goodnessOfFit: goodness of fit for a count vector

In chenlab-sj/nbid: Differential expression analysis using negative binomial with independent dispersions (NBID)

Description

The distribution can be Poisson, negetive binomial or zero inflated negative binomial (ZINB). For Poisson, glm is used for the fitting For NB, glm.nb is used for the fitting. For ZINB, a NB is first fitted and then zeroinfl is used for fitting

Usage

goodnessOfFit(count, distribution, plot = F)

Arguments

count	a count vector
distribution	"poisson" for Poisson distribution, "nb" for the negative binomial distribution, "zinb" for the zero inflated negative binomial distribution
plot	If TRUE, plot the empirical and theoretical density and cumulative distribution function using package fitdistrplus

Value

a data frame with the pvalue of the goodness of fit and whether the fit is converged

Examples

## Not run: 
gene1 = rnbinom(500, size = 0.1, mu = 1)
print(goodnessOfFit(gene1, "poisson"))
print(goodnessOfFit(gene1, "nb"))
print(goodnessOfFit(gene1, "zinb"))

gene2 = rpois(500, lambda = 1)
print(goodnessOfFit(gene2, "poisson"))
print(goodnessOfFit(gene2, "nb"))
print(goodnessOfFit(gene2, "zinb"))

## End(Not run)

chenlab-sj/nbid documentation built on Nov. 4, 2019, 8:50 a.m.