16 Design of spatial experiments: Model fitting and prediction

Publisher Summary This chapter focuses on the design of spatial experiments. Gribik et al. were the first to use the optimal experimental design methods for environmental monitoring. They analyzed the problem of allocating measuring resources to aid in accurately estimating ground level pollution concentrations throughout a region X . The regression model was the linearized version of the diffusion model for four pollution sources and unknown background source. Because the diffusion model used in the study was a large scale model, measurements separated by distances smaller than a threshold value distance appeared to be correlated in the corresponding parameter estimation problem. In most spatial experiments, after the sites are selected measurements are usually taken on some regular schedule, for instance, several times a day, or they are continuously recorded. Generally, the response function may depend upon time. Random errors can be correlated both in time and space. When time is included explicitly in a model, then the concept of sensor allocation can be extended and “mobile” sensors may be introduced in the model.

[1]  S. Cambanis,et al.  Sampling Designs for Estimating Integrals of Stochastic Processes , 1992 .

[2]  Mong-Na Lo Huang,et al.  Marginally restricted linear-optimal designs , 1993 .

[3]  P. Hoel.  Minimax Designs in Two Dimensional Regression , 1965 .

[4]  Z. Ying.  Maximum likelihood estimation of parameters under a spatial sampling scheme , 1993 .

[5]  Valerii V. Fedorov,et al.  Optimal design with bounded density: optimization algorithms of the exchange type , 1989 .

[6]  Alan J. Miller,et al.  A review of some exchange algorithms for constructing discrete D-optimal designs , 1992 .

[7]  E. Spjøtvoll,et al.  Random coefficients regression models. a review 1 , 1977 .

[8]  Stamatis Cambanis,et al.  Sampling Designs for Estimation of a Random Process , 1993, Proceedings. IEEE International Symposium on Information Theory.

[9]  G. Oehlert.  The ability of wet deposition networks to detect temporal trends , 1995 .

[10]  E. Ziegel.  Optimal design and analysis of experiments , 1990 .

[11]  Werner G. Müller,et al.  Estimation and Experimental Design for Second Kind Regression Models , 1990 .

[12]  Radakovič.  The theory of approximation , 1932 .

[13]  G. Oehlert,et al.  Shrinking a wet deposition network , 1996 .

[14]  P. Bickel,et al.  Robustness of Design Against Autocorrelation in Time I: Asymptotic Theory, Optimality for Location and Linear Regression , 1979 .

[15]  J. Kiefer.  General Equivalence Theory for Optimum Designs (Approximate Theory) , 1974 .

[16]  J. Cooper,et al.  Theory of Approximation , 1960, Mathematical Gazette.

[17]  D. W. Arthur,et al.  Methods of numerical Integration (2nd edition), by Philip J. Davis and Philip Rabinowitz. Pp 612. £36·50. 1984. ISBN 0-12-206360-0 (Academic Press) , 1986, The Mathematical Gazette.

[18]  Calyampudi R. Rao,et al.  Linear Statistical Inference and Its Applications. , 1975 .

[19]  W. J. Studden,et al.  Theory Of Optimal Experiments , 1972 .

[20]  H. Grundel,et al.  The London School of Economics , 1938, Nature.

[21]  Henry P. Wynn,et al.  Maximum entropy sampling , 1987 .

[22]  Valery V. Fedorov,et al.  Optimal Experimental Design : Spatial Sampling , 1994 .

[23]  Christopher J. Nachtsheim,et al.  Tools for Computer-Aided Design of Experiments , 1987 .

[24]  Paul G. Hoel,et al.  Efficiency Problems in Polynomial Estimation , 1958 .

[25]  Minimum norm quadratic estimation of components of spatial covariance , 1985 .

[26]  Rainer Schwabe,et al.  Designing Experiments for Additive Nonlinear Models , 1995 .

[27]  H. P. Wynn,et al.  OPTIMUM SUBMEASURES WITH APPLICATION TO FINITE POPULATION SAMPLING , 1982 .

[28]  R. Schwabe.  Optimal Designs for Additive Linear Models , 1996 .

[29]  R. Cook,et al.  Marginally restricted D-optimal designs , 1980 .

[30]  D. Lindley.  On a Measure of the Information Provided by an Experiment , 1956 .

[31]  Harshinder Singh,et al.  On recursive formulas for isotonic regression useful for statistical inference under order restrictions , 1990 .

[32]  W. J. Studden,et al.  Tchebycheff Systems: With Applications in Analysis and Statistics. , 1967 .

[33]  Valery V. Fedorov,et al.  Optimal Designs for Time—Dependent Responses , 1995 .

[34]  Martin B. Zarrop,et al.  Optimal experiment design for dynamic system identification , 1977 .

[35]  Donald Ylvisaker,et al.  Prediction and Design , 1987 .

[36]  George A. F. Seber,et al.  Linear regression analysis , 1977 .

[37]  Noel A Cressie,et al.  Statistics for Spatial Data. , 1992 .

[38]  R. D. Cook,et al.  A Comparison of Algorithms for Constructing Exact D-Optimal Designs , 1980 .

[39]  J. Kiefer.  Optimum Experimental Designs , 1959 .

[40]  Wolfgang Bischoff,et al.  On exact D-optimal designs for regression models with correlated observations , 1992 .

[41]  Jürgen Pilz,et al.  Bayesian estimation and experimental design in linear regression models , 1992 .

[42]  D. Chang.  Design of Optimal Control for a Regression Problem , 1979 .

[43]  W. J. Studden,et al.  A Kiefer-Wolfowitz Theorem in a Stochastic Process Setting , 1979 .

[44]  G. Wahba,et al.  Design Problems for Optimal Surface Interpolation. , 1979 .

[45]  Dennis Cook,et al.  Constrained Optimization of Experimental Design , 1995 .

[46]  T. J. Mitchell,et al.  Bayesian Prediction of Deterministic Functions, with Applications to the Design and Analysis of Computer Experiments , 1991 .

[47]  Noel A. C. Cressie,et al.  Statistics for Spatial Data: Cressie/Statistics , 1993 .

[48]  Stamatis Cambanis,et al.  13 Sampling designs for time series , 1985 .

[49]  D. M. Titterington,et al.  Aspects of Optimal Design in Dynamic Systems , 1980 .

[50]  Paul Lanoie,et al.  A Comparison of Two Approaches , 1995 .

[51]  D. V. Gokhale,et al.  A Survey of Statistical Design and Linear Models. , 1976 .

[52]  T. J. Mitchell,et al.  Bayesian design and analysis of computer experiments: Use of derivatives in surface prediction , 1993 .

[53]  F. Pukelsheim.  Optimal Design of Experiments , 1993 .

[54]  Andrej Pázman,et al.  Foundations of Optimum Experimental Design , 1986 .

[55]  Toby J. Mitchell,et al.  Computer Construction of “D-Optimal” First-Order Designs , 1974 .

[56]  R Fisher,et al.  Design of Experiments , 1936 .

[57]  G. Wahba.  Regression Design for Some Equivalence Classes of Kernels , 1974 .

[58]  Wolfgang Näther.  Effective observation of random fields , 1985 .

[59]  D. Jain.  Linear integral equations: theory and technique : Ram P. Kanwal. 296 pages, 11 diagrams. New York, Academic Press, 1971. Price $16.50 (approx. £6.50). , 1974 .

[60]  R. J. Martin.  On the design of experiments under spatial correlation , 1986 .

[61]  Random interpolation in the theory of experimental design , 1989 .

[62]  W. Bischoff.  On D-optimal designs for linear models under correlated observations with an application to a linear model with multiple response , 1993 .

[63]  A. Stroud.  Approximate calculation of multiple integrals , 1973 .

[64]  T. Müller-Gronbach.  Optimal designs for approximating the path of a stochastic process , 1996 .

[65]  Calyampudi Radhakrishna Rao,et al.  Linear Statistical Inference and its Applications , 1967 .

[66]  M. Kupperman.  Linear Statistical Inference and Its Applications 2nd Edition (C. Radhakrishna Rao) , 1975 .

[67]  Andrej Pázman,et al.  Design Measures and Extended Information Matrices for Optimal Designs when the Observations are Correlated , 1995 .

[68]  W. Mueller.  Design of an Air-Pollution Monitoring Network , 1988 .

[69]  James V. Zidek,et al.  Using Prior Information in Designing Intervention Detection Experiments , 1993 .

[70]  K. Mardia.  Minimum norm quadratic estimation of components of spatial covariance , 1985 .

[71]  J. Sacks,et al.  Designs for Regression Problems With Correlated Errors: Many Parameters , 1968 .

[72]  Anthony C. Atkinson,et al.  Optimum Experimental Designs , 1992 .

[73]  Dale L. Zimmerman,et al.  A comparison of spatial semivariogram estimators and corresponding ordinary Kriging predictors , 1991 .

[74]  Stanley R. Johnson,et al.  Random Coefficient Regression Models and Carcass Pricing: A Comment , 1971 .

[75]  G. Wahba.  On the Regression Design Problem of Sacks and Ylvisaker , 1971 .

[76]  V. Fedorov,et al.  Invited Discussion Paper Constrained Optimization of Experimental Design , 1995 .

[77]  A. G. Butkovskii,et al.  Green's Functions and Transfer Functions Handbook , 1982 .

[78]  J. Sacks,et al.  Designs for Regression Problems with Correlated Errors III , 1966 .

[79]  David M. Steinberg,et al.  Optimal configuration of a seismographic network: A statistical approach , 1990, Bulletin of the Seismological Society of America.

[80]  V. Fedorov,et al.  Comparison of two approaches in the optimal design of an observation network , 1989 .

[81]  Philip Rabinowitz,et al.  Methods of Numerical Integration , 1985 .