Dear STATA community,
Please help!
I have messy data containing over thirty variations of different words (e.g., leadership) in four columns for over 800 observations. A screenshot of the data is attached. I could not use the dataex command due to the large size of the file.
How do I quickly calculate how many times each of the words appear among all four columns?
I also need to do crosstabulations between these two words at a time. How would I do it?
Do I need to recode each word into a numeric value?
I would appreciate your help!
Olena
Related Posts with Messy string data: how to do crosstabulations and descriptives
Gender wage gap, hourly wage or weekly wage- Combining the values of different categories into ONE with a repeated ID
- Mediation analysis (bias-corrected bootstrapping): Using panel survey data with fixed effects (sem/gsem/xtdpdml command)
- How to add scatter plot to xtline and modify its colours accordingly
- Editing graph
Subscribe to:
Post Comments (Atom)
0 Response to Messy string data: how to do crosstabulations and descriptives
Post a Comment