# Applies multiple testing procedures built to control (asymptotically) the FDR for correlation testing. Applies multiple testing procedures built to control (asymptotically) the FDR for correlation testing. Some have no theoretical proofs for tests on a correlation matrix. ```r ApplyFdrCor( data, alpha = 0.05, stat_test = "empirical", method = "LCTnorm", Nboot = 1000, vect = FALSE, arr.ind = FALSE ) ``` ## Arguments - `data`: matrix of observations - `alpha`: level of multiple testing - `stat_test`: - **'empirical'**: $\sqrt{n}*abs(corr)$ - **'fisher'**: $\sqrt{n-3}*1/2*\log( (1+corr)/(1-corr) )$ - **'student'**: $\sqrt{n-2}*abs(corr)/\sqrt(1-corr^2)$ - **'2nd.order'**: $\sqrt{n}*mean(Y)/sd(Y)$ with $Y=(X_i-mean(X_i))(X_j-mean(X_j))$ - `method`: choice between 'LCTnorm' and 'LCTboot' developped by Cai & Liu (2016), 'BH', traditional Benjamini-Hochberg's procedure Benjamini & Hochberg (1995)'s and 'BHboot', Benjamini-Hochberg (1995)'s procedure with bootstrap evaluation of p-values - `Nboot`: number of iterations for bootstrap p-values evaluation - `vect`: if TRUE returns a vector of TRUE/FALSE values, corresponding to `vectorize(cor(data))`; if FALSE, returns an array containing rows and columns of significant correlations - `arr.ind`: if TRUE, returns the indexes of the significant correlations, with repspect to level alpha ## Returns Returns either * logicals indicating if the corresponding correlation is significant, as a vector or a matrix depending on `vect`, * an array containing indexes $\lbrace(i,j),\,i\

ApplyFdrCor function