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: choosing parametric model


From   Glenn Hoetker <[email protected]>
To   "[email protected]" <[email protected]>
Subject   Re: st: choosing parametric model
Date   Fri, 1 Jul 2011 09:19:38 -0700

It is also worth asking oneself how much the exact underlying rate matters. Sometimes it is of substantive interest.   Often, however, it isn't.  If similar distributions (e.g., one that increases monotonically and one that increases, but then turns down at a duration where there are few observations left) give substantively similar results, how important is it to show which is "right"? It may often be the case that showing your results are robust to multiple distributions is more important than whether one distribution has an AIC that is .5 less than another distribution.  

Of course, if the shape of the distribution is of substantive interest, or if results are not substantively similar across distributions, identifying the best fitting underlying distribution is more important.

G.

Sent from my iPad

On Jul 1, 2011, at 12:57 AM, "Maarten Buis" <[email protected]> wrote:

> On Fri, Jul 1, 2011 at 6:51 AM, Yusvita Triwiadhian S. wrote:
>> Parametric models in survival specifies a particular shape for the
>> hazard rate i.e the time dependency, maybe exponential,weibull, etc..
>> How do we choose the correct parametric model to assume about the
>> shape of the time dependency?
>> can I use AIC by comparing the AIC scores for different parametric
>> models and then the smallest is better? if "yes", The AIC scores that
>> is used when there are no covariates or when there are covariates?
>> which one is better?
> 
> 

*
*   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