Statistical tools and helper functions, including back-transformation of principal component (PCA) scores, creatiion of all possible formulae from a set of terms while respecting marginality and user-specified constraints, stratified sampling, and 2-D histograms.
You can install this package the usual way from CRAN
:
install.packages('statisfactory')
Alternatively, you can install the development version (plus dependency omnibus
) using:
remotes::install_github('adamlilith/omnibus')
remotes::install_github('adamlilith/statisfactory')
You may need to install package remotes
first.
makeFormulae()
: Make all possible formulaeuclid()
: Euclidean distancefuzzyJaccard()
: Fuzzy Jaccard index for non-binary valuesgeoMean()
: Geometric meaninvLogitAdj()
: Probit transform robust to 0's or 1'slogitAdj()
: Logit transform robust to 0's and 1'smmode()
: Modal valuepsum()
: Element-wise sum (like pmin()
and pmax()
)se()
: Standard error of the meanart()
: Aligned rank transform for using ANOVAs on rank datarankMulti()
: Rank values by multiple tie-breaking criteria*backTransPCA()
: "Back-transform" PCA scores to their original values
countConnected()
: Count number of contiguous "blocks" of cellssampleAcross()
: Permute values across two vectors or columns in two data frames or matricessampleStrat()
: Sample values stratified by one or more other variablesnagelR2()
: Nagelkerge's / Craig & Uhler's R2hist2d()
: Two-dimensional histogramhistOverlap()
: Histogram with overlapping or arbitrary binsAdam B. Smith
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.