Hello! I am using aggregated data and I want to assess the reliability of a scale of five items created with those aggregated data. I used the command alphawgt in Stata and entered as frequency weight the analytic sample for each country. Is it the right procedure to assess reliability in this case? or is there any other way? Thanks in advance.
Could you please provide some more information on the variables and the information collection procedure used to generate the data? Weighting for an aggregate like GDP works different than weighting for inflation, growth rates or per capita proportions; and if you're using survey data, you will first have to weigh the data with the sampling probabilities...
Alpha produces cronbachs alpha,which is a useful stating point. Might want to look at factor analysis.
- Badges
- Science topic