Kimo Boukamba, I'm not exactly sure what's going wrong for you, but it seems you're not conducting parallel analysis correctly. Perhaps try the following site:

https://analytics.gonzaga.edu/parallelengine/

In it, enter your information (number of items and number of participants) and I think you can retain the default entries for the other fields.

Can you try that and see whether you get better results?

Incidentally, "officially" PCA isn't really EFA, even though you'll probably get similar results either way.

I think that, if your scree plot and parallel analyses indicate there are only 3 factors in your data, I'd run with that. Using eigenvalues > 1 (the Kaiser criterion) is often not a good strategy for determining number of factors. In fact, I have often found it quite misleading.

Do feel free to get back if you keep having problems.

Kimo Boukamba, I'm not exactly sure what's going wrong for you, but it seems you're not conducting parallel analysis correctly. Perhaps try the following site:

https://analytics.gonzaga.edu/parallelengine/

In it, enter your information (number of items and number of participants) and I think you can retain the default entries for the other fields.

Can you try that and see whether you get better results?

Incidentally, "officially" PCA isn't really EFA, even though you'll probably get similar results either way.

I think that, if your scree plot and parallel analyses indicate there are only 3 factors in your data, I'd run with that. Using eigenvalues > 1 (the Kaiser criterion) is often not a good strategy for determining number of factors. In fact, I have often found it quite misleading.

Do feel free to get back if you keep having problems.

The eigenvalues, if calculated correctly and on the same correlation matrix, are going to be the same.

After conducting PCA, further exploratory analysis are meant to check whether there is any hidden latent variable that was not properly identified in PCA. This is achieved by rotating the significant PCs (EV>1) by varimax rotation. I think the Parallel Analysis (EV

Read the articles below for better reference purpose:

- Source identification and evaluation of surface water quality using factor and discriminant analysis.

- Spatial assessment of air quality patterns in Malaysia using multivariate analysis.

- River water quality assessment using environmentric techniques....

Thank you all for your suggestions.

Robert Trevethan I have carefully re-run the parallel analysis using two different methods but the EV

Kimo Boukamba, I'm really glad you got back. You have chosen the incorrect option in the parallel analysis site. You should choose Principal Components as the type of analysis, not Factors.

Please do that, and then conduct your parallel analysis.

I think that the YouTube presentation you refer to might be a bit misleading.

Please feel free to keep coming back to me. I'm happy to walk with you until you solve your problem. I'm pretty sure it can be solved easily.

Robert Trevethan

sorry i have just updated my response.

Here is the last bit:

As far as the way forward is concerned, I am happy to proceed with the 3-factor solution. However, for the sake of understanding, the EV

Kimo Boukamba, we are a little bit out of kilter with our communication. Don't worry. I think that, if you choose Principal Components, not Factor, in your parallel analysis, your problem will go away.

I looked in more detail at the YouTube presentation you referred to. I think the presenter is very skilled at making things more complicated than they need be. I'd not worry about it, or try to understand it, at all.

Again, come back if I might be able to help more.