computeObservedFstat {biclust}

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)

Arguments

x

Data Matrix

bicResult

Biclust object from biclust package

number

Number of bicluster in the output for computing observed statistics

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.

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

Author(s)

Tatsiana KHAMIAKOVA [e-mail]

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)