plot.g12post: Generic Plotting of Prior and Posterior distribution.

In yijin71/statg012: statg012: Statistical Inference at UCL

Description

Plot the columns of one matrix against the columns of anothor. These matrices come from different functions, including binombeta, nbinombeta, poisgamma, gamgam and normnorm.

Usage

## S3 method for class 'g12post'
plot(x, y, leg_pos = c("topright", "bottomright", "bottom",
  "bottomleft", "left", "topleft", "top", "right", "center"), which = c(1:5),
  prob = c(25, 50, 75, 95), ...)

Arguments

x, y	vectors or matrices of data for plotting. The number of row should match. If one of them are missing, the other is taken as y and an x vector of 1:n is used. Missing values (NAs) are allowed.
leg_pos	a character vector of legend place.
which	if matrices are from normnorm, a subset of the plots is required, specify a subset of the numbers 1:6. See below 'Details' for the different kinds.
prob	the probability level.
...	other arguments from matplot, legend and contour to plotting functions.

Details

The 1 plot shows the prior and posterior distribution of mu. The 2 plot shows the prior and posterior distribution of tau. The 3 plot shows the prior contour with probabilites. The 4 plot shows the posterior contour with probabilites. The 5 plot shows the prior and posterior contours with probabilites together.

Examples

## Get the posterior distribution with Gamma-Gamma model and plot.
y <- rgamma(10, shape = 3)
ex <- gamgam(y, a = 3, 4, 1)
plot(ex, leg_pos = "center" , box.lty=0)

## Obtain the posterior distribution with Normal-Gamma model,
## assuming both mu and sigma are unknown.
x <- rnorm(100, mean = 1, sd = 0.5)
ex <- normnorm(y, m = 2, s = 1, a = 1, b = 2)
## show the fourth and fifth plot
plot(ex, which = 4, main = "Posterior Contour",
           xlim = c(-3,3), ylim = c(0,3))
plot(ex, which = 5, main = "Prior and Posterior Contour")

yijin71/statg012 documentation built on May 23, 2019, 4:04 p.m.