In hughjonesd/truelies: Bayesian Methods to Estimate the Proportion of Liars in Coin Flip Experiments

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)

truelies

truelies implements Bayesian methods, described in Hugh-Jones (2019), for estimating the proportion of liars in coinflip-style experiments, where subjects report a random outcome and are paid for reporting a "good" outcome.

For R source for the original paper, see https://github.com/hughjonesd/GSV-comment.

Installation

# stable version on CRAN
install.packages("truelies")

# latest version from github
remotes::install_github("hughjonesd/truelies")

Example

If you have 33 out of 50 reports of heads in a coin flip experiment:

library(truelies)
d1 <- update_prior(heads = 33, N = 50, P = 0.5, prior = dunif)
plot(d1)

dist_mean(d1)

# 95% confidence interval, using hdrcde
dist_hdr(d1, 0.95)

Citation

r format(citation("truelies"), style = "text")

Bibtex

cit <- citation("truelies")
cit$key <- "hughjones2019"
print(cit, style = "Bibtex")

hughjonesd/truelies documentation built on Sept. 19, 2021, 1:20 a.m.