Dear Statalisters,
Thanks for your help.
I have received a patient dataset of the following format:
ID var1 var2 var3 var4QUESTION1 var5RESPONSE1 var6
var7......
1 x1 x2 x3 x4q1 x5r1
x6 x7 .....
1 x1 x2 x3 x4q1 x5r2
x6 x7 .... everything is duplicated except Response 2 for
Question 1 (mtple response issue)
1 x1 x2 x3 x4q1 x5r3
x6 x7......everything the same except Response 3 to Q1
1 x1 x2 x3 x4q2 x5r1
x6 x7 .....everything the same except Q2 & R2
1 x1 x2 x3 x4q3 x5r1
x6 x7 .....everything the same except Q3 & R3
.....
2 x1 x2 x3 x4q1 x5r1
x6 x7 ...
2 x1 x2 x3 x4q2 x5r2
x6 x7 ...
2 x1 x2 x3 x4q1 x5r1
x6 x7 ...
....
3 x1 x2 x3 x4q2 x5r1
x6 x7.....no missing values for Questions not answered
3 x1 x2 x3 x4q2 x5r2
x6 x7.....
....
I have read the multiple responses (Cox, drum) and repeated measures,
I have no unique ID and so cannot reshape the dataset, I need to
combine all the responses from all the questions to construct some
indices and need to have all this info on "one row/ID"; Stata sees the
data as duplicates but I cannot drop the observation as the response
variable is unique.... How do I get into a matrix of unique
(nonrepeating IDs) by unique variables (even if the rows become very
long)...There are 11,700 observations (rows)(responses to ~30
questions) for unique N=242. So I need to collapse the dataset into
242 rows with X columns.
Irina
Irina Campbell
________________________________________________________________
Irina V. McKeehan Campbell, Ph.D., M.P.H.
Director of Clinical Development and Quality Care
Cogent Healthcare, Inc.
www.cogenthealthcare.com
tel/fax: (845) 358-6607
mobile: (914) 844-6145
[email protected]
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
