sampleSize: A function for sample size calculations

Description

This generic function sampleSize calculates the protein variance and the sample size required to estimate the clinically important differences (DIFF). The input data are the consensus parameters of peaks with medium biological variation.

Usage

sampleSize(Data,intraclasscorr,signifcut, ...)

Arguments

Data

An object of aclinicalProteomicsData class.

intraclasscorr

An object of numeric class. It is a known value of the intraclass correlation, or an estimate from a pilot data.

signifcut

An object of numeric class. It is significance threshold (usually, taken to be 0.05 in the analysis of the protein profiling studies).

...

Some methods for this generic function may take additional, optional arguments. At present none do.

Value

protein_variance: consensus protein variance
replicate_correlation: consensus intraclass correlation
sample_size: the sample size required

Details

The sample sizes are computed for various combinations of the power with values beta=c(0.90,0.80,0.70) and the significance values, alpha = c(0.001, 0.01,0.05). Note that here we use beta for power rather than the conventional 1-beta.

References

Nyangoma SO, Ferreira JA, Collins SI, Altman DG, Johnson PJ, and Billingham LJ: Sample size calculations for planning clinical proteomic profiling studies using mass spectrometry. Bioinformatics (Submitted)

Smyth GK, et al.: Use of within-array replicate spots for assessing differential expression in microarray experiments. Bioinformatics 2005, 21, 2067 - 75

Smyth GK: Linear models and emperical Bayes methods for assessing differential expression in microarray experiments. Stat Appl Genet Mol Biol 2004, 3, 1, Article 3

Examples

Run this code

########################################################################
## SAMPLE SIZE
#######################################################################
#The function sampleSize calculates the biological variance, differences.
#These are the consensus values of peaks with median biological variation
# It also gives sample sizes for beta=c(0.90,0.80,0.70) and alpha = c(0.001, 0.01,0.05)

####################################################################
####################################################################
####################################################################

intraclasscorr  <-  0.60 #cut-off for intraclass correlation

signifcut <- 0.05      #significance cut-off

data(liverdata)

data(liver_pheno)

OBJECT=new("aclinicalProteomicsData")

OBJECT@rawSELDIdata=as.matrix(liverdata)
OBJECT@covariates=c("tumor" ,    "sex")
OBJECT@phenotypicData=as.matrix(liver_pheno)
OBJECT@variableClass=c('numeric','factor','factor')
OBJECT@no.peaks=53


sampleSize(OBJECT,intraclasscorr,signifcut)

####################################################################
####################################################################
####################################################################

Run the code above in your browser using DataLab