Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: RE: AW: Rank transformation


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: RE: AW: Rank transformation
Date   Sun, 21 Jun 2009 18:45:39 +0100

Check out the -track- option of -egen, rank()-. 

Note that 

. search rank 

would have pointed you to this (and other stuff too).

Your example doesn't correspond to your original question, but that
seems of minor importance. 

Nick 
n.j.cox@durham.ac.uk 

Apostolos Ballas

Let's say for respondents 1 and 2 the answers are as follows:

   RESP.1 RESP.2
Q1	3	2
Q2	2	5
Q3	4	5
Q4	1	3
Q5	4	4
Q6	3	2
Q7	4	4
Q8	2	3
Q9	4	4
Q10	3	4
Q11	4	4
Q12	4	5
Q13	5	4
Q14	4	1

I want to recode it as follows:

   RESP.1  RESP.2
Q1	4	2
Q2	2	12
Q3	7	12
Q4	1	4
Q5	7	6
Q6	4	2
Q7	7	6
Q8	2	4
Q9	7	6
Q10	4	6
Q11	7	6
Q12	7	12
Q13	14	6
Q14	7	1

Martin Weiss

Forget about your spreadsheet thing and stick to Stata, first of all.
Secondly, give an excerpt from your data, as your request sounds easily
doable...

Apostolos Ballas
Betreff: st: Rank transformation

I have a dataset where X respondents have replied to 10 questions.
Answers
are on a Likert scale. I want to transform the data where the highest
scoring question is ranked 1st and the lowest 10th. Is there a simple
way
that I can do that automatically in Stata or should I recode everything
in
Excel?

*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index