# Propagating uncertainty between models in EpiNow2

**URL:** <https://community.epinowcast.org/t/propagating-uncertainty-between-models-in-epinow2/119>\
**Category:** Other Resources\
**Tags:** application\
**Created:** [8 February 2023 20:56 UTC](https://community.epinowcast.org/t/propagating-uncertainty-between-models-in-epinow2/119 "2023-02-08T20:56:33Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![samabbott](https://dub1.discourse-cdn.com/flex005/user_avatar/community.epinowcast.org/samabbott/32/5_2.png) [@samabbott](https://community.epinowcast.org/u/samabbott)\
**Post date:** [8 February 2023 20:56 UTC](https://community.epinowcast.org/t/propagating-uncertainty-between-models-in-epinow2/119/1 "2023-02-08T20:56:33Z")

</div>

Interesting discussion happening in the `EpiNow2` discussion forum about how to pass nowcasts into a modelling pipeline for Rt estimation and short-term forecasting.

Useful to think about the parts of the problem `epinowcast` covers better but doesn’t in reality as still complex to us, the parts of the problem that could be better served by other approaches, and more generally how estimating the various delays and quantities of interest.

> **[Propagating uncertainty from estimate\_truncation() · Discussion #365 ·...](https://github.com/epiforecasts/EpiNow2/discussions/365#discussioncomment-4908837)**
>
> Hi! I'm interested in understanding how to propagate the uncertainty associated with data truncation into R estimates and forecasts. According to the Estimate Truncation of Observed Data page, ...

---

<div class="post-metadata">

**Author:** ![samabbott](https://dub1.discourse-cdn.com/flex005/user_avatar/community.epinowcast.org/samabbott/32/5_2.png) [@samabbott](https://community.epinowcast.org/u/samabbott)\
**Post date:** [23 February 2023 16:18 UTC](https://community.epinowcast.org/t/propagating-uncertainty-between-models-in-epinow2/119/2 "2023-02-23T16:18:21Z")

</div>

This issue relates to the talk ([Community Seminar 2023-03-01 - Adrian Lison - Generative modeling approaches to nowcasting with incomplete line list data](https://community.epinowcast.org/t/community-seminar-2023-03-01-adrian-lison-generative-modeling-approaches-to-nowcasting-with-incomplete-line-list-data/122)) @adrianlison will be giving at the next Seminar.

He has done quite a lot of work looking at the impact of passing estimates between models (as done in `EpiNow2` vs joint modelling as done in his work and optionally in `epinowcast`.