maxTinftyCor_SD {TestCor}

Multiple testing method of Drton & Perlman (2007) for correlations, with stepdown procedure.

Description

Multiple testing method based on the evaluation of quantile by simulation of observations from the asymptotic distribution (Drton & Perlman (2007)), with stepdown procedure.

Usage

maxTinftyCor_SD(
  data,
  alpha = 0.05,
  stat_test = "empirical",
  Nboot = 1000,
  OmegaChap = covDcorNorm(cor(data), stat_test),
  vect = FALSE,
  logical = TRUE,
  arr.ind = FALSE
)

Arguments

data

matrix of observations

alpha

level of multiple testing

stat_test

4 test statistics are available:

'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))

Nboot

number of iterations for Monte-Carlo quantile evaluation

OmegaChap

matrix of covariance of test statistics; optional, useful for oracle estimation and step-down

vect

if TRUE returns a vector of TRUE/FALSE values, corresponding to vectorize(cor(data)); if FALSE, returns an array containing TRUE/FALSE values for each entry of the correlation matrix

logical

if TRUE, returns either a vector or a matrix where each element is equal to TRUE if the corresponding null hypothesis is rejected, and to FALSE if it is not rejected if FALSE, returns a list of successive p-values : element [[i+1]] of the list giving the p-values evaluated on the non-rejected hypothesis at step [[i]]; p-values are either as a vector or a list depending on vect

arr.ind

if TRUE, returns the indexes of the significant correlations, with respect to level alpha

Value

Returns

• logicals, equal to TRUE if the corresponding element of the statistic vector is rejected, as a vector or a matrix depending of the value of vect,

• an array containing indexes \lbrace(i,j),\,i<j\rbrace for which correlation between variables i and j is significant, if arr.ind=TRUE.

References

Drton, M., & Perlman, M. D. (2007). Multiple testing and error control in Gaussian graphical model selection. Statistical Science, 22(3), 430-449.

Roux, M. (2018). Graph inference by multiple testing with application to Neuroimaging, Ph.D., Université Grenoble Alpes, France, https://tel.archives-ouvertes.fr/tel-01971574v1.

See Also

ApplyFwerCor, maxTinftyCor

Examples

 
n <- 100
p <- 10
corr_theo <- diag(1,p)
corr_theo[1,3] <- 0.5
corr_theo[3,1] <- 0.5
data <- MASS::mvrnorm(n,rep(0,p),corr_theo)
alpha <- 0.05
# significant correlations:
maxTinftyCor_SD(data,alpha,stat_test='empirical', arr.ind=TRUE)
# successive p-values
res <- maxTinftyCor_SD(data,stat_test='empirical', logical=FALSE)
lapply(res,FUN=function(x){round(x,2)})
# succesive rejections
lapply(res,FUN=function(x){whichCor(x<alpha)})