biclust (version 2.0.3.1)

computeObservedFstat: Diagnostic F Statistic Calculation

Description

Functions for obtaining F statistics within bicluster and the significance levels. The main effects considered are row, column and interaction effect.

Usage

computeObservedFstat(x, bicResult, number)

Value

Data frame with three rows ("Row Effect", "Column Effect", "Tukey test") and 2 columns for corresponding statistics (Fstat) and their p-values (PValue). 2

Arguments

x

Data Matrix

bicResult

Biclust object from biclust package

number

Number of bicluster in the output for computing observed statistics

Author

Tatsiana KHAMIAKOVA

Details

F-statistics are calculated from the two-way ANOVA mode with row anc column effect. The full model with interaction is unidentifiable, thus, Tukey's test for non-additivity is used to detect an interaction within a bicluster. p-values are obtained from assymptotic F distributions.

See Also

diagnosticTest, diagnosticPlot2, ChiaKaruturi, diagnoseColRow

Examples

#---simulate dataset with 1 bicluster ---#
xmat<-matrix(rnorm(50*50,0,0.25),50,50) # background noise only 
rowSize <- 20 #number of rows in a bicluster 
colSize <- 10 #number of columns in a bicluster
a1<-rnorm(rowSize,1,0.1) #sample row effect from N(0,0.1) #adding a coherent values bicluster:
b1<-rnorm((colSize),2,0.25)  #sample column effect from N(0,0.05)
mu<-0.01 #constant value signal
 for ( i in 1 : rowSize){
 	for(j in 1: (colSize)){
 		xmat[i,j] <- xmat[i,j] + mu + a1[i] + b1[j] 	
 	}
 }
 #--obtain a bicluster by running an algorithm---# 
plaidmab <- biclust(x=xmat, method=BCPlaid(), cluster="b", fit.model = y ~ m + a+ b,  
background = TRUE, row.release = 0.6, col.release = 0.7, shuffle = 50, back.fit = 5, 
max.layers = 1, iter.startup = 100, iter.layer = 100, verbose = TRUE)

#Calculate statistics and their p-values to infer about the structure within bicluster:
Structure <- computeObservedFstat(x=xmat, bicResult = plaidmab, number = 1)