You can. To use set analysis, you need an aggregation function like sum() or only(). To use an aggregation function like that in a dimension, you need to use an aggr(). So as a quick example that I just did in one of my applications to make sure I wasn't mistaken:
=aggr(only({<"Sheet / Tin"={'SHEET'}>} "Bill Payer Name"),"Bill Payer Name")
It's a bit of a silly example, but it demonstrates that you can indeed use set analysis in a dimension in a pivot table.
