R Users meeting: computationally reproducible research in R

You are here

In case you want to prepare yourself, you can download the .R and .Rmd files from https://github.com/wageningen/RUsers/tree/master/2018_03_14_computationally_reproducible_research , and make sure you have installed R-packages rmarkdown and knitr.

Level: medium in terms of R, but interesting for everybody

Wednesday March 14, 2018, 16:00, in C106 (Forum Building 1st floor, Wageningen campus; https://ssc.wur.nl/Schedule/2016/Room/C0106 ).

(1) https://englianhu.files.wordpress.com/2016/01/reproducible-research-with-r-and-studio-2nd-edition.pdf
(2) https://www.practicereproducibleresearch.org/


‘The origins of the scientific method, epitomized by Sir Francis Bacon's work in the early 1600s, amount to insistence on direct evidence. This is reflected in the motto of The Royal Society, founded in 1660: Nullius in verba, which roughly means "take nobody's word for it" (...) Over time, Robert Boyle and others developed conventions for documenting experiments in sufficient detail, using prose and illustrations of the apparatus and experimental set up, that the reader could imagine being in the room, observing the experiment and its outcome. (...)
Such observability -visibility into the process of generating results- provides the evidence that the scientific claim is true. It helps ensure we are not fooling ourselves or each other, accidentally or deliberately. (...)
However, science has largely abandoned that transparency and observability, resulting in a devolution from show me to trust me. Scientific publications simply do not contain the information needed to know what was done, nor to try to replicate the experiment and data analysis. (...)
Working reproducibly makes it easier to get correct results and enables others to check whether results are correct. (...).’  From: Kitzes et al., 2017; bold face by the R user team.

For more information: see https://github.com/wageningen/RUsers#rusers.