New version of {boot.pval} on CRAN

R
Statistics
Author

Måns Thulin

Published

January 16, 2025

A new version of the boot.pval package is now available on CRAN. It can be used to compute bootstrap p-values and confidence intervals for regression coefficients with a single line of code. It works for linear models, GLMs, Cox regression, mixed models, and more.

News in version 0.6

  • Now works also when there’s missing data (previously, an error inherited from car::Boot would appear if the data frame contained missing values).
  • Improved presentation of low p-values.
  • Added support for BCa intervals.
  • A vignette has been added.

A short example

After fitting a regression model, confidence intervals for \(\beta_i\) and bootstrap p-values for the hypotheses \(H_0: \beta_i=0\) can be obtained with a single line of code:

library(boot.pval)
model <- lm(mpg ~ hp + vs, data = mtcars)

boot_summary(model)
               Estimate Lower.bound Upper.bound p.value
(Intercept) 26.96300111 21.06466359 32.43154604  <0.001
hp          -0.05453412 -0.08042437 -0.02384551  <0.001
vs           2.57622314 -1.09704998  6.61474042   0.176

And publication-ready tables in two lines:

boot_summary(model) |>
  summary_to_gt()
Estimate 95 % CI p-value
(Intercept) 26.963 (21.065, 32.432) <0.001
hp −0.055 (−0.080, −0.024) <0.001
vs 2.576 (−1.097, 6.615) 0.176