PCA with random effects

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

PCA with random effects

David Sidhu
I have the results of a rating study in which ~30 participants rated a subset
of 20 items on 25 different dimensions.

I would like to perform PCA on these ratings to reduce the 25 different
dimensions. However, instead of doing this on the mean ratings for each
item, I would like to perform the PCA at the level of individual ratings. I
am assuming that in order to do this I have to specify the fact that ratings
are nested within participants and within items (i.e., crossed random
effects for subjects and items). Is this possible?

---
David M. Sidhu, MSc<http://davidmsidhu.com/>
PhD Candidate
Department of Psychology
University of Calgary







        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: PCA with random effects

Bert Gunter-2
This is a statistical question, which is typically off topic here.
This list is primarily concerned with R programming questions,
although the two areas sometimes do intersect. I suggest you post on a
statistical list such as stats.stackexchange.com instead, especially
if you do not get a useful reply here.

Cheers,
Bert
Bert Gunter

"The trouble with having an open mind is that people keep coming along
and sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )


On Mon, Apr 2, 2018 at 3:43 PM, David Sidhu <[hidden email]> wrote:

> I have the results of a rating study in which ~30 participants rated a subset
> of 20 items on 25 different dimensions.
>
> I would like to perform PCA on these ratings to reduce the 25 different
> dimensions. However, instead of doing this on the mean ratings for each
> item, I would like to perform the PCA at the level of individual ratings. I
> am assuming that in order to do this I have to specify the fact that ratings
> are nested within participants and within items (i.e., crossed random
> effects for subjects and items). Is this possible?
>
> ---
> David M. Sidhu, MSc<http://davidmsidhu.com/>
> PhD Candidate
> Department of Psychology
> University of Calgary
>
>
>
>
>
>
>
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.