# Survival models in rstanarm

**URL:** <https://discourse.mc-stan.org/t/survival-models-in-rstanarm/3998>\
**Category:** Developers\
**Created:** [April 26, 2018, 5:13am UTC](https://discourse.mc-stan.org/t/survival-models-in-rstanarm/3998 "2018-04-26T05:13:23Z")\
**Posts on this page:** 1\
**Showing post:** 64

<div class="post-metadata">

**Author:** ![lcomm](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.mc-stan.org/lcomm/32/1238_2.png) [@lcomm](https://discourse.mc-stan.org/u/lcomm)\
**Post date:** [November 14, 2018, 8:45pm UTC](https://discourse.mc-stan.org/t/survival-models-in-rstanarm/3998/64 "2018-11-14T20:45:07Z")

</div>

I wish I had seen this earlier. I just spent this afternoon implementing a posterior predictive checks based on Kaplan-Meier survival estimates and it looks like you’ve already done that.

Isn’t this just generating from a truncated event time distribution where the truncation takes the form of an upper bound? Is that what you mean by _conditioned_: you are conditioning on getting to observe the event, so you are forcing it to be less than T^\*?

---

_[View the full topic](https://discourse.mc-stan.org/t/survival-models-in-rstanarm/3998)._