cvpred_mbplsda {packMBPLSDA}

Cross-validated predicted categories from a multi-block partial least squares discriminant model

Description

Function to perform 2-fold cross-validation for multi-block partial least squares discriminant analysis, in order to get for each observation the cross-validated predicted categories, and the statistical description of the predictions (mean, sd, 95

Usage

cvpred_mbplsda(object, nrepet = 100, threshold = 0.5, bloY, optdim, cpus = 1, 
algo = c("max", "gravity", "threshold"))

Arguments

object

an object created by mbplsda

nrepet

integer indicating the number of repetitions

threshold

numeric indicating the threshold, between 0 and 1, to consider the categories are predicted with the threshold prediction method.

bloY

integer vector indicating the number of categories per variable of the Y-block.

optdim

integer indicating the (optimal) number of components of the multi-block partial least squares discriminant model

cpus

integer indicating the number of cpus to use when running the code in parallel

algo

character vector indicating the method(s) of prediction to use (see details)

Details

Three different algorithms are available to predict the categories of observations. In the max, and respectively the threshold algorithms, numeric values are calculated from the matrix of explanatory variables and the regression coefficients. Then, the predicted categorie for each variable of the Y-block is the one which corresponds to the higher predicted value, respectively to the values higher than the indicated threshold. In the gravity algorithm, predicted scores of the observations on the components are calculated. Then, each observation is assigned to the observed category of which it is closest to the barycentre in the component space.

Value

TRUEnrepet

number of repetitions

matPredYc.max

with the max algorithm, boolean matrix indicating the cross-validated predicted categories on the calibration datasets, the prediction accuracy for each categorie, each Y-block variable, and overall

matPredYv.max

with the max algorithm, boolean matrix indicating the cross-validated predicted categories on the validation datasets, the prediction accuracy for each categorie, each Y-block variable, and overall

matPredYc.gravity

with the gravity algorithm, boolean matrix indicating the cross-validated predicted categories on the calibration datasets, the prediction accuracy for each categorie, each Y-block variable, and overall

matPredYv.gravity

with the gravity algorithm, boolean matrix indicating the cross-validated predicted categories on the validation datasets, the prediction accuracy for each categorie, each Y-block variable, and overall

matPredYc.threshold

with the threshold algorithm, boolean matrix indicating the cross-validated predicted categories on the calibration datasets, the prediction accuracy for each categorie, each Y-block variable, and overall

matPredYv.threshold

with the threshold algorithm, boolean matrix indicating the cross-validated predicted categories on the validation datasets, the prediction accuracy for each categorie, each Y-block variable, and overall

statPredYc.max

with the max algorithm, matrix indicating the statistical description of prediction categories for each observation on the calibration datasets: number of predictions as an observation of the calibration dataset, modal value, probability to be predicted with its standard deviation, 95% confidence interval, quantiles 0.025 and 0.975, median value

statPredYv.max

with the max algorithm, matrix indicating the statistical description of prediction categories for each observation on the validation datasets: number of predictions as an observation of the validation dataset, modal value, probability to be predicted with its standard deviation, 95% confidence interval, quantiles 0.025 and 0.975, median value

statPredYc.gravity

with the gravity algorithm, matrix indicating the statistical description of prediction categories for each observation on the calibration datasets: number of predictions as an observation of the calibration dataset, modal value, probability to be predicted with its standard deviation, 95% confidence interval, quantiles 0.025 and 0.975, median value

statPredYv.gravity

with the gravity algorithm, matrix indicating the statistical description of prediction categories for each observation on the validation datasets: number of predictions as an observation of the validation dataset, modal value, probability to be predicted with its standard deviation, 95% confidence interval, quantiles 0.025 and 0.975, median value

statPredYc.threshold

with the threshold algorithm, matrix indicating the statistical description of prediction categories for each observation on the calibration datasets: number of predictions as an observation of the calibration dataset, modal value, probability to be predicted with its standard deviation, 95% confidence interval, quantiles 0.025 and 0.975, median value

statPredYv.threshold

with the threshold algorithm, matrix indicating the statistical description of prediction categories for each observation on the validation datasets: number of predictions as an observation of the validation dataset, modal value, probability to be predicted with its standard deviation, 95% confidence interval, quantiles 0.025 and 0.975, median value

Note

at least 90 cross-validation repetitions may be recommended

Author(s)

Marion Brandolini-Bunlon (<[e-mail]>) and Stephanie Bougeard (<[e-mail]>)

References

Stone, M. (1974). Cross-validatory choice and assessment of statistical predictions. Journal of the Royal Statistical Society B, 36(2), 111-147.

Brandolini-Bunlon, M., Petera, M., Gaudreau, P., Comte, B., Bougeard, S., Pujos-Guillot, E.(2019). A new tool for multi-block PLS discriminant analysis of metabolomic data: application to systems epidemiology. Presented at 12emes Journees Scientifiques RFMF, Clermont-Ferrand, FRA(05-21-2019 - 05-23-2019).

Brandolini-Bunlon, M., Petera, M., Gaudreau, P., Comte, B., Bougeard, S., Pujos-Guillot, E.(2019). Multi-block PLS discriminant analysis for the joint analysis of metabolomic and epidemiological data. Metabolomics, 15(10):134

Brandolini-Bunlon, M., Petera, M., Gaudreau, P., Comte, B., Bougeard, S., Pujos-Guillot, E.(2020). A new tool for multi-block PLS discriminant analysis of metabolomic data: application to systems epidemiology. Presented at Chimiometrie 2020, Liege, BEL(01-27-2020 - 01-29-2020).

See Also

mbplsda plot_cvpred_mbplsda packMBPLSDA-package

Examples

data(status)
data(medical)
data(omics)
data(nutrition)
ktabX <- ktab.list.df(list(medical = medical[,1:10], 
nutrition = nutrition[,1:10], omics = omics[,1:20]))
disjonctif <- (disjunctive(status))
dudiY   <- dudi.pca(disjonctif , center = FALSE, scale = FALSE, scannf = FALSE)
bloYobs <- 2
ncpopt <- 1
modelembplsQ <- mbplsda(dudiY, ktabX, scale = TRUE, option = "uniform", scannf = FALSE, nf = 2)
CVpred <- cvpred_mbplsda(modelembplsQ, nrepet = 30, threshold = 0.5, bloY = bloYobs, 
optdim = ncpopt, cpus = 1, algo = c("max"))


data(status)
data(medical)
data(omics)
data(nutrition)
ktabX <- ktab.list.df(list(medical = medical, 
nutrition = nutrition, omics = omics))
disjonctif <- (disjunctive(status))
dudiY   <- dudi.pca(disjonctif , center = FALSE, scale = FALSE, scannf = FALSE)
bloYobs <- 2
ncpopt <- 1
modelembplsQ <- mbplsda(dudiY, ktabX, scale = TRUE, option = "uniform", scannf = FALSE, nf = 2)
CVpred <- cvpred_mbplsda(modelembplsQ, nrepet = 90, threshold = 0.5, bloY = bloYobs, 
optdim = ncpopt, cpus = 1, algo = c("max"))