Statalist The Stata Listserver

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

Re: st: -mfx-: can I just keep the interaction variable?

From   Scott Cunningham <>
Subject   Re: st: -mfx-: can I just keep the interaction variable?
Date   Mon, 11 Sep 2006 10:29:52 -0400


You're right; that must be it, because when I drop vce(boot) the - mfx- works fine. What's a good solution for calculating the marginal effects when you've used bootstrapping to construct standard errors, but -mfx- is having that type of trouble?


On Sep 10, 2006, at 10:22 PM, Richard Williams wrote:

At 07:33 PM 9/10/2006, Scott Cunningham wrote:

The dataset is the NLSY97, selection just on males, blacks and whites
only, and balanced for the 1997-2002.  Here's the entire code, plus
output.  I'm going to snip the fixed effects, though.

. xi:xtpoisson rp i.race age age2 hgc hhd1 i.year i.fip, vce(boot);
Note: One or more parameters could not be estimated in 7 bootstrap
replicates; standard error
      estimates include only complete replications.

. mfx, dydx varlist(_Irace_2 age age2 hgc hhd1);
no observations
I wonder if the vce(boot) and/or the fact that not all replicates were successful has something to do with it? What happens if you run it without vce(boot)? What does ereturn list tell you e(N) is?

Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX: (574)288-4373
HOME: (574)289-5227
EMAIL: Richard.A.Williams.5@ND.Edu
WWW (personal):
WWW (department):
* For searches and help try:
*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index