Post_y: Posterior predictive distribution of the count in the control...

In brr: Bayesian Inference on the Ratio of Two Poisson Rates

Description

Density, distribution function, quantile function and random generation for the posterior predictive distribution of the count in the control group.

Usage

dpost_y(ynew, Tnew, a = 0.5, b = 0, c = 0.5, d = 0, x, y, T)

ppost_y(q, Tnew, a = 0.5, b = 0, c = 0.5, d = 0, x, y, T)

qpost_y(p, Tnew, a = 0.5, b = 0, c = 0.5, d = 0, x, y, T)

rpost_y(n, Tnew, a = 0.5, b = 0, c = 0.5, d = 0, x, y, T)

spost_y(Tnew, a = 0.5, b = 0, c = 0.5, d = 0, x, y, T, ...)

Arguments

ynew,q	vector of non-negative integer quantiles
a,b	non-negative shape parameter and rate parameter of the Gamma prior distribution on the rate μ
c,d	non-negative shape parameters of the prior distribution on φ
x,y	counts (integer) in the treated group and control group of the observed experiment
T,Tnew	sample sizes of the control group in the observed experiment and the predicted experiment
p	vector of probabilities
n	number of observations to be simulated
...	arguments passed to summary_PGIB

Details

The posterior predictive distribution of the count in the treated group is a Poisson-Gamma-Inverse Beta distribution.

Value

dpost_y gives the density, ppost_y the distribution function, qpost_y the quantile function, rpost_y samples from the distribution, and spost_y gives a summary of the distribution.

Note

Post_y is a generic name for the functions documented.

Examples

barplot(dpost_y(0:10, 10, 2, 7, 3, 4, 5, 3, 10))
spost_y(10, 2, 7, 3, 4, 5, 3, 10, output="pandoc")

brr documentation built on May 2, 2019, 1:04 a.m.