Fitting distribution in R
Hi everyone!
I have some data that describe gene expression of several people.
I want to understand whether the distribution of the data can be modeled as the Poisson or the Negative binomial distribution.
For the Poisson I use the next commands:
n <- length(x)
lambda = mean(x) # I use the MLE for the Poisson parameter
f.hyp = dpois(x,lambda)*n
chiSquare.pois = sum((f.obs-f.hyp)^2/f.hyp)
Am I right with this code ?
How can I estimate the parameters for the neg.binomial distribution and compare these two models (poisson and neg.binomial ) ?
0 answers
No answers yet.
Log in to answer this question.
More posts like this
-
How to get parameter estimation r and p for Negative Binomial distribution using R?
written by bioinfo89 •
-
Wilcoxon test, t-test and negative binomial test for DEG of scRNA-Seq data
written by CY
-
Zero-inflated negative binomial distribution in R
written by ma23 •
-
Chi Square test for negative binomial distribution using R.
written by ma23 •
-
poisson - negative binomial mixture with flexmix and countreg
written by smt8n •
-
What is the reason why we usually use normalized values from RNA-Seq (FPKM, RPKM, etc.) ?
written by ebrudermanver
-
Using the dispersion result from DESeq2 from one dataset to generate negative binomial sample
written by hirak.sarkar •
-
Question about zero.truncated
written by jamie •
-
Expected number of read duplicates
written by dariober
-
Why number of reads in a sample that are assigned to gene i can be modeled by a negative bionomial …
written by jack
I would probably start with the papers and source codes of the established tools that model RNA-seq as NB, such as
DESeq2andedgeRto get an impression on how/why they do it.As pointed out, check previous work to understand why people decided for a particular distribution for a given data type. Typically when trying to decide which distribution best approximates the data, visual tools (e.g. density and QQ plots) and goodness-of-fit tests are used (e.g. chi-squared test). For choosing between (families of) distributions, have a look at the R package fitdistrplus and its descdist() function.