Discriminant and cluster analysis of possibly high-dimensional time series data by a class of disparities

Discriminant and cluster analysis of high-dimensional time series data have been an urgent need in more and more academic fields. To settle the always-existing problem of bias in distance-based classifiers for high-dimensional models, we consider a new classifier with jackknife-type bias adjustment for stationary time series data. The consistency of the classifier is theoretically shown under suitable conditions, including the situations of possibly high-dimensional data. We also conduct the cluster analysis for real financial data.