[Network analysis] inconsistent results

Zedo

Hi,

I am running network analysis in JASP (0.19.2) and then in R for a double check and further exploration. I met quite different results so I started with a simple model to find the reason. Here, I used four variables without missing values and ran a very simple network using the "Correlation" estimator in JASP. As I understand, this should result in a network where the weight matrix is exactly the same as the correlation matrix. But, as you can see, the values are the same (i.e., 0.357, 0.367, 0.223, 0.292, 0.343), but in different cells.

I replicated that in R as follows. This is the same as the correlation matrix.

So I wonder, does JASP change the order of variables when presenting network results without correctly defining the labels? As I checked, the correct order should be:

Thank you very much for your help!

Best,

Zedo

vandenman

Hi Zedo,

Thanks for pointing this out. It indeed looks like the order in the weights matrix is incorrect. I also checked the order in the Network plot, and that one does appear to line up with the results from the correlation matrix.

Best,

Don