Skip to contents

'Explorable Multiverse' Data Analysis and Reports in R

Source: R/multiverse-package.R
multiverse-package.Rd

Implement 'multiverse' style analyses (Steegen S., Tuerlinckx F, Gelman A., Vanpaemal, W., 2016) doi:10.1177/1745691616658637 to show the robustness of statistical inference. 'Multiverse analysis' is a philosophy of statistical reporting where paper authors report the outcomes of many different statistical analyses in order to show how fragile or robust their findings are. The 'multiverse' package (Sarma A., Kale A., Moon M., Taback N., Chevalier F., Hullman J., Kay M., 2021) doi:10.31219/osf.io/yfbwm allows users to concisely and flexibly implement 'multiverse-style' analysis, which involve declaring alternate ways of performing an analysis step, in R and R Notebooks.

multiverse is an R package that aims to make it easy to declare 'multiverse-style' analysis in R and R notebooks. The 'multiverse' package allows users to concisely and flexibly declare alternate ways of performing an analysis step in order to show how fragile or robust their findings are.

Details

'Multiverse style' analyses (Steegen 2016) is intended to highlight the robustness of an analysis to arbitrary decisions that are present in any data analysis. Considering all possible combinations of reasonable decisions that can be made at each step of an analysis, 'multiverse style' analysis can surface whether an outcome is an artifact of a particular idiosyncratic combination of analysis choices, or if it is robust against such arbitrary choices.

However, current tools do not support declaring 'multiverse' analysis easily, requiring users to declare custom control flows and multiple nested 'if-else' blocks. The `multiverse` package aims to simplify the process of composing 'multiverse' analysis using a flexible and concise syntax.

To get started with the multiverse package please refer to vignette("branch")`, vignette("conditions") and vignette("multiverse-in-rmd"). For example implementations of analysis using the multiverse package, see the case studies vignette("durante-multiverse-analysis") and vignette("hurricane").

References

Steegen, Sara, Francis Tuerlinckx, Andrew Gelman, and Wolf Vanpaemel. (2016). Increasing transparency through a multiverse analysis. _Perspectives on Psychological Science_, 11(5), 702-712. doi:10.1177/1745691616658637 .

See also

Useful links:

Author

Maintainer: Abhraneel Sarma abhraneel@u.northwestern.edu

Authors:

Other contributors: