https://github.com/bethatkinson/rmed2019_surv
Wrangling survival data
https://github.com/bethatkinson/rmed2019_surv
Last synced: 10 months ago
JSON representation
Wrangling survival data
- Host: GitHub
- URL: https://github.com/bethatkinson/rmed2019_surv
- Owner: bethatkinson
- Created: 2019-08-22T20:43:00.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2019-09-12T20:54:28.000Z (almost 7 years ago)
- Last Synced: 2025-03-12T00:58:43.816Z (over 1 year ago)
- Language: HTML
- Homepage:
- Size: 875 KB
- Stars: 20
- Watchers: 2
- Forks: 7
- Open Issues: 0
-
Metadata Files:
- Readme: README.Rmd
Awesome Lists containing this project
README
---
title: "Wrangling Survival Data:
From Time-dependent Covariates to Multistate Endpoints"
output: github_document
---
### [R/Medicine 2019 conference](https://r-medicine.com/)
---
`r emo::ji("spiral_calendar")` September 12, 2019
`r emo::ji("clock8")` 01:00pm - 05:00pm
`r emo::ji("round_pushpin")` Boston, MA
`r emo::ji("white_check_mark")` [Register](https://cvent.me/en41V)
---
## Overview
In this four-hour workshop, I will review basic code for standard survival analysis, then work through examples for more complex scenarios. The majority of the focus will be on creating the correct dataset using tools available in the `survival` package. The final portion of the class will explore the most complex scenario - multistate data. The format will be a mix of lecture and hands-on exercises.
## Learning objectives
* Understand different survival data formats
* Create start/stop data using functions in the `survival` package
* Check data for errors
* Create multistate data and perform basic analysis
## Is this course for me?
This workshop is targeted at people who work in the medical field with survival data (or who anticipate needing to work with it). A very basic understanding of survival analysis will be helpful, though not required. A basic understanding of R is assumed.
* Have you had to manipulate data prior to running time-to-event analysis?
* Do you anticipate needing to run analyses with time-dependent covariates or multiple endpoints?
+ *Even better,* have you used the `survival` package?
* Have you used R with the RStudio Integrated Development Environment (IDE)? Are you familiar with the various “panes” and “tabs”? For instance, can you quickly find all objects in your current global environment, and can you send R code from a source file (.R, .Rmd) to the console?
## Schedule
| Time | Activity |
|:--------------|:----------------------------------------|
| 01:00 - 01:50 | Session 1 (basic analysis, motivation) |
| 01:50 - 02:00 | *Break* |
| 02:00 - 02:50 | Session 2 (intro to tools, examples) |
| 02:50 - 03:00 | *Break* |
| 03:00 - 03:50 | Session 3 (check data, common mistakes) |
| 03:50 - 04:00 | *Break* |
| 04:00 - 04:50 | Session 4 (multistate data) |
| 04:50 - 05:00 | Wrap-up / Overtime |
## Instructor
Beth Atkinson has been a statistician at Mayo Clinic for 29 years and has worked with Splus then R since starting at Mayo, including development work on the `rpart` package. She has worked extensively with Terry Therneau, author of the `survival` package, and has spent many hours wrangling data so that it is set up appropriately for time-to-event analyses. Currently she is working with Terry and Cindy Crowson on a book focused on time-to-event analyses, which will include an on-line compendium of detailed examples.
## Pre-work
```{r child = here::here('prework.Rmd')}
```
---
[](https://creativecommons.org/licenses/by/4.0/)
This work is licensed under a [Creative Commons Attribution 4.0
International License](https://creativecommons.org/licenses/by/4.0/).