qlfInterest: quasi-likelihood F-test

Description Usage Arguments Value Author(s) See Also Examples

View source: R/qlfInterest.R

Description

Compute quasi-likelihood F-test using edgeR package. For more information see glmQLFit and glmQLFTest functions in edgeR package.

Usage

1
2
3
	qlfInterest(x, design=c(), silent=TRUE, disp="common", 
		coef=c(), contrast=NULL, 
		poisson.bound=TRUE, ...)

Arguments

x

Object of type SummarizedExperiment.

design

Design matrix.

silent

Whether run silently, i.e. without printing the top differential expression tags. The default is TRUE.

disp

The method of estimating the dispersion in the data. Available options are: "common", "trended", "tagwiseInitCommon" and "tagwiseInitTrended". It is also possible to assign a number.

coef

Integer or character vector indicating which coefficients of the linear model are to be tested equal to zero. See glmQLFTest for more information.

contrast

Numeric vector or matrix specifying contrasts of the linear model coefficients to be tested equal to zero. See glmQLFTest for more information.

poisson.bound

Logical value, if TRUE (i.e. default) the pvalue would be higher than when obtained fom likelihood ratio test while Negative Binomial dispersion is zero.

...

Other parameter settings for the glmQLFTest function in the edgeR package.

Value

All values produced by glmQLFTest plus the following :

dispersionType

The name of the type of dispersion used.

dispersion

The estimated dispersion values.

Author(s)

Ali Oghabian

See Also

exactTestInterest, glmInterest, treatInterest

Examples

1
2
3
4
5
6
7
#Test retention differentiation across the 3 types of sampels
group <- getAnnotation(mdsChr22Obj)[,"type"]
qlfRes<- qlfInterest(x=mdsChr22Obj, 
	design=model.matrix(~group), silent=TRUE, 
	disp="tagwiseInitTrended", coef=2:3, contrast=NULL)

qlfRes

IntEREst documentation built on May 3, 2018, 6 p.m.