tidylo: Weighted Tidy Log Odds Ratio

How can we measure how the usage or frequency of some feature, such as words, differs across some group or set, such as documents? One option is to use the log odds ratio, but the log odds ratio alone does not account for sampling variability; we haven't counted every feature the same number of times so how do we know which differences are meaningful? Enter the weighted log odds, which 'tidylo' provides an implementation for, using tidy data principles. In particular, here we use the method outlined in Monroe, Colaresi, and Quinn (2008) <doi:10.1093/pan/mpn018> to weight the log odds ratio by a prior. By default, the prior is estimated from the data itself, an empirical Bayes approach, but an uninformative prior is also available.

Version: 0.2.0
Imports: dplyr, rlang
Suggests: covr, ggplot2, janeaustenr, knitr, rmarkdown, stringr, testthat (≥ 2.1.0), tidytext
Published: 2022-03-22
Author: Tyler Schnoebelen [aut], Julia Silge ORCID iD [aut, cre, cph], Alex Hayes ORCID iD [aut]
Maintainer: Julia Silge <julia.silge at gmail.com>
BugReports: https://github.com/juliasilge/tidylo/issues
License: MIT + file LICENSE
URL: https://juliasilge.github.io/tidylo/, https://github.com/juliasilge/tidylo
NeedsCompilation: no
Materials: README NEWS
CRAN checks: tidylo results

Documentation:

Reference manual: tidylo.pdf
Vignettes: Tidy Log Odds

Downloads:

Package source: tidylo_0.2.0.tar.gz
Windows binaries: r-devel: tidylo_0.2.0.zip, r-release: tidylo_0.2.0.zip, r-oldrel: tidylo_0.2.0.zip
macOS binaries: r-release (arm64): tidylo_0.2.0.tgz, r-oldrel (arm64): tidylo_0.2.0.tgz, r-release (x86_64): tidylo_0.2.0.tgz
Old sources: tidylo archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=tidylo to link to this page.