Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# Re: st: Cox proportional hazard model

 From Nyasha Tirivayi To statalist@hsphsun2.harvard.edu Subject Re: st: Cox proportional hazard model Date Thu, 12 Aug 2010 23:40:33 +0200

```Dear Maarten

To clarify.. the hypothesis is duration of AIDS medication increases
the probability of the patient returning to work, with positive
externalities on non-patient family members, who now shift from caring
for the patient to work.

So the duration of the AIDS medication taken by the patient is the
time variable, and getting employed/returning to work is the event

Is there any way possible or running cox regressions for the
non-patient family members too?

Nyasha Tirivayi
Maastricht University

On Thu, Aug 12, 2010 at 11:24 PM, Maarten buis <maartenbuis@yahoo.co.uk> wrote:
> --- On Thu, 12/8/10, Nyasha Tirivayi wrote:
>> I would like to model  intrahousehold transitions from
>> unemployment to employment. In the household are:
>> 1. A patient receiving AIDS medication
>> 2. And non-patient household members living together with
>> the patient.
>>
>> I am thinking of applying the cox proportional hazard
>> model, where duration of AIDS medication is the time
>> variable. How can  I analyse the transitions by other
>> non-patient family members, when they do not receive
>> AIDS medication? Do I assign the time variable to
>> the patient and his/her non-patient family members?
>
> You need to define what it is that you are interested in:
> is it 1) how long do people take their medicine, or 2) how
> long till people find a job?
>
> If 1) then it only makes sense to look at the patients, they
> are the ones that need to take the medicine not the family
> members. Characteristics of the family members can enter into
> your model as explanatory variables.
>
> if 2) you want to start time with the moment they become
> available for the labor market (i.e. leave school or loose
> their job). The time that a family member takes the medicine
> can enter into your model as an explanatory variable, or
> alternatively a time varying explanatory variable indicating
> whether or not someone in the family receives medication.
>
> 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/
```