can only be 80 characters long. Megan's independent variable list was therefore getting truncated just before she got to the last 3 vars. The fact that "ortho" was included twice in her var list didn't help any either.

One solution would be to use Austin's hireg2, and another would be to shorten the variable names. If you want to patch a copy of the original hireg (rename it hireg2 or something like that like Austin did), I think all you need to do is look for the lines

local v = "`v' `1'"
local vn = "`1'"
local vv = "`vv',`vn'"
local vl = " `vl' `1'"

and delete the equals signs, i.e. change the lines to

local v "`v' `1'"
local vn "`1'"
local vv "`vv',`vn'"
local vl " `vl' `1'"

Incidentally, I would always use the nomiss option with hireg. Otherwise you could be comparing models estimated with different cases.

I don't know if Paul Bern is on Statalist. I'll try to email him about this.

Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: Richard.A.Williams.5@ND.Edu

* For searches and help try:

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