Constructing an index: is it necessary to standardize?

[Andrea Arancio]

Hi Statalist!
I would really need your help on this before-christmas issue!

I'm constructing an index made by the sum of three variables, which all vary in the range [0,1] (as they have been divided by their theoretical maximum).

Depending on the sample analyzed, it is not always assured that the three variables have the same variances (and st. deviations). In order to attribute them the same importance, one solution, before making the sum, would be to standardize them (subtracting the mean and dividing by the standard deviation). In this case the index would correspond to the sum of standardized scores.

My questions are:
- is standardization necessarily required? would it have other drawbacks (apart from changing the scale)?
- would you reccommend standardization or another solution?
- Could the sum of unstandardized scores be OK?

Thanks a lot and happy XMAS!

[Andrea Arancio]

Also cross-posted here: https://stats.stackexchange.com/ques...to-standardize

[Phil Bromiley]

You'll increase your chances of a helpful answer by following the FAQ ona asking questions - provide State code in code delimiters, readable Stata output, and sample data using dataex.

There are a bunch of ways to generate scores - the alpha routine, principal components,and SEM come to mind. They make different assumptions, although sometimes they may give similar results. Is standardization necessary? It depends on the situation. If you want the three components to have equal influence, then you probably want to standardize. There is a Stata function (in egen probably) that does the standardization.