Hi, all,
I had a data set of 2000+ variables (all binary or categorical), for example, 1000+ are characteristics of people (such as nationality, gender, etc.), the other 1000+ are fruits and vegetables (with 1 indicate the person likes it, and 0 indicates the person does not like). For example, in the picture I attached, we can see 1. most Columbians love Jackfruit; 2. most female like watermelon and pineapple; 3. most German female like apple...etc.
Is there a way (for example, maybe there is a code that STATA could automatically run many regressions and tell me which two variables are strongly correlated) that I can check correlations among those 2000+ variables quickly?
Thank you very much! I am totally lost......
Array
Related Posts with How to check correlation among 2000+ variables in a quick way?
Expand spell data into a panel with specific reoccuring observation datesDear Statalisters, I have an administrative dataset that is updated on the 1st and 15th day of ever…
Remove space from file nameHello all, I am working with a bunch of excel files and wish to re-save them without any spaces in …
Looping too many variablesI did the following for too many variables: Variable 1: Code: bysort year Industry: egen Industry_…
SUR vs GMM, 3SLS vs GMMHello, I'm trying to understand how GMM works and noticed that GMM produces the same estimates as O…
Add line to sts graph (kaplan meier)Im having trouble with overlaying two graphs. I have 3208 observations for my survival graph (curv…
Subscribe to:
Post Comments (Atom)
0 Response to How to check correlation among 2000+ variables in a quick way?
Post a Comment