Statalist


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

Re: st: RE: Incorporating sample design into logistic regression model


From   sjsamuels@gmail.com
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: RE: Incorporating sample design into logistic regression model
Date   Wed, 16 Dec 2009 14:35:47 -0500

This is not an SPSS list, but, yes, you do need the Complex Samples
module.  If you use the survey weights in a WEIGHT CASES statement,
SPSS will assume that the sample size is N, the population size.  The
estimates of coefficients will be unbiased, but standard errors and
tests of significance will be completely wrong. The scale weight in a
generalized linear model will also give the wrong results.

Since you are here:  I started with Stata myself years ago, because
one of my students could not afford to buy the SPSS module she needed,
although the base program was free. SPSS users find Stata very easy to
use because the command structures are similar.  If you are at a
University where there are other Stata users, it is easy to set up a
"Grad Plan" for individual purchases of Stata. (As an individual
faculty member, I set up such a plan for my campus once.)  The Grad
Plan cost of a single copy of Stata 11 SE  is much less than the
academic price of  the "Complex Samples"  module.  Even if you are not
at a University, I think Stata is worth the price.  I assure you from
personal experience that it is both more powerful and easier to use
than SPSS.  There are no extra modules, although you can pay more to
take advantage of multiple processors.  (I haven't needed to do this
yet) There are many free resources for learning Stata, and  the entire
documentation is available in PDF. The documentation has many
examples.  As you may be aware, the SPSS manuals show how to fill in
menus, but teach almost nothing about understanding  the commands they
demonstrate.,

-Steve

On Wed, Dec 16, 2009 at 2:05 PM, Martin Weiss <martin.weiss1@gmx.de> wrote:
>
> <>
>
> Sure you are on the right list?
>
>
> HTH
> Martin
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Jamie Burnett
> Sent: Mittwoch, 16. Dezember 2009 20:02
> To: 'statalist@hsphsun2.harvard.edu'
> Subject: st: Incorporating sample design into logistic regression model
>
>
> Hi, I desperately need some help?
>
>
> How do I go about using logistic regression in SPSS when I have Design
> (sample) weights (due to unequal probabilities of selection in my survey)
> and I want to take them into account when estimating the beta coefficients
> of my model. According to R. Groves and M. Couper 'Nonresponse in Household
> Interview Surveys' they talk about estimating the unknown parameters by
> maximising the weighted log-likelihood.
>
>
>
> Can this be done in SPSS either through simply weighting the data (through
> Data>Weight cases) before running a binary logistic regression or do I need
> to use the Advanced Generalised Linear Model add-on and include the sample
> weight as a scale weight variable? Or do I need the add-on Complex Samples?
>
>
>
> Any help greatly appreciated.
>
>
>
> Many thanks
>
> Jamie Burnett
>
>
>
>
>
>
> ============================================================================
> ====================
> This e-mail and all attachments it may contain is confidential and intended
> solely for the use of the individual to whom it is addressed. Any views or
> opinions presented are solely those of the author and do not necessarily
> represent those of Ipsos MORI and its associated companies. If you are not
> the intended recipient, be advised that you have received this e-mail in
> error and that any use, dissemination, printing, forwarding or copying of
> this e-mail is strictly prohibited. Please contact the sender if you have
> received this e-mail in error.
>
> Market & Opinion Research International Ltd (trading as Ipsos MORI),
> Registered in England and Wales No. 948470, 79-81 Borough Road, London SE1
> 1FY, United Kingdom. VAT reg no. 443932151. Email: ukinfo@ipsos.com
>
> ============================================================================
> ====================
>
>
> *
> *   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/
>



-- 
Steven Samuels
sjsamuels@gmail.com
18 Cantine's Island
Saugerties NY 12477
USA
845-246-0774

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