
 This toy data contains 1000 genes, and 6 samples in each of the two classes.
 The sequencing depths of the 12 samples are rep(c(1, 2), 6).
 The first 80 genes are set to be overexpressed in Class 2, and the next 20 genes are set to be underexpressed in Class 2.
 The other 900 genes are null.
 This is a Poisson-distributed data.


datasets

This package implements a method for normalization,
testing, and false discovery rate estimation for RNA-sequencing
data. The description of the method is in Li J, Witten DM,
Johnstone I, Tibshirani R (2012). Normalization, testing, and
false discovery rate estimation for RNA-sequencing data.
Biostatistics 13(3): 523-38. We estimate the sequencing depths
of experiments using a new method based on Poisson
goodness-of-fit statistic, calculate a score statistic on the
basis of a Poisson log-linear model, and then estimate the
false discovery rate using a modified version of permutation
plug-in method. A more detailed instruction as well as sample
data is available at
http://www.stanford.edu/~junli07/research.html.  In this
version, we changed the way of calculating log foldchange for
two-class data. The FDR estimation part remains unchanged.

Jun Li

PoissonSeq

Significance analysis of sequencing data based on a Poisson log
linear model

dat function

A list.
  <dl>
		<dt><code>n</code></dt><dd>the count matrix</dd> <dt><code>y</code></dt><dd>the outcome vector</dd> <dt><code>type</code></dt><dd>the outcome type</dd> <dt><code>pair</code></dt><dd>whether the samples are paired or not</dd> </dl> 

dat: A toy RNA-Seq data.

Description

Usage

Arguments

Format