dear all,

I have a dataset with 40 cases (countries) and 40 years (with missing) about religious behaviour.

I need to cluster these trends according to their pattersn of religious behaviour using sequence analysis. I have some questions about this:

- Is this method appropriate when you have few cases?

- My dependent variable (average religious practice) is a scalar one (ranging from 0 to 1). Is it fine to leave it as it is or it is better to recode in few categories?

- Given the quite high number of missing values, the STATA sqom doesn't perform well, unless I use only the longest pieces of complete sequences (which is not fine because you miss the time frame, which is peculiar for this analysis). How can I solve this?

thank you in advance for your suggestions!

bests,

Francesco Molteni