Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: Discrete time hazard model-interval censored


From   Steve Samuels <sjsamuels@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Discrete time hazard model-interval censored
Date   Fri, 27 Aug 2010 15:57:23 -0400

It appears that you've asked different versions of this question
before.  I'm no better equipped to answer it then the original
responders.  Take a look at this thread on estimating "average
treatment effects" and Austin Nichol's references therein:
http://www.stata.com/statalist/archive/2010-08/msg01268.html.  I don't
know what do if employed status at the start is endogenous.

Best wishes,

Steve

On Fri, Aug 27, 2010 at 1:49 PM, Nyasha Tirivayi <ntirivayi@gmail.com> wrote:
> Dear Steve
>
> Thanks for your response. If i use a logistic regression for
> transition to employment, do I follow the example below:
>
>  logistic employment beneficiary age gender  if LagEmployment==0
>
> where LagEmployment==0 is previous state of unemployment and
> beneficiary indicates participating in a social program.  Do I need to
> xtset the data?  And how do I correct for endogeneity of beneficiary
> and LagEmployment?
>
> May you kindly advise
>
> Regards
>
> Nyasha Tirivayi
> PhD Researcher
> Maastricht University
> Netherlands
>
> On Fri, Aug 27, 2010 at 7:37 PM, Steve Samuels <sjsamuels@gmail.com> wrote:
>> --
>>
>> With only one interval, a discrete hazard model is _not_ suitable.
>> Use a -logistic- (or -cloglog-) model instead.
>>
>> Steve
>>
>> Steven J. Samuels
>> sjsamuels@gmail.com
>> 18 Cantine's Island
>> Saugerties NY 12477
>> USA
>> Voice: 845-246-0774
>> Fax:    206-202-4783
>>
>> On Fri, Aug 27, 2010 at 1:26 PM, Nyasha Tirivayi <ntirivayi@gmail.com> wrote:
>>> Dear All
>>>
>>> I have a dataset on labour force participation in an African country.
>>> There are two waves of interviews, January 2009 and August 2009. I am
>>> interested in looking at the effects of a social program on the
>>> transitions into employment. The survey asked questions like, "are you
>>> empoyed at the moment" .  I am especially interested in those who at
>>> first interview had were not employed. However ,we do not know exactly
>>> the date when they do  get employed, we only have a response at second
>>> interview whether they are employed or not.
>>>
>>> Could anyone advise me if a discrete time hazard model is suitable?
>>> What stata methods do I use for the interval censoring? And how do I
>>> correct for the selection bias of the social program?
>>>
>>> May you kindly advise
>>>
>>> Regards
>>>
>>> Nyasha Tirivayi
>>> PhD researcher
>>> Maastricht Graduate School of Governance
>>> Maastricht University
>>> Netherlands
>>> *
>>> *   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/
>

*
*   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   |   Site index