Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

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

Re: st: Trouble producing population standard deviations with collapse (sd)

From   Steve Samuels <>
Subject   Re: st: Trouble producing population standard deviations with collapse (sd)
Date   Fri, 13 Jul 2012 19:33:54 -0400

If your subset "represents 100% of the population", the implication is that you have survey data, and must,
 therefore, have a weight variable e.g. "final_wt". Add [pw = final_wt] before the comma. To compute
standard errors, -svyset- your data and use Stata's survey commands.


On Jul 13, 2012, at 4:36 PM, Matt Vivier wrote:

Hello all,

My specs are:
Stata/IC 12.1 for Windows (64-bit x86-64)
Revision 06 Feb 2012

I am having some trouble getting collapse to produce the result I am
looking for. I have done some searching, and have not found anyone
else presenting this problem. I need it to generate the population
standard deviation for a large number of subsets of data, but it
appears the command I am using is generating a sample standard
deviation. Each subset of the data represents 100% of the population I
am interested in the SD for. Is there a simple way to do this, or will
I need to compute the SD using another process?

My code is as follows:

collapse (sum) TotCost TotAcute TotPostAcute ReadmissionCost
ReadmissionClaims count (sd) SDTotCost=TotCost
SDTotPostAcute=TotPostAcute SDReadmissionCost=ReadmissionCost (mean)
AvgTotCost=TotCost AvgTotPostAcute=TotPostAcute
AvgReadmissionCost=ReadmissionCost, by(drg_condition TriggerProvider

Thank you for your help,

The information contained in this message may be privileged, confidential, 
and protected from disclosure. If you are not the intended recipient, or an 
employee, or agent responsible for delivering this message to the intended 
recipient, you are hereby notified that any dissemination, distribution, or 
copying of this communication is strictly prohibited. If you have received 
this communication in error, please notify us immediately by replying to 
the message and deleting from your computer.
*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index