Bookmark and Share

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: Bootstrapping in svy with vce(linearized)


From   Rini Rao <[email protected]>
To   [email protected]
Subject   Re: st: Bootstrapping in svy with vce(linearized)
Date   Thu, 12 Apr 2012 20:00:08 -0400

Dear Stas & Steve,

You were right - Thank you for your prompt inputs and insight ! Your
instructions were helpful and the analysis is on track. Much
appreciated.

Rini.


On Thu, Apr 12, 2012 at 6:03 PM, Steve Samuels <[email protected]> wrote:
>
> Rini Rao:
>
> Look at the results of -svy: regress- again; they state the reason for the missing standard errors; it has little to do with sample size. Also re-read the -help- for -svyset- about the consequences of choosing the singleunit(missing) option. Choose a different one; I suggest "centered" as the most conservative.
>
> And, as Stas pointed out, you must incorporate your -if- clause into the subpop() definition.
>
> Steve
> [email protected]
>
> On Apr 12, 2012, at 2:18 PM, Rini Rao wrote:
>
> Hello fellow Stata folks,
>
> I am using the NHANES data with the svy command and vce(linearized).
> For my analysis, I have created subgroups based on certain parameters
> for complete data. e.g (s_white_1840)
>
> For certain subgroups, I have ended up with very small sample sizes
> (e.g. n=353) and in some cases I only get a model co-efficient
> estimate without accompanying standard errors.
> e.g.
>
> . svyset psu [pweight=wtsaf], strata(strata) vce(linearized) singleunit(missing)
>
>
> . xi: svy, sub(s_gaby_diab_1318): regress egfr abdobes if homa_1318<4 & htn==0
> (running regress on estimation sample)
>
> Survey: Linear regression
>
> Number of strata   =        74                     Number of obs
> =      1544
> Number of PSUs     =       148                  Population size    = 6726762.5
>
> Subpop. no. of obs =      1544
>
> Subpop. size       = 6726762.5
>
> Design df          =        74
>                                                                 F(
> 0,     74)    =         .
>                                                                 Prob
>> F           =         .
>
> R-squared          =    0.0029
>
> ------------------------------------------------------------------------------
>              |                Linearized
>       egfr |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
> -------------+----------------------------------------------------------------
> abdobes |   3.147383          .        .       .            .           .
>   _cons |   92.33331          .        .       .            .           .
> ------------------------------------------------------------------------------
> Note: missing standard errors because of stratum with single sampling unit.
>
>
> Now, how can I obtain unbiased S.E. and confidence intervals for this
> estimate. Is it acceptable to run a bootstrap using this command? (I
> get a reasonable output using this command but I don't know if it
> makes sense to use this).
>
> bootstrap _b _se if homa_1318<4 & fabg<100 & htn==0, reps(1000)
> strata(s_gaby_diab_1318) seed(89) : regress egfr abdobes
>
> Harini Sarathy.
> *
> *   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index