ENBIS-13 in Ankara

15 – 19 September 2013 Abstract submission: 5 February – 5 June 2013

Optimal Designs for the Gaussian Processes Model via Spectral Decomposition

16 September 2013, 12:55 – 13:15


Submitted by
Ofir Harari
Ofir Harari (Tel Aviv University), David M. Steinberg (Tel Aviv University)
Gaussian processes provide a popular statistical modelling approach in various fields, including spatial statistics and computer experiments. Strategic experimental design could prove crucial when data are hard to collect. We use the Karhunen-Loeve decomposition to study several popular design criteria. The resulting expressions are useful for understanding and comparing the criteria. A truncated form of the expansion is used to generate optimal designs. We give detailed results, including an error analysis, for the well-established Integrated Mean Squared Prediction Error.
View paper

Return to programme