Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

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

Re: st: "covariates in dataset 2 do not match covariates in dataset1"

From   Maarten buis <>
Subject   Re: st: "covariates in dataset 2 do not match covariates in dataset1"
Date   Tue, 16 Mar 2010 01:05:22 -0700 (PDT)

--- On Mon, 15/3/10, Michelle L Stransky wrote:
> I'm working with a multiply imputed dataset (so I have 5
> poverty variables to account for missing values).  I
> used the -reshape long- command to make each imputed
> variable it's own case (so now, for each case, I have it
> listed 5 times each with 1 imputation of income).
> I'm running a series of regressions, trying to fine tune
> the predictor variables.  The first regression runs
> fine but subsequent regressions (whether I use my .do file
> or copy & paste them into the command window) will not
> calculate.  I receive an error message stating that
> "covariates in dataset 2 do not match covariates in
> dataset1".
> I checked the file and everything seemed fine; the only
> things that don't exactly match across imputations of the
> dataset are the poverty values.  In fact, I've used
> this exact procedure on 2 other (very similar) datasets with
> no problems.  It's only been in the last month that I
> receive this message.
> What doesn't make sense to me is that the first regression
> command runs perfectly fine but subsequent commands do not
> (they're all in exactly the same form-- mim: svy: logistic
> dv iv1 iv2 iv3).  And if I close Stata and then open it
> and run the second regression it works.  I've attempted
> to run this analysis on Stata9 Intercooled and Stata11
> SE.  It doesn't seem to matter; I receive the same
> error.
> Do you have any recommendations or suggestions for me as to
> why this happens and/or how to fix it?

-mim- is looking for a variable _mj to identify the different
datasets and _mi to identify the observations. Do these exist
in your dataset?

-- Maarten

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen


*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index