![Statalist](/includes/images/head_statalist.jpg) |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: Cluster analysis variables - bug?
Ricardo Ovaldia <ovaldia at yahoo dot com> reports a possible bug with
-cluster kmeans- creating two new variables where it should create one.
His -cluster- command is
. cluster kmeans q4_*, k(3) name(c1) s(kr(67492))
and he says this creates two new variables for him named 'c1' and 'cluster'.
I have been unable to reproduce this behavior (using Stata 9.2) Since I do not
have his data, I generated some of my own. This is my log file:
. clear
. set seed 2718
. set obs 100
obs was 0, now 100
. gen byte t1 = mod(int(3*uniform()),3) + 1
. gen byte t2 = mod(int(3*uniform()),3) + 1
. gen byte t3 = mod(int(3*uniform()),3) + 1
. summ
Variable | Obs Mean Std. Dev. Min Max
-------------+--------------------------------------------------------
t1 | 100 1.97 .8097262 1 3
t2 | 100 2.03 .8698659 1 3
t3 | 100 1.9 .8348471 1 3
. cluster kmeans t*, k(3) name(c1) s(kr(67492))
. summ
Variable | Obs Mean Std. Dev. Min Max
-------------+--------------------------------------------------------
t1 | 100 1.97 .8097262 1 3
t2 | 100 2.03 .8698659 1 3
t3 | 100 1.9 .8348471 1 3
c1 | 100 2.07 .7946157 1 3
If Ricardo requires further assistance with this, he should contact technical
support at [email protected] following the procedures outlined on
http://www.stata.com/support/faqs/techsup/sendout.html and possibly also
including a subset on his data on which he can reproduce the problem.
-- Jean Marie
[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/