Please suggest a way of recoding a continuous variable into a 'Likert Scale' variable.
Lowest 20% should be translated to 1.
Next 20% should be translated to 2.
.
.
Top 20% should be translated to 5.
Your help is greatly appreciated.
Nicholas Kormanik
Proc means, summary or univariate on the data requesting the appropriate percentiles.
Code if/then/else using those values OR a custom format assigning the values 1 to 5 (or possibly more meaningful text) to the raw values.
Or possibly Proc Rank using groups=5 to create a new variable but you would have to add 1 to the value as rank will create 0 to 4 for the value.
Proc means, summary or univariate on the data requesting the appropriate percentiles.
Code if/then/else using those values OR a custom format assigning the values 1 to 5 (or possibly more meaningful text) to the raw values.
Or possibly Proc Rank using groups=5 to create a new variable but you would have to add 1 to the value as rank will create 0 to 4 for the value.
Perhaps using 0 to 4 would work, too, as opposed to 1 to 5. I don't see that it would make any difference. So Proc Rank may be the one to use.
I would greatly prefer not having to put in specific values of the raw data, as I have a hundred such variables to recode.
It's finally time to hack! Remember to visit the SAS Hacker's Hub regularly for news and updates.
Learn the difference between classical and Bayesian statistical approaches and see a few PROC examples to perform Bayesian analysis in this video.
Find more tutorials on the SAS Users YouTube channel.
Ready to level-up your skills? Choose your own adventure.