How to plot survival estimates from the model / excess hazard ratio

Cruise — Tue, 11 Jun 2019 21:29:55 GMT

Hello folks,

I'm trying to reproduce the graph below (Woods et al.,2012) attached to this post. And I read and produced the cumulative relative risk tables following Dr. Dickman's resources for http://www.pauldickman.com/survival/sas/relative_survival_using_sas.pdf. Now I'm getting into the Chapter: Modelling relative survival hoping that I'm pursuing the right direction to find a way to reproduce the graph.

My question is:

1. Do you recognize this graph as a SAS output? or you think that authors might have created this plot from any output estimates data?

2. Does proc phreg produce "excess hazard ratio" as used on the y-axis int he plot below over a survival time in weeks?

I know these authors mostly use stata software. But I can't imagine that SAS wouldn't have a way to produce something close. I keep reading Dr. Dickman's manual. In the meantime, I greatly appreciate to hear from your educated suggestions as to how I should approach to produce a similar plot like below. I use comparable data to that of Woods et al., and datasets that Dr. Dickman used in his tutorial.

Re: How to plot survival estimates from the model / excess hazard ratio

Cruise — Tue, 11 Jun 2019 21:39:55 GMT

It appears that Dickman suggested to use poisson regression to model and output relative excess risks. Please let me know if this might be the way to obtain estimates to graph in SAS. I'll keep testing in the meantime. Thanks.

proc genmod data=&grouped(where=(fu le 5)) order=formatted;
title2 'Poisson error model fitted to collapsed data';
title3 'Main effects model (follow-up, sex, age, and dgnyear)';
fwdlink link = log(_MEAN_-d_star);
invlink ilink= exp(_XBETA_)+d_star;
class fu sex age yydx;
model d = fu sex yydx age / error=poisson offset=ln_y type3;
format fu fu. age age. yydx yydx.;
run;

topic Re: How to plot survival estimates from the model / excess hazard ratio in Statistical Procedures

How to plot survival estimates from the model / excess hazard ratio

Re: How to plot survival estimates from the model / excess hazard ratio