ebCorrelation: Class "ebCorrelation"

In BetaModels: Bayesian Analysis of Different Rates in Different Groups

Class "ebCorrelation"

Description

Fit an empirical Bayes model to detemine which values in a large collection of correlation coefficients are significant.

Usage

ebCorrelation(ss, nObs, nPoints = 500)
## S4 method for signature 'ebCorrelation'
hist(x,
           xlab='Correlation', ylab='Prob(Different | Y)', main='',
           highlight='purple', lowlight='blue', ...)
## S4 method for signature 'ebCorrelation,missing'
plot(x,
                  prior=1, significance=0.9, ylim=c(-0.5, 1),
                  xlab='Correlation', ylab='Prob(Unusual | Rho)',
                  highlight='purple', ...)
## S4 method for signature 'ebCorrelation'
summary(object, prior=1, significance=0.9, ...)
## S4 method for signature 'ebCorrelation'
cutoffSignificant(object, prior, significance, ...)
## S4 method for signature 'ebCorrelation'
selectSignificant(object, prior, significance, ...)
## S4 method for signature 'ebCorrelation'
countSignificant(object, prior, significance, ...)

Arguments

ss	A numerical vector containing correlation coefficinets between -1 and 1.
nObs	A numerical vector of length one, the number of objects used in every computation of correlation coefficients.
nPoints	the number of points at which to estimate the distribution.
object	object of class ebCorrelation
x	object of class ebCorrelation
xlab	Graphical parameter.
ylab	Graphical parameter.
ylim	Graphical parameter.
main	Graphical parameter.
...	Optional extra parameters, either graphical or for the significance functions.
prior	A real number between 0 and 1; the prior probability that a correlation coefficinet is not significant.
significance	A real number between 0 and 1; the posterior probability betyond which a correlation coefficinet will be called significant.
highlight	Character string denoting a color.
lowlight	Character string denoting a color.

Details

TBD

Value

The ebCorrelation constructor returns an object of the indicated class.

TBD

Creating Objects

Although objects can be created directly using new, the most common usage will be to pass a vector of correlation coefficients to the ebCorrelation function.

Slots

correlation:

numeric vector of correlation coefficients.

nObservation:

the number of sample observations used to compute correlations.

xvals:

vector of the x-axis grid points at which to compute the posterior probability; see Details.

pdf:

vector of the ermpirically estimated probability densities at xvals; see Details.

theoretical.pdf:

vector of the theoretical probability densities at xvals; see Details.

unravel:

Matrix of posterior probabilities.

call:

A call object recording how the constructior function was invoked.

Methods

summary(object, ...)

Prints a summary of the ebCorrelation object. This includes (1) the maximum a posterior coordinates on x-y-space, (2) the usual alpha-beta parameters for the Beta distribution, and (3) the mean and variance.

image(x, col, ...)

Plots an ikmage of the posterior probabilities using te specified color map. The point with the maximum posterior probability is marked in red.

Author(s)

Kevin R. Coombes [e-mail]

References

Efron's paper on empirical Bayes for differential exprewssion.

Examples

showClass("ebCorrelation")
set.seed(12345)
cc <- c(rbeta(4600, 24, 24), rbeta(400, 8, 8))
rr <- 2*cc-1
fit <- ebCorrelation(rr, 51)
hist(fit)
plot(fit, prior = 0.85)
countSignificant(fit, prior = 0.85, significance = 0.8)
cutoffSignificant(fit, prior = 0.85, significance = 0.8)
summary(fit)
summary(fit, prior = 0.85, significance = 0.8)

BetaModels documentation built on Feb. 9, 2024, 3:01 a.m.