Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: Multiple Imputation

From   "Nick Cox" <[email protected]>
To   <[email protected]>
Subject   st: RE: Multiple Imputation
Date   Wed, 2 Mar 2005 18:48:31 -0000

This shows how dangerous it is to make changes to a program 
if you don't understand the consequences of what you are 
doing. By making the change you did you made -mvis- call 
itself. This is not automatically wrong in general but it is quite 
wrong in this particular case. Your original call specified -m()- 
but your internal call did not, hence the error message, although 
it is not the message. 

The root of the problem, I guess, is that you installed only some 
of the files you need. Somehow, you did not install _mvis.ado. 
Perhaps you missed other files. 

I recommend that you go back and reinstall the package. The 
best way to do that is probably to take the version on SSC: 

. ssc inst mice, replace 

Then try again. You should not need to contact Patrick Royston
for support. 

[email protected] 

[email protected]
> I have been attempting to use Royston's multiple imputation 
> programs (mvis, 
> uvis) but have run into problems. When I first invoked mvis, 
> I received an 
> error message advising that "_mvis" was an unrecognized 
> command. I opened 
> the file, found "_mvis", edited it to read "mvis" and reran 
> the program. 
> This time, I received an error message that the option "m()" 
> was needed; it 
> had been and was specified through a number of runs. Any 
> suggestions or 
> advice on this, or are these concerns more appropriately addressed to 
> Royston? And, just to be clear, despite my editing of this 
> ado file, I know 
> little to nothing about programming. 

*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index