erpavetest {ERP}

Significance testing of averaged ERPs.

Description

The function first calculates averaged ERP values within a predetermined number of equally-spaced intervals then tests for significance of the relationship between averaged ERPs and covariates in a linear model framework.

Usage

erpavetest(dta, design, design0 = NULL, nintervals = 10, 
method = c("none","BH","holm","hochberg","hommel","bonferroni","BY","fdr"),alpha = 0.05)

Arguments

dta

Data frame containing the ERP curves: each column corresponds to a time frame and each row to a curve.

design

Design matrix of the nonnull model for the relationship between the ERP and the experimental variables. Typically the output of the function model.matrix

design0

Design matrix of the null model. Typically a submodel of the nonnull model, obtained by removing columns from design. Default is NULL, corresponding to the model with no covariates.

nintervals

Number of intervals in the partition of the whole interval of observation. Default is 10.

method

FDR- or FWER- controlling multiple testing procedures as available in the function p.adjust. Default is "none", for no multiplicity correction.

alpha

The FDR or FWER control level. Default is 0.05

Value

pval

p-values of the tests.

correctedpval

Corrected p-values, for the multiplicity of tests. Depends on the multiple testing method (see function p.adjust).

significant

Indices of the time points for which the test is positive.

segments

Factor giving the membership of timepoints to each interval in the partition.

breaks

Breakpoints of the partition.

test

Pointwise F-statistics if p>1, where p is the difference between the numbers of parameters in the nonnull and null models. Otherwise, if p=1, the function returns pointwise t-statistics (signed square-roots of F-statistics).

df1

Residual degrees of freedom for the nonnull model.

df0

Residual degrees of freedom for the null model.

signal

Estimated signal: a pxT matrix, where T the number of frames.

r2

R-squared values for each of the T linear models.

Author(s)

David Causeur, IRMAR, UMR 6625 CNRS, Agrocampus Ouest, Rennes, France.

See Also

erptest, erpfatest, gbtest, p.adjust

Examples

data(impulsivity)

# Paired t-tests for the comparison of the ERP curves in the two conditions, 
# within experimental group High, at channel CPZ

erpdta.high = impulsivity[impulsivity$Group=="High",5:505] 
   # ERP curves for subjects in group 'High'
covariates.high = impulsivity[impulsivity$Group=="High",1:4]
   # Experimental covariates for subjects in group 'High'

design = model.matrix(~C(Subject,sum)+Condition,data=covariates.high)
   # Design matrix to compare ERP curves in the two conditions
design0 = model.matrix(~C(Subject,sum),data=covariates.high)
   # Design matrix for the null model (no condition effect)

tests = erpavetest(erpdta.high,design,design0)
   
time_pt = seq(0,1000,2)     # sequence of time points (1 time point every 2ms in [0,1000])
nbs = 20                    # Number of B-splines for the plot of the effect curve
effect=which(colnames(design)=="ConditionSuccess")
erpplot(erpdta.high,design=design,frames=time_pt,effect=effect,xlab="Time (ms)",
        ylab=expression(Effect~curve~(mu~V)),bty="l",ylim=c(-3,3),nbs=nbs,
        cex.axis=1.25,cex.lab=1.25,interval="simultaneous")
   # with interval="simultaneous", both the pointwise and the simultaneous confidence bands
   # are plotted
abline(v=time_pt[tests$breaks],lty=2,col="darkgray")
   # Add a grid to show breakpoints
points(time_pt[tests$significant],rep(0,length(tests$significant)),pch=16,col="blue")
   # Identifies significant time points by blue dots
title("Success-Failure effect curve with 95 percent C.I.",cex.main=1.25)
mtext(paste("12 subjects - Group 'High' - ",nbs," B-splines",sep=""),cex=1.25)