Statalist


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

st: tobit with "svy" and "mim"


From   Ryan Wells <[email protected]>
To   [email protected]
Subject   st: tobit with "svy" and "mim"
Date   Sun, 31 Jan 2010 09:26:54 -0800 (PST)

I am attempting to run a tobit model...but the data I am using are both derived from a complex survey design and also have been multiply imputed using "ice".
When I run the syntax I thought would be appropriate (below), I get the following error:

. mim,storebv:svy:tobit amount_saved par_exp4 par_aspr4 par_bach grandpar_bach age_parent income_ten_thou numkids ///
> female asian hispanic black par_nativeng parttime nowork catholic private ///
> par_involv heldback ztest_score daycare nursery headstart kinder, ul ll

command tobit not recognised by mim; try specifying category option


heeding this warning, I enter the following syntax with the category(fit) option, and receive a different message:

. mim,storebv category(fit):svy:tobit amount_saved par_exp4 par_aspr4 par_bach grandpar_bach age_parent income_ten_thou nu
> mkids ///
> female asian hispanic black par_nativeng parttime nowork catholic private ///
> par_involv heldback ztest_score daycare nursery headstart kinder, ul ll

-> _mj==1
-> svy: tobit amount_saved par_exp4 par_aspr4 par_bach grandpar_bach age_parent income_ten_thou numkids female asian hispa
> nic black par_nativeng parttime nowork catholic private par_involv heldback ztest_score daycare nursery headstart kinder
> , ul ll
(running tobit on estimation sample)
iweight not allowed
an error occurred when svy executed tobit

In fact, iweight is allowed with tobit, but something in my code is clearly not liked by Stata, leading to this message. It also appears that it may be limiting itself to only one of the multiply-imputed datasets when I use "category(fit)"? ("_mj==1") I could use just of of the imputed datasets (which does work fine and gives results) therefore, not having to use the "mim" command, but then I lose the power of multiple imputation...

Any suggestions how to use all three ( 1) svy 2) mim 3) tobit ) in one command? or how to get accurate results without doing this?


      
*
*   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