Hi all,
I was wondering if anyone could give me some suggestion on command
-svytab-.
My goal is to get the frequencies distribution of most of the
variables
in a survey data set (with sampling weight). I don't choose -
tabulate-
because it can't be used together with pweight.
So, I generate a constant variable which equals 1 and -svytab each
variable I'm interested with in the data set together with the
constant
variable 1.
The problem is that, it takes about 5 minutes to do just one svytab .
After svytab for 4 variables, stata shows there's not enough memory to
do svytab to the rest variables,although the memory has already been
set to 1g. (The data set has 3,932,343 observations and 90 variables.)
So, my questions are as follows.
(1) Is it normal that -svytab- need so much memory and it works so
slowly ?
(2) Is there any better way to check frequencies of a lot of variables
with sampling weight?
(3) Suppose the goal of checking frequencies is just to see if
there's
anything weird or any errors in the data. Is there any problem if I
just use -tabulate- and put the weight variable as aweight or fweight
instead of pweight?
Thanks a lot for your help!
Mandy
*
* 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/
