Panel Data Parametric Survival Regression

[Sarina Hamidizade]

I would greatly appreciate if you could let me know how to choose among different parametric distributions including gama, Weibull, lognormal, loglogistic and etc for panel (time series cross sectional data) survival analysis or discrete time survival analysis in STATA 14.
Also, how to decide to use proportional hazard or accelerated failure time.


I read these materials but they are about continuous time survival analysis:

http://spia.uga.edu/faculty_pages/rb...rdOneNotes.pdf
http://spia.uga.edu/faculty_pages/rb...rdTwoNotes.pdf
http://spia.uga.edu/faculty_pages/rb...ThreeNotes.pdf

Then, I tried to calculate LR test, which is explained on page 22 of the second note, in order to calculate p_value. However, I am not sure or I don't know what to do. Besides, I just could test PH assumption for cox model, which is not a kind of panel data.

What's more, I couldn't do what is instructed on pages 24 and 25 of Oxford second note. In fact, when I use the "predict" command, it gives me an array of continuous values even though my dependent variable is discrete.

The following table is based on my estimations, which are attached in conjuction with my data.

Survival Distribution		AIC	BIC	Log-Likelihood	df
Exponential	Proportional Hazard	433.663	471.1031	-209.83151	7
Exponential	Accelerated Failure Time	433.663	471.1031	-209.83151	7
Lognormal	Proportional Hazard	377.6502	420.4389	-180.82508	8
Loglogistic	Proportional Hazard	377.874	420.6627	-180.93701	8
Gama	Proportional Hazard	cannot compute an improvement -- discontinuous region encountered
Weibull	Proportional Hazard	cannot compute an improvement -- discontinuous region encountered
Weibull	Accelerated Failure Time	205.8869	248.6756	-94.943472	8

Best regards,

[Phil Bromiley]

Please look at the FAQ on asking questions - providing Stata code using code delimiters, Stata output, and sample data using dataex will increase the chances you'll get a helpful answer. Many of us do not open word or excel files. Also, try to drop anything you don't need - the simpler the question and code, the easier for us to help you. For example, we don't need to know about models that did not estimate.

Try a new posting following the FAQ - you may get a better response. I don't do survival analysis so I can't speak to the substance of your question. In other models, you could use AIC and BIC and just pick the best one (I'm not sure about the sign here on AIC/BIC. You can easily check by running a useless model and calculating AIC.) They both appear to agree. But I have no idea if this is legitimate in survival analysis.

Also, do Google and Google Scholar searches on selecting distributions in survival analysis. There are certainly papers on this.