fragility

A collection of user-friendly functions for assessing and visualizing fragility of individual studies (Walsh et al., 2014 doi:10.1016/j.jclinepi.2013.10.019; Lin, 2021 doi:10.1111/jep.13428), conventional pairwise meta-analyses (Atal et al., 2019 doi:10.1016/j.jclinepi.2019.03.012), and network meta-analyses of multiple treatments with binary outcomes (Xing et al., 2020 doi:10.1016/j.jclinepi.2020.07.003). The included functions are designed to: 1) calculate the fragility index (i.e., the minimal event status modifications that can alter the significance or non-significance of the original result) and fragility quotient (i.e., fragility index divided by sample size) at a specific significance level; 2) give the cases of event status modifications for altering the result's significance or non-significance and visualize these cases; 3) visualize the trend of statistical significance as event status is modified; 4) efficiently derive fragility indexes and fragility quotients at multiple significance levels, and visualize the relationship between these fragility measures against the significance levels; and 5) calculate fragility indexes and fragility quotients of multiple datasets (e.g., a collection of clinical trials or meta-analyses) and produce plots of their overall distributions. The outputs from these functions may inform the robustness of clinical results in terms of statistical significance and aid the interpretation of fragility measures. The usage of this package is illustrated in Lin et al. (2023 doi:10.1016/j.ajog.2022.08.053) and detailed in Lin and Chu (2022 doi:10.1371/journal.pone.0268754).

Examples that run

90%

Documented parameters

100%

Return-value docs

100%

References docs

84%

Nothing depends on this yet.

8 releases. Pick two to compare their code metrics. R releases are shown for context.

First published

2020-04-07

Total releases

8 / 6 yrs

License

GPL (>= 2) OSI

Minimum R

≥ 3.5.0

Bundled data

26 KB / 4 files

Download size

82 KB

Installed size

not tracked yet

With dependencies

not tracked yet

Cite this package

Run in R for the authors' preferred citation:

This is what citation() produces when a package has no citation file of its own. If it prints something else, use that.

Cite the R Observatory

For a number measured here: a download total, a coverage figure, an archival date.

From data release v2026-08-22, which the citation names so these numbers can be found later. More on citing and the projects behind them.