In DInfanger/pvaluefunctions: Creates and Plots P-Value Functions, S-Value Functions, Confidence Distributions and Confidence Densities

knitr::opts_chunk$set(
  collapse = TRUE, 
  comment = "#>",
  fig.path = "man/figures/README-"
)

P-value functions

Accompanying paper

We published an accompanying paper to illustrate the use of p-value functions:

Infanger D, Schmidt-Trucksäss A. (2019): P value functions: An underused method to present research results and to promote quantitative reasoning. Statistics in Medicine. 38: 4189-4197. doi: 10.1002/sim.8293.

Recreation of the figures in the paper

The code and instructions to reproduce all graphics in our paper can be found in the following GitHub repository: https://github.com/DInfanger/pvalue_functions

Overview

This is the repository for the R-package pvaluefunctions. The package contains R functions to create graphics of p-value functions, confidence distributions, confidence densities, or the Surprisal value (S-value) (Greenland 2019).

Installation

You can install the package directly from CRAN by typing install.packages("pvaluefunctions"). After installation, load it in R using library(pvaluefunctions).

library(devtools)

# Load main function
source_url("https://raw.githubusercontent.com/DInfanger/pvaluefunctions/master/R/confidence_distributions.R")

Dependencies

The function depends on the following R packages, which need to be installed beforehand:

Use the command install.packages(c("ggplot2", "scales", "zipfR", "pracma", "gsl")) in R to install those packages.

Examples

For more examples and code, see the vignette.

# devtools::install_github("DInfanger/pvaluefunctions")

library(pvaluefunctions)

#-----------------------------------------------------------------------------
# Create p-value function
#-----------------------------------------------------------------------------

res <- conf_dist(
  estimate = c(-1.58)
  , df = c(17.77647)
  , tstat = c(-1.860813)
  , type = "ttest"
  , plot_type = "p_val"
  , n_values = 1e4L
  # , est_names = c("")
  , conf_level = c(0.95, 0.90, 0.80)
  , null_values = c(0)
  , trans = "identity"
  , alternative = "two_sided"
  , log_yaxis = FALSE
  , cut_logyaxis = 0.05
  , xlab = "Mean difference (group 1 - group 2)"
  , together = FALSE
  , plot_p_limit = 1 - 0.999
  , plot_counternull = TRUE
  , inverted = FALSE
  , title = expression(italic(P)~"-value function for a"~italic(t)~"-test")
  , plot = TRUE
)

#-----------------------------------------------------------------------------
# Create s-value function
#-----------------------------------------------------------------------------

res <- conf_dist(
  estimate = c(-1.58)
  , df = c(17.77647)
  , tstat = c(-1.860813)
  , type = "ttest"
  , plot_type = "s_val"
  , n_values = 1e4L
  # , est_names = c("")
  , conf_level = c(0.95, 0.90, 0.80)
  , null_values = c(0)
  , trans = "identity"
  , alternative = "two_sided"
  , log_yaxis = FALSE
  , cut_logyaxis = 0.05
  , xlab = "Mean difference (group 1 - group 2)"
  , together = FALSE
  , col = "#C977A2"
  , plot_p_limit = 1 - 0.999
  , plot_counternull = TRUE
  , inverted = FALSE
  , title = expression(italic(S)~"-value function for a"~italic(t)~"-test")
)

rse_fun <- function(x){
  100*(1 - exp(x))
}

rse_fun_inv <- function(x){
  log(1 - (x/100))
}

res <- conf_dist(
  estimate = c(log(0.72))
  , stderr = (0.187618)
  , type = "coxreg"
  , plot_type = "p_val"
  , n_values = 1e4L
  , est_names = c("RSE")
  , conf_level = c(0.95, 0.8, 0.5)
  , null_values = rse_fun_inv(c(0))
  , trans = "rse_fun"
  , alternative = "two_sided"
  , log_yaxis = FALSE
  , cut_logyaxis = 0.05
  , xlab = "Relative survival effect (1 - HR%)"
  , xlim = rse_fun_inv(c(-30, 60))
  , together = FALSE
  , plot_p_limit = 1 - 0.999
  , plot_counternull = TRUE
  , inverted = TRUE
  , title = "Figure 1 in Bender et al. (2005)"
)

References

Bender R, Berg G, Zeeb H. (2005): Tutorial: using confidence curves in medical research. Biom J. 47(2): 237-47.

Berrar D (2017): Confidence Curves: an alternative to null hypothesis significance testing for the comparison of classifiers. Mach Learn. 106:911-949.

Fraser D. A. S. (2019): The p-value function and statistical inference. Am Stat. 73:sup1, 135-147.

Greenland S (2019): Valid P-Values Behave Exactly as They Should: Some Misleading Criticisms of P-Values and Their Resolution with S-Values. Am Stat. 73sup1, 106-114.

Infanger D, Schmidt-Trucksäss A. (2019): P value functions: An underused method to present research results and to promote quantitative reasoning. Stat Med. 38, 4189-4197. doi: 10.1002/sim.8293.

Poole C. (1987a): Beyond the confidence interval. Am J Public Health. 77(2): 195-9.

Poole C. (1987b): Confidence intervals exclude nothing. Am J Public Health. 77(4): 492-3.

Rafi Z, Greenland S. (2020): Semantic and cognitive tools to aid statistical science: replace confidence and significance by compatibility and surprise. BMC Med Res Methodol. 20, 244. doi: 10.1186/s12874-020-01105-9.

Rosenthal R, Rubin DB. (1994): The counternull value of an effect size: A new statistic. Psychol Sci. 5(6): 329-34.

Schweder T, Hjort NL. (2016): Confidence, likelihood, probability: statistical inference with confidence distributions. New York, NY: Cambridge University Press.

Xie M, Singh K, Strawderman WE. (2011): Confidence Distributions and a Unifying Framework for Meta-Analysis. J Am Stat Assoc. 106(493): 320-33. doi: 10.1198/jasa.2011.tm09803.

Xie Mg, Singh K. (2013): Confidence distribution, the frequentist distribution estimator of a parameter: A review. Internat Statist Rev. 81(1): 3-39.