Statalist The Stata Listserver

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

Re: st: tetrachoric correlation

From   Maarten buis <[email protected]>
To   [email protected]
Subject   Re: st: tetrachoric correlation
Date   Wed, 15 Nov 2006 17:20:20 +0000 (GMT)

--- prneiva <[email protected]> wrote:
> When I write  matrix list r(Rho), the answer is matrix r(Rho) not
> found. 

Did you type -matrix list r(Rho)- after typing -tetrachoric varlist,
whatever option-? Better yet, did you copy the example I gave you and
tried that. That example should not give that error message, at least
it didn't gave me that error message.
> When I use the following procedure:
> matrix C = r(Rho)
> local n = r(N)
> factormat C, n(`n')
> the answer is: matrix C has missing values. 
> I don�t know what is happening, since the codebook shows that there
> is no missing values. 

Missing values in your data isn't the issue here, the missing values
are in the matrix. -factormat- needs all pairwise correlations, and if
one is missing it complaints. You can still get a complete correlation
matrix if you have missing data. One way to see what's going on is to
type -matrix list C-. 

Actually, if you are using real data I'd be worried if I did not have
missing values. It's not that I like them, but I know that real data
has them and that if I can't find them someone else has done something
I might not like, like just delete any case with a missing value or
impute it with the mean.


Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting adress:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

Send instant messages to your online friends 
*   For searches and help try:

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