Re: st: Cox proportional hazard model

[Michael McCulloch <mm@pinestreetfoundation.org>]

Hello Nyasha, the answer to this question is in something you wrote  
earlier, "I do, not have data on employment/unemployment spells",   
which means that you can't do time-to-event analysis regardless of the  
method being considered.
Michael


On Aug 12, 2010, at 4:00 PM, Nyasha Tirivayi wrote:

> Dear Michael and Maarten
>
> I guess I got confused because I read the following manual from page  
> 13.
>
> http://rikain.com/Manuals/Social_+_Human_Rights/practical-guide-%20to-transition-data-analysis.pdf
>
> And in it the writer acknowledged they did not actual data on
> employment and unemployment spells. So they created spells where the
> first spell was from time AIDS medicaiton began to first survey.
> Second spell was time from first survey to second survey.
>
> If you have time, please kindly browse through the manual and kindly
> confirm if it is in error!
>
> Regards
>
> Nyasha Tirivayi
> Maastricht University
>
> On Fri, Aug 13, 2010 at 12:39 AM, Nyasha Tirivayi  
> <ntirivayi@gmail.com> wrote:
> > Dear Michael
> >
> > Thanks for the suggestion. I will change my approach.
> >
> > Nyasha Tirivayi
> > Maastricht University
> >
> > On Fri, Aug 13, 2010 at 12:34 AM, Michael McCulloch
> > <mm@pinestreetfoundation.org> wrote:
> > > Nyasha, Maarten explained very well the nature of what data you'd  
> > > need to to
> > > time-to-employment analysis, which it turns out you can't measure  
> > > in the
> > > context of your current project. This means you can't do survival  
> > > analysis
> > > like the Cox method.
> > >
> > > Another alternative analysis strategy is to instead study the  
> > > likelihood of
> > > a person getting a job within some pre-determined time frame,  
> > > using logistic
> > > regression. The dependent variable then is getting employment (yes/ 
> > > no), and
> > > the predictor variables are things like
> > >                food aid
> > >                use of AIDS medication
> > >                and other characteristics of the person or household
> > > Michael
> > >
> > >
> > > On Aug 12, 2010, at 3:06 PM, Nyasha Tirivayi wrote:
> > >
> > > > Dear Maarten
> > > >
> > > > Thanks for clarifying. Now I understand. I had this wrong. In that
> > > > case I think I need to ask for ideas for alternative method since  
> > > > I do
> > > > not have data on employment/unemployment spells.
> > > >
> > > > I have realized that I have 2 period panel data on employment  
> > > > status.
> > > > So I have employment1 and employment2. I am interested in seeing  
> > > > the
> > > > effects of AIDS medication  on transitions from one state to  
> > > > another.
> > > >
> > > > I also have another treatment variable- food aid. So you have some
> > > > households where a patient is on AIDS medication and household
> > > > receives food assistance. If I choose instead to look at the  
> > > > effect of
> > > > food assistance ( meaning all households in analysis will now  
> > > > have a
> > > > patient on AIDS medication), what kind of transition analysis can I
> > > > do.. or maybe I should simply carry out multiple regression  
> > > > analysis
> > > > or propensity score matching?
> > > >
> > > > Kindly advise
> > > >
> > > > Regards
> > > >
> > > > Nyasha Tirivayi
> > > > Maastricht University
> > > >
> > > > On Thu, Aug 12, 2010 at 11:56 PM, Maarten buis <maartenbuis@yahoo.co.uk 
> > > > >
> > > > wrote:
> > > > > --- On Thu, 12/8/10, Nyasha Tirivayi wrote:
> > > > > > So the duration of the AIDS medication taken by the patient
> > > > > > is the time variable, and getting employed/returning to work
> > > > > > is the event
> > > > >
> > > > > The time variable and the event are not two separate concepts,
> > > > > the duration is the time till the event occurs. When you look
> > > > > at time till employment, then starting AIDS medication is not
> > > > > the beginning of a spell, leaving the labor market, leaving
> > > > > school, becoming unemployed, are the beginning of the spell.
> > > > > Whether or not the patient takes AIDS medication is your
> > > > > explanatory variable, not your explained variable.
> > > > >
> > > > > Hope this helps,
> > > > > Maarten
> > > > >
> > > > > --------------------------
> > > > > Maarten L. Buis
> > > > > Institut fuer Soziologie
> > > > > Universitaet Tuebingen
> > > > > Wilhelmstrasse 36
> > > > > 72074 Tuebingen
> > > > > Germany
> > > > >
> > > > > http://www.maartenbuis.nl
> > > > > --------------------------
> > > > >
> > > > >
> > > > >
> > > > >
> > > > > *
> > > > > *   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/
> > >
> > >
> > > Best wishes,
> > >
> > > Michael McCulloch, LAc MPH PhD
> > > Pine Street Foundation
> > > 124 Pine Street
> > > San Anselmo, CA 94960-2674
> > > tel:    415-407-1357
> > > fax:    206-338-2391
> > >
> > > *
> > > *   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/


Best wishes,

Michael McCulloch, LAc MPH PhD
Pine Street Foundation
124 Pine Street
San Anselmo, CA 94960-2674
tel:	415-407-1357
fax: 	206-338-2391

*
*   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/