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

Re: st: Extremely poor performance in repeated ANOVA

From   Michael Ingre <[email protected]>
To   "[email protected]" <[email protected]>
Subject   Re: st: Extremely poor performance in repeated ANOVA
Date   Thu, 05 Feb 2004 10:25:52 +0100

David Airey <[email protected]>:
> On my computer, a 1.25 GHz Powerbook, the timing for this problem with
> Michael Ingre's data set was:
> r; t=119.92 9:02:08

. r; t=183.95 9:50:22 (PowerBook 800Mz)

> Data Desk could not, for example, compute a Ingre's problem using
> MANOVA, according to the manual. Stata can.

I don't think Stata can either. But you could try prove me wrong.

> Ouch. Are there no alternatives in any of the xt- commands in Stata?
> This is usually where I get frustrated with what I don't
> know--(in?)applicability of the xt commands to experimental repeated
> measures data typically analyzed by ANOVA/MANOVA or mixed modeling.

I have only had a brief look at the xt commands and it is possible that
there is an alternative there. My (limited) understanding is that they are
more suitable for true time series data (and autoregressive correlation
structures) than for data from complex designs with several within subject
factors.  I'm not sure about the applicability of for example -xtgee- for my
kind of data. In xtgee you can at least model a couple of different
correlation structures and even supply your own matrix. I'm happy for advise
about the xt commands in experimental designs.

>> Mixed modeling is an area that I'm very interested in. I have no
>> practical
>> experience of it but from what I've read it is the answer to many of my
>> problems. And that's why I will take some time to learn GLLAMM which
>> as I
>> understand is the closest to Proc Mixed you can get in Stata.
> Yes, but another list member has repeatedly stated that GLLAMM has
> limited ability for modeling the covariance structure. When you take
> that course, report back!

Well, you can't get it all.... I'm taking a one week intensive course in
K´┐Żln/Germany in the middle of March. Lecturer is prof. Andrew Pickles
co-author of GLLAMM. It will be fun and hopefully some question marks will
be straighten out. I will report (to anyone who's interested) about the
applicability of GLLAMM in experimental designs however, I don't expect any
improvements in speed ...


*   For searches and help try:

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