PELVIS (version 1.2.1)

tenFoldCV.glm: Internal function for evaluating the performance of logistic regression models used in Bruzek's revised method (2019)

Description

Error rate, and rate of individuals remaining indeterminate, using 10-fold cross validation for a given logistic regression model in the context of Bruzek's revised method.

Usage

tenFoldCV.glm(dat.glm, mod, conf_level=0.95)

Arguments

dat.glm

A dataframe (with no missing values) on which to perform a 10-fold CV.

mod

GLM model to be evaluated.

conf_level

Threshold for sex determination, classically 0.95 following Bruzek's recommendations.

Value

A complete dataframe of results displayed through the R-Shiny application.

References

Santos, F., Guyomarc'h, P., Rmoutilova, R. and Bruzek, J. (2019) A method of sexing the human os coxae based on logistic regressions and Bruzek's nonmetric traits. American Journal of Physical Anthropology. doi: 10.1002/ajpa.23855