# Forest plot for Multi-state cox model

**URL:** <https://discourse.datamethods.org/t/forest-plot-for-multi-state-cox-model/4560>\
**Category:** general\
**Created:** [June 23, 2021, 4:07pm UTC](https://discourse.datamethods.org/t/forest-plot-for-multi-state-cox-model/4560 "2021-06-23T16:07:52Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![KAMRAN\_KHAN](https://discourse.datamethods.org/letter_avatar_proxy/v4/letter/k/51bf81/32.png) [@KAMRAN\_KHAN](https://discourse.datamethods.org/u/KAMRAN_KHAN)\
**Post date:** [June 23, 2021, 4:07pm UTC](https://discourse.datamethods.org/t/forest-plot-for-multi-state-cox-model/4560/1 "2021-06-23T16:07:52Z")

</div>

Does anyone know how to create a HR forest plot for a multi-state model in survival package?

In the multi-state model we have data in the form of counting process just like when we have time-varying covariates in a Cox regression model. We have a coxph(Surv(time1, time2, event) ~ 1) setup.

I would appreciate any help.

---

<div class="post-metadata">

**Author:** ![pmbrown](https://discourse.datamethods.org/user_avatar/discourse.datamethods.org/pmbrown/32/1382_2.png) [@pmbrown](https://discourse.datamethods.org/u/pmbrown)\
**Post date:** [June 25, 2021, 6:12am UTC](https://discourse.datamethods.org/t/forest-plot-for-multi-state-cox-model/4560/2 "2021-06-25T06:12:20Z")

</div>

it’s a good Q. I’ve never implemented a multi state model and wonder how the results are typically summarised

---

<div class="post-metadata">

**Author:** ![f2harrell](https://discourse.datamethods.org/user_avatar/discourse.datamethods.org/f2harrell/32/165_2.png) [@f2harrell](https://discourse.datamethods.org/u/f2harrell)\
**Post date:** [June 25, 2021, 3:53pm UTC](https://discourse.datamethods.org/t/forest-plot-for-multi-state-cox-model/4560/3 "2021-06-25T15:53:03Z")

</div>

See some examples at [https://hbiostat.org/proj/covid19](https://hbiostat.org/proj/covid19) especially the VIOLET and ORCHID analyses.