Statalist


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

Re: st: Poststratification


From   Steven Samuels <[email protected]>
To   [email protected]
Subject   Re: st: Poststratification
Date   Mon, 19 Jan 2009 11:31:39 -0500


Tomas, I didn't answer the question you asked. You should include the geographic strata as well. However their exclusion would affect only standard errors and degrees of freedom.

-Steve
On Jan 19, 2009, at 11:08 AM, Steven Samuels wrote:

You must include the [pweight] option. The example is the Stata Survey Data Manual (p. 50 Version 10) is misleading. Because the example used SRS, probability weights were equal.

-Steve


On Jan 19, 2009, at 10:42 AM, Tomas Lind wrote:

I have a survey that is stratified on geographical areas. Now I want to poststratify on a combination of age and income. Should I specify both strata and option poststrata or shall I specify only option poststrata? The
result is slightly different.

// svyset with strata
svyset  [pweight=v] , strata(str)  poststrata(ai)  postweight(n_ai)

// svyset without strata
svyset              ,           poststrata(ai)  postweight(n_ai)


/Tomas

*
*   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/

*
*   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/

*
*   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/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index