[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

From |
Steven Joel Hirsch Samuels <sjhsamuels@earthlink.net> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: QUERY: svyset for a single stage survey with strata and clusters |

Date |
Tue, 21 Aug 2007 18:26:26 -0400 |

David, your specification is incorrect, but your question cannot be answered without one piece of information: was sampling with or without replacement? I'll assume that it was without replacement, the most likely method. In that case, do the following:

1. Create a variable nschools, which is the number of schools in each stratum--the population number not the sample number.

Code Follows:

/ ************************************************************************ **********/

gen finalwt=1/include

gen fpc2=1

svyset [pweight=final_wt] school, strata(schtype) fpc(nschools) || _n, fpc(fpc2)

/ ************************************************************************ **********/

If your purpose is to do statistical tests or other analytic comparisons, do NOT include the "fpc" (finite population correction) terms (WE Deming, Some Theory of Sampling, Wiley, 1950 (Dover, 1984)). The fpc terms are appropriate only for descriptive studies.

-Steven

On Aug 21, 2007, at 11:40 AM, DavidB.epid@public-health.ucl.ac.uk wrote:

Dear Statalist,

I have a survey design which runs as follows:

12 types of schools in London were identified. The type of school is

in a variable called 'schtype'. We sampled at random a certain

number of schools of each type. The school identifier is called 'schl'.

The selection school probability is held in a variable called 'include'.

In each school all children were sampled regardless of the number of

children.

Hence I take it the strata variable is 'schtype', the cluster variable is

'schl' and the fpc is 'include'.

Am I correct to write the svyset command as:

svyset schl, strata(schtype) fpc(include) vce(linearized)

Thank you for any help you can offer.

David Boniface.

*

* 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/

Steven Joel Hirsch Samuels sjhsamuels@earthlink.net 18 Cantine's Island Saugerties, NY 12477 Phone: 845-246-0774 EFax: 208-498-7441 * * 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/

**References**:**st: QUERY: svyset for a single stage survey with strata and clusters***From:*DavidB.epid@public-health.ucl.ac.uk

- Prev by Date:
**Re: st: GLLAMM modeling** - Next by Date:
**Re: st: profile.do can not be found** - Previous by thread:
**st: QUERY: svyset for a single stage survey with strata and clusters** - Index(es):

© Copyright 1996–2014 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |