Dear,
I am struggling with starting the analyses for the following data:
We have 60 participants rating 40 photographed environments. Every participant rates the same 40 photographs. We aim to investigate the participants' and photographs' characteristics predicting the rating of the photograph.
Based upon the MCMC manual and other readings I think this can be regarded as a cross-classified model with measurements at level 1 within participants and photographs crossed at level 2?
I have currently organized the data as follows; participants numbered 1-60 and photographs 1-40 "within" each participant. The measurements are numbered 1-2400. Is this correct? Are there any other factors I should take into account?
An additional complication is that we have 2 different ratings of the photographs. Is it possible to run a multivariate model within the above described cross-classified structure? Or are there other solutions?
Thank you very much in advance!
Kind regards
Jelle Van Cauwenberg
question about a cross-classified model
Re: question about a cross-classified model
Hi Jelle,
Yes this sounds appropriate for the analysis you intend to do. I would firstly look at each of the 2 ratings separately and fit a straightforward single response cross-classified model as in the chapter in my MCMC book. To fit a MV model you will need to follow the example in the MV Normal modelling chapter except that you will have an extra higher level and will need to tick the cross-classified box but it should work fine.
Hope this helps,
Bill.
Yes this sounds appropriate for the analysis you intend to do. I would firstly look at each of the 2 ratings separately and fit a straightforward single response cross-classified model as in the chapter in my MCMC book. To fit a MV model you will need to follow the example in the MV Normal modelling chapter except that you will have an extra higher level and will need to tick the cross-classified box but it should work fine.
Hope this helps,
Bill.
Re: question about a cross-classified model
Hi Bill,
thanks for your reply, this certainly helps!
Kind regards
Jelle
thanks for your reply, this certainly helps!
Kind regards
Jelle