Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: st:histogram for weighted data
From
Nick Cox <[email protected]>
To
"'[email protected]'" <[email protected]>
Subject
RE: st:histogram for weighted data
Date
Thu, 17 Mar 2011 18:41:50 +0000
There was a question on histograms with pweights just two days ago.
http://www.stata.com/statalist/archive/2011-03/msg00984.html
Please follow the thread, and its references; also check the archives first!
Nick
[email protected]
Amanda Fu
My data set is constructed from a sample. Therefore, each observation
is assigned a probability weight to be representative of the
population. There are no cluster or sample unit. I would like to make
a histogram for some variables, but histogram just allows frequency
weight.
In my opinion, when making histogram to describe the distribution of a
variable in a weighted data set, it is appropriate to use the
"sampling weight" as "frequency weight". Even if the -hist- command
allows to use sampling weight, the graph should be the same as that
used frequency weight.
I would appreciate it if anyone could correct me if my opinion is
wrong.
*
* 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/