Abstract
Two approaches are considered to design experiments for a correlated random field when the objective is to obtain precise predictions over the whole experimental domain. Both take the uncertainty of the estimated parameters of the correlation structure of the random field into account. The first one corresponds to a compound D-optimality criterion for both the trend and covariance parameters. The second one relies on an approximation of the mean squared prediction error already proposed in the literature. It is conjectured, and shown on a paradigmatic example, that for some particular settings both approaches yield similar optimal designs, thereby revealing a sort of accordance between the two criteria for random fields. However, our example also shows that a strict equivalence theorem as in the uncorrelated case is not achievable. As a side issue we cast doubts on the ubiquity of equidistant space-filling designs.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Abt, M.: Estimating the prediction mean squared error in gaussian stochastic processes with exponential correlation structure. Scand. J. Stat. 26(4), 563–578 (1999)
Baldi Antognini, A., Zagoraiou, M.: Exact optimal designs for computer experiments via kriging metamodelling. J. Stat. Plan. Infer. 140(9), 2607–2617 (2010) http://dx.doi.org/10.1016/j.jspi.2010.03.027
Bursztyn, D., Steinberg, D.: Comparison of designs for computer experiments. J. Stat. Plan. Infer. 136(3), 1103–1119 (2006) http://dx.doi.org/10.1016/j.jspi.2004.08.007
Cressie, N.A.C.: Statistics for Spatial Data (Wiley Series in Probability and Statistics), rev sub Edition. Wiley-Interscience, New York (1993)
Dette, H., Kunert, J., Pepelyshev, A.: Exact optimal designs for weighted least squares analysis with correlated errors. Stat. Sinica. 18 (1), 135–154 (2008)
Fedorov, V., Müller, W.: Optimum design for correlated processes via eigenfunction expansions. In: López-Fidalgo, J., Rodríguez-Díaz, J., Torsney, B. (Eds.), mODa’8 – Advances in Model–Oriented Design and Analysis, Proceedings of the 8th Int. Workshop, Almagro (Spain). Physica Verlag, Heidelberg, 57–66 (2007)
Ginsbourger, D., Dupuy, D., Badea, A., Carraro, L., Roustant, O.: A note on the choice and the estimation of kriging models for the analysis of deterministic computer experiments. Appl. Stoch. Model. Bus. 25(2), 115–131 (2009) http://dx.doi.org/10.1002/asmb.741
Harman, R., Stulajter, F.: Optimal prediction designs in finite discrete spectrum linear regression models. Metrika, 72, 281-294 (2009) http://dx.doi.org/10.1007/s00184-009-0253-4
Harville, D.A., Jeske, D.R.: Mean squared error of estimation or prediction under a general linear model. J. Am. Stat. Assoc. 87(419), 724–731 (1992)
Kiefer, J., Wolfowitz, J.: The equivalence of two extremum problems. Canadian. J. Math. 12, 363–366 (1960)
Kislák, J., Stehlík, M.: Equidistant and D-optimal designs for parameters of Ornstein-Uhlenbeck process. Stat. Probabil. Lett. 78(12), 1388–1396 (2008)
Müller, W., Pázman, A.: Measures for designs in experiments with correlated errors. Biometrika. 90(2), 423–434 (2003)
Müller, W.G.: Collecting Spatial Data, 3rd Edition. Springer, Heidelberg (2007)
Müller, W. G., Stehlík, M.: Issues in the optimal design of computer simulation experiments. Appl. Stoch. Model. Bus. 25(2), 163–177 (2009)
Müller, W. G., Stehlík, M.: Compound optimal spatial designs. Environmetrics 21(3-4), 354–364 (2009) http://dx.doi.org/10.1002/env.1009
Pronzato, L.: Optimal experimental design and some related control problems. Automatica 44(2), 303–325 (2008)
Pronzato, L.: One-step ahead adaptive D-optimal design on a finite design space is asymptotically optimal. Metrika 71(2), 219–238 (2010) http://dx.doi.org/10.1007/s00184-008-0227-y
Sacks, J., Welch, W.J., Mitchell, T.J., Wynn, H.P.: Design and analysis of computer experiments. Stat. Sci. 4(4), 409–423 (1989)
Stein, M.L.: Interpolation of Spatial Data: Some Theory for Kriging. (Springer Series in Statistics), 1st Edition. Springer (1999)
Torsney, B., Martín-Martín, R.: Multiplicative algorithms for computing optimum designs. J. Stat. Plan. Infer. 139(12), 3947–3961 (2009) http://dx.doi.org/10.1016/j.jspi.2009.05.007
Ying, Z.: Asymptotic properties of a maximum likelihood estimator with data from a Gaussian process. J. Multivariate Anal. 36, 280–296 (1991)
Zagoraiou, M., Antognini, A.B.: Optimal designs for parameter estimation of the Ornstein-Uhlenbeck process. Appl. Stoch. Model. Bus online (5), 583–600 (2009) http://dx.doi.org/10.1002/asmb.749
Zhu, Z., Stein, M.: Spatial sampling design for parameter estimation of the covariance function. J. Stat. Plan. Infer. 134(2), 583–603 (2005)
Zhu, Z., Stein, M.L.: Spatial sampling design for prediction with estimated parameters. J Agr Biol Envir St 11(1), 24–44 (2006)
Zhu, Z., Zhang, H.: Spatial sampling design under the infill asymptotic framework. Environmetrics 17(4), 323–337 (2006)
Zimmerman, D.L.: Optimal network design for spatial prediction, covariance parameter estimation, and empirical prediction. Environmetrics. 17(6), 635–652 (2006)
Acknowledgements
The article was mainly written during the first author’s research stay at the University of Nice-Sophia Antipolis and he wants to acknowledge its generous support. This work was also partially supported by a PHC Amadeus/OEAD Amadée grant FR11/2010. We are also grateful to an attentive referee for pointing out several omissions and typos.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Müller, W.G., Pronzato, L., Waldl, H. (2012). Relations Between Designs for Prediction and Estimation in Random Fields: An Illustrative Case. In: Porcu, E., Montero, J., Schlather, M. (eds) Advances and Challenges in Space-time Modelling of Natural Events. Lecture Notes in Statistics(), vol 207. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17086-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-17086-7_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17085-0
Online ISBN: 978-3-642-17086-7
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)