×

Designs for crossvalidating approximation models. (English) Zbl 1279.62158

Summary: Multifold crossvalidation is routinely used for assessing the prediction error of an approximation model for a black-box function. Despite its popularity, this method is known to have high variability. To mitigate this drawback, we propose an experimental design approach that borrows Latin hypercube designs to construct a structured crossvalidation sample such that the input values in each fold achieve uniformity. Theoretical results show that the estimate of the prediction error of the proposed method has significantly smaller variability than its counterpart under independent and identically distributed sampling. Numerical examples corroborate the theoretical results.

MSC:

62K10 Statistical block designs
05B15 Orthogonal arrays, Latin squares, Room squares
65C60 Computational problems in statistics (MSC2010)
PDFBibTeX XMLCite
Full Text: DOI Link