plotBayes: Function for exploring Bayesian inference for the sample mean...

In mcbeem/plotBayes: Function for exploring Bayesian inference for the sample mean for Normal data

Description

This function plots the prior, likelihood, and posterior distribution of the sample mean. It reports the MAP (maximum a posteriori) and EAP (expected a posteriori) estimates of the mean as well as the 95% credible interval around the MAP.

Usage

plotBayes(data, prior.type = "normal", prior.parameters, min, max,
  points = 1000, credible = 0.95)

Arguments

data	A vector of data
prior.type	The type of distribution for the prior. Can be "uniform" or "normal"
prior.parameters	A vector of length two providing the parameter values for the prior. When prior.type="normal", the values are the mean and sd. When prior.type="uniform", the values are the min and the max.
min	The minimum possible value of mu to consider.
max	The maximum possible value of mu to consider.
points	The number of values of mu to be calculated, higher means more precision. Defaults to 1000.
credible	The width of the credible interval specified as a number between zero and one. Defaults to 0.95 for a 95% credible interval.

Value

Returns a list with the following components:

• mean The sample mean of the data.
  

• map The maximum a posteriori estimate of the mean.
  

• eap The expected a posteriori estimate of the mean.
  

• credible.interval The values defining the endpoints of the Bayesian credible interval.

Examples

set.seed(1)
data <- rnorm(n=10, mean=1, sd=1)
plotBayes(data, prior.type="normal", prior.parameters=c(0, .5), min=-2, max=2) 
plotBayes(data, prior.type="uniform", prior.parameters=c(.7, 1.5), min=-2, max=2)
plotBayes(data, prior.parameters=c(.7, 1.5), min=-2, max=2, credible=.9)

mcbeem/plotBayes documentation built on Nov. 19, 2019, 8:15 a.m.