0

My goal is to compare two of the groups I tested in a QAP using netlogit function in the sna package (I have five conditions). I have created confidence intervals as well and can access the standard error through the netlogit function. However, the typical tests (Fischer, etc) won't allow network matrices. Any ideas on how to compare two groups for statistical significance using matrix data?

Here is one matrix example (1 is tie between two nodes and 0 is no tie).

```
```Id   1   2   3   4   5   6
```1    0   1   1   0   1   0
```3    0   0   0   0   0   0
```4    0   0   0   0   1   0
```5    0   0   0   0   0   0
```6    1   1   1   1   1   0
    
  • It would be easier to help if you provide examples to how your data is formatted exactly. Network matrices can have many forms, so a small example of the two matrices you wish to compare will allow us to understand what the challenge is. – dvd280 Aug 24 '20 at 08:09
  • Thanks, @dvd280. I appreciate the suggestion. It's network data, so the comparison between groups results in the likelihood of a tie between two individuals under different conditions. The trouble I am having is finding a package that can test the differences between groups for statistical significance for a follow-up test (that can run with matrix data, not vector). – Kristie Neff Moergen Aug 24 '20 at 14:33

0 Answers0