To path indicator Subpages of “Research“ To navigation To quick access To footer with other services
To content
Logo of TRR 391
Students in summer on north campus, red gears in background. © Roland Baege​/​TU Dortmund
A01

Optimal designs for spatio-temporal data

A01 has its focus on optimal design of experiments to increase the accuracy of spatio-temporal data analysis. It will develop a novel approach by considering the estimation and design problem simultaneously in continuous spatio-temporal models followed by the construction of implementable designs and estimators by appropriate discrete approximations. The long-term goal is the development of a unifying optimal design methodology for spatio-temporal modeling including models based on partial and stochastic partial differential equations.

Project Leaders

Prof. Dr. Holger Dette
Faculty of Mathematics - Chair of Stochastics
Ruhr University Bochum

JProf. Dr. Kirsten Schorning
Department of Statistics - Chair of Mathematical Statistics
TU Dortmund University

Summary

We determine optimal designs of experiments to increase the accuracy of statistical analysis of spatio-temporal data following a model-based approach. The main focus is on the development of a general methodology using the transition between discrete and continuous data structures. In particular, we determine the likelihood function, Fisherinformation matrix, maximum likelihood estimators and designs for models that are discrete in space and continuous in time, and use these results to derive efficient and implementable designs by discrete approximations of the optimal (continuous) solutions.

As it is often difficult to specify a concrete model in the stage of designing experiments, a large part of the project is devoted to the problem of constructing efficient designs under model uncertainty. Here we concentrate on designs that are robust with respect to model assumptions (using compound, Bayesian and minimax criteria that take the model uncertainty into account) and on designs for model validation developing new concepts of optimal discrimination designs for the analysis of spatio-temporal data (such as optimality criteria based on the Kullback-Leibler distance). Moreover, we also construct optimal designs for model-averaging estimates and determine efficient designs for state space models for networks and for spatial functional models.

An important aspect that will be addressed throughout this project, is scalability, as optimization has to be performed over large dimensional spaces often. Typical challenges include the calculation of optimal discrete approximations, of Bayesian and minimax optimal (discrimination) designs and of optimal designs for state space models.

Alexanderian, A. (2021). Optimal experimental design for infinite-dimensional Bayesian inverse problems governed by PDEs: A review. Inverse Problems 37, 043001. doi: 10.1088/1361-6420/abe10c.

Alhorn, K., K. Schorning, and H. Dette (2019). Optimal designs for frequentist model averaging. Biometrika 106, 665–682. doi: 10.1093/biomet/asz036.

Alhorn, K., H. Dette, and K. Schorning (2021). Optimal designs for model averaging in non-nested models. Sankhya : A 83, 745–778. doi: 10.1007/s13171-020-00238-9.

Atkinson, A. C. and R. D. Cook (1995). D-optimum designs for heteroscedastic linear models. Journal of the American Statistical Association 90, 204–212. doi: 10.1080/01621459.1995.10476503.

Bohorquez, M., R. Giraldo, and J. Mateu (2016a). Optimal dynamic spatial sampling. Environmetrics 27, 293–305. doi: 10.1002/env.2397.

Bohorquez, M., R. Giraldo, and J. Mateu (2016b). Optimal sampling for spatial prediction of functional data. Statistical Methods & Applications 25, 39–54. doi: 10.1007/s10260-015-0340-9.

Braess, D. and H. Dette (2013). Optimal discriminating designs for several competing regression models. The Annals of Statistics 41, 897–922. doi: 10.1214/13-AOS1103.

Calatayud, J., M. Jornet, and J. Mateu (2023). Spatio-temporal stochastic differential equations for crime incidence modeling. Stochastic Environmental Research and Risk Assessment 37, 1839–1854. doi: 10.1007/s00477-022-02369-x.

Chernoff, H. (1953). Locally optimal designs for estimating parameters. The Annals of Mathematical Statistics 24, 586–602. doi: 10.1214/aoms/1177728915.

Cressie, N. and C. K. Wikle (2011). Statistics for Spatio-Temporal data. New Jersey: Wiley.

Dasgupta, S., S. Mukhopadhyay, and J. Keith (2024). G-optimal grid designs for kriging models. Scandinavian Journal of Statistics, 1061–1085. doi: 10.1111/sjos.12699.

Dette, H., R. Guchenko, V. B. Melas, and W. K. Wong (2017a). Optimal discrimination designs for semiparametric models. Biometrika 105, 185–197. doi: 10.1093/biomet/asx058.

Dette, H. and T. Holland-Letz (2009). A geometric characterization of C-optimal designs for heteroscedastic regression. The Annals of Statistics, 4088–4103. doi: 10.1007/s11004-008-9147-7.

Dette, H., L. Hoyden, S. Kuhnt, and K. Schorning (2017b). Optimal Designs for Thermal Spraying. Journal of the Royal Statistical Society Series C: Applied Statistics 66, 53–72. doi: 10.1111/rssc.12156.

Dette, H., M. Konstantinou, and A. Zhigljavsky (2017c). A new approach to optimal designs for correlated observations. The Annals of Statistics 45. doi: 10.1214/16-AOS1500.

Dette, H., V. B. Melas, and R. Guchenko (2015). Bayesian T-optimal discriminating designs. The Annals of Statistics 43, 1959–1985. doi: 10.1214/15-AOS1333.

Dette, H., A. Pepelyshev, and A. Zhigljavsky (2016). Optimal designs in regression with correlated errors. The Annals of Statistics 44. doi: 10.1214/15-AOS1361.

Dette, H., A. Pepelyshev, and A. Zhigljavsky (2019). The BLUE in continuous-time regression models with correlated errors. The Annals of Statistics 47. doi: 10.1214/18-AOS1734.

Dette, H. and K. Schorning (2013). Complete classes of designs for nonlinear regression models and principal representations of moment spaces. The Annals of Statistics 41, 1260–1267. doi: 10.1214/13-AOS1108.

Dette, H. and K. Schorning (2016). Optimal designs for comparing curves. The Annals of Statistics 44. doi: 10.1214/15-AOS1399.

Dette, H. and S. Titoff (2009). Optimal discrimination designs. The Annals of Statistics 37, 2056–2082. doi: 10.1214/08-AOS635.

Diggle, P. and S. Lophaven (2006). Bayesian Geostatistical Design. Scandinavian Journal of Statistics 33, 53–64. doi: 10.1111/j.1467-9469.2005.00469.x.

Doob, J. L. (1949). Heuristic approach to the Kolmogorov-Smirnov theorems. Annals of Mathematical Statistics 20, 393–403. doi: 10.1214/aoms/1177729991.

Dryden, I. L., A. Koloydenko, and D. Zhou (2009). Non-euclidean statistics for covariance matrices, with applications to diffusion tensor imaging. The Annals of Applied Statistics 3, 1102–1123. doi: 10.1214/09-AOAS249.

Duan, P., L. He, L. Huang, G. Chen, et al. (2022). Sensor scheduling design for complex networks under a distributed state estimation framework. Automatica 146, 110628. doi: 10.1016/j.automatica.2022.110628.

Duarte, B. P. M., A. C. Atkinson, and N. M. C. Oliveira (2021). Optimal experimental design for linear time invariant state-space models. Statistics and Computing 31, 45. doi: 10.1007/s11222-021-10020-y.

Feller, C., K. Schorning, H. Dette, G. Bermann, et al. (2017). Optimal designs for dose response curves with common parameters. The Annals of Statistics 45. doi: 10.1214/16-AOS1520.

Gruijter, J. J. de, M. F. P. Bierkens, D. J. Brus, and M. Knotters (2006). Sampling for natural resource monitoring. Germany: Springer. doi: 10.1007/3-540-33161-1.

Harman, R. and W. G. Müller (2020). A design criterion for symmetric model discrimination based on flexible nominal sets. Biometrical Journal 62, 1090–1104. doi: 10.1002/bimj.201900074.

Hoeting, J. A., D. Madigan, A. E. Raftery, and C. T. Volinsky (1999). Bayesian model averaging: A tutorial (with comments by M. Clyde, David Draper and E. I. George, and a rejoinder by the authors. Statistical Science 14, 382–417. doi: 10.1214/ss/1009212519.

Ierimonti, L., I. Venanzi, and F. Ubertini (2021). ROC analysis-based optimal design of a spatio-temporal online seismic monitoring system for precast industrial buildings. Bulletin of Earthquake Engineering 19, 1441–1466. doi: 10.1007/s10518-020-01032-6.

Jahn, J. (2020). Introduction to the theory of nonlinear optimization. Fourth edition. Cham, Switzerland: Springer. doi: 10.1007/978-3-030-42760-3.

Ji, H. and H.-G. Müller (2016). Optimal designs for longitudinal and functional data. Journal of the Royal Statistical Society Series B: Statistical Methodology 79, 859–876. doi: 10.1111/rssb.12192.

Jones, R. H. and Y. Zhang (1997). Models for Continuous Stationary Space-Time Processes. Modelling Longitudinal and Spatially Correlated Data. Ed. by T. G. Gregoire, D. R. Brillinger, P. J. Diggle, E. Russek-Cohen, et al. New York, NY: Springer New York, 289–298. doi: 10.1007/978-1-4612-0699-6_25.

Kaipio, J. and E. Somersalo (2005). Statistical and Computational Inverse Problems. New York: Springer. doi: 10.1007/0-387-27132-5_7.

Kolar, M., L. Song, A. Ahmed, and E. P. Xing (2010). Estimating time-varying networks. The Annals of Applied Statistics 4, 94–123. doi: 10.1214/09-AOAS308.

Koutra, V., S. G. Gilmour, and B. M. Parker (2021). Optimal block designs for experiments on networks. Journal of the Royal Statistical Society Series C: Applied Statistics 70, 596–618. doi: 10.1111/rssc.12473.

Koval, K., A. Alexanderian, and G. Stadler (2020). Optimal experimental design under irreducible uncertainty for linear inverse problems governed by PDEs. Inverse Problems 36, 075007. doi: 10.1088/1361-6420/ab89c5.

Kunert, J. and R. J. Martin (2000). On the determination of optimal designs for an interference model. The Annals of Statistics 28, 1728–1742. doi: 10.1214/aos/1015957478.

Lesauskiene, E. and K. Dučinskas (2003). Universal Kriging for Spatio-Temporal Data. Mathematical Modelling and Analysis 8, 283–290. doi: 10.3846/13926292.2003.9637230.

Li, Q., R. Negi, and M. D. Ilić (2011). Phasor measurement units placement for power system state estimation: A greedy approach. 2011 IEEE Power and Energy Society General Meeting, 1–8. doi: 10.1109/PES.2011.6039076.

Lim, J. (2013). Spatio-Temporal Design: Advances in Efficient Data Acquisition by MATEU, J. and MÜLLER, W. G. Biometrics 69, 800. doi: 10.1111/biom.12093.

Lindgren, F., H. Bakka, D. Bolin, E. Krainski, et al. (2023). A diffusion-based spatio-temporal extension of Gaussian Matérn fields. doi: 10.48550/arXiv.2006.04917.

Lindgren, F., H. Rue, and J. Lindström (2011). An explicit link between Gaussian fields and Gaussian Markov random fields: The stochastic partial differential equation approach. Journal of the Royal Statistical Society Series B 73, 423–498. doi: 10.1111/j.1467-9868.2011.00777.x.

Liu, X., K. Yeo, and S. Lu (2022). Statistical Modeling for Spatio-Temporal Data From Stochastic Convection-Diffusion Processes. Journal of the American Statistical Association 117, 1482–1499. doi: 10.1080/01621459.2020.1863223.

López-Fidalgo, J., C. Tommasi, and P. C. Trandafir (2007). An Optimal Experimental Design Criterion for Discriminating Between Non-Normal Models. Journal of the Royal Statistical Society Series B: Statistical Methodology 69, 231–242. doi: 10.1111/j.1467-9868.2007.00586.x.

Mateu, J. and W. G. Müller (2012a). Collecting Spatio-Temporal Data. Spatio-Temporal Design. John Wiley & Sons, Ltd, 1–36. doi: 10.1002/9781118441862.ch1.

Mateu, J. and W. G. Müller, eds. (2012b). Spatio-temporal design: Advances in efficient data acquisition. Statistics in practice. Chichester, West Sussex, United Kingdom: Wiley. doi: 10.1002/9781118441862.

Mehr, C. B. and J. A. McFadden (1965). Certain properties of Gaussian processes and their first-passage times. Journal of the Royal Statistical Society. Series B. Methodological 27, 505–522. doi: 10.1111/j.2517-6161.1965.tb00611.x.

Müller, C. and K. Schorning (2023). A-optimal designs for state estimation in networks. Statistical Papers 64, 1159–1186. doi: 10.1007/s00362-023-01435-y.

Müller, W. G. and M. Stehlík (2010). Compound optimal spatial designs. Environmetrics 21, 354–364. doi: 10.1002/env.1009.

Müller, W. G. and D. L. Zimmerman (1999). Optimal designs for variogram estimation. Environmetrics 10, 23–37. doi: 10.1002/(SICI)1099-095X(199901/02)10:1<23::AID-ENV333>3.0.CO;2-P.

Nowak, W., F. P. J. De Barros, and Y. Rubin (2010). Bayesian geostatistical design: Task-driven optimal site investigation when the geostatistical model is uncertain. Water Resources Research 46, 2009WR008312. doi: 10.1029/2009WR008312.

Nowak, W. (2010). Measures of Parameter Uncertainty in Geostatistical Estimation and Geostatistical Optimal Design. Mathematical Geosciences 42, 199–221. doi: 10.1007/s11004-009-9245-1.

Oeksendal, B. (2003). Stochastic Differential Equations. 6th ed. Berlin: Springer.

Park, S. Y., L. Xiao, J. D. Willbur, A.-M. Staicu, et al. (2018). A joint design for functional data with application to scheduling ultrasound scans. Computational Statistics & Data Analysis 122, 101–114. doi: 10.1016/j.csda.2018.01.009.

Parker, B. M., S. G. Gilmour, and J. Schormans (2016). Optimal design of experiments on connected units with application to social networks. Journal of the Royal Statistical Society Series C: Applied Statistics 66, 455–480. doi: 10.1111/rssc.12170.

Parker, B. M., S. G. Gilmour, and J. A. Schormans (2011). Design of experiments for categorical repeated measurements in packet communication networks. Technometrics 53, 339–352. doi: 10.1198/TECH.2011.10052.

Pázman, A., M. Hainy, and W. G. Müller (2022). A convex approach to optimum design of experiments with correlated observations. Electronic Journal of Statistics 16, 5659–5691. doi: 10.1214/22-EJS2071.

Porcu, E., R. Furrer, and D. Nychka (2021). 30 Years of space-time covariance functions. WIREs Computational Statistics 13. doi: 10.1002/wics.1512.

Pukelsheim, F. (2006). Optimal Design of Experiments. Philadelphia: SIAM. doi: 10.1137/1.9780898719109.

Qian, W., C. A. Rolling, G. Cheng, and Y. Yang (2019). On the Forecast Combination Puzzle. Econometrics 7, 39. doi: 10.3390/econometrics7030039.

Ravi, S. N., V. Ithapu, S. Johnson, and V. Singh (2016). Experimental Design on a Budget for Sparse Linear Models and Applications. Proceedings of The 33rd International Conference on Machine Learning. Vol. 48, 583–592. url: https://proceedings.mlr.press/v48/ravi16.html.

Sagnol, G., M. Bouhtou, and S. Gaubert (2010). Successive C-optimal designs: A scalable technique to optimize the measurements on large networks. Performance Evaluation Review 38, 347–348. doi: 10.1145/1811099.1811080.

Sagnol, G. and R. Harman (2015a). Computing exact D-optimal designs by mixed integer second-order cone programming. The Annals of Statistics 43, 2198–2224. doi: 10.1214/15-AOS1339.

Sagnol, G. and R. Harman (2015b). Optimal designs for steady-state Kalman filters. Stochastic Models, Statistics and Their Applications. Ed. by A. Steland, E. Rafaj\lowicz, and K. Szajowski. Vol. 122, 149–157. doi: 10.1007/978-3-319-13881-7_17.

Schorning, K. and M. Konstantinou (2017). Bayesian optimal designs for dose-response curves with common parameters. doi: 10.48550/arXiv.1711.05704.

Schorning, K., M. Konstantinou, and H. Dette (2021). OPTIMAL DESIGNS FOR SERIES ESTIMATION IN NONPARAMETRIC REGRESSION WITH CORRELATED DATA. Statistica Sinica. doi: 10.5705/ss.202018.0497.

Sigrist, F., H. R. Künsch, and W. A. Stahel (2015). Stochastic partial differential equation based modelling of large space–time data sets. Journal of the Royal Statistical Society. Series B (Statistical Methodology) 77, 3–33. doi: 10.1111/rssb.12061.

Singhal, H. and G. Michailidis (n.d.). Optimal Sampling in State Space Models with Applications to Network Monitoring. doi: 10.1145/1384529.1375474.

Spöck, G. and J. Pilz (2012). Spatial sampling design by means of spectral approximations to the error process. Spatio-Temporal Design. Ed. by J. Mateu and W. G. Müller. 1st ed. Wiley, 72–102. doi: 10.1002/9781118441862.ch4.

Stehlík, M., J. López-Fidalgo, V. Casero-Alonso, and E. Bukina (2015). Robust integral compounding criteria for trend and correlation structures. Stochastic Environmental Research and Risk Assessment 29, 379–395. doi: 10.1007/s00477-014-0892-5.

Strouwen, A., B. M. Nicolaï, and P. Goos (2023). Adaptive and robust experimental design for linear dynamical models using Kalman filter. Statistical Papers. doi: 10.1007/s00362-023-01438-9.

Uciński, D. (2020). D-optimal sensor selection in the presence of correlated measurement noise. Measurement 164, 107873. doi: 10.1016/j.measurement.2020.107873.

Uciński, D. and B. Bogacka (2005). T -Optimum Designs for Discrimination Between Two Multiresponse Dynamic Models. Journal of the Royal Statistical Society Series B: Statistical Methodology 67, 3–18. doi: 10.1111/j.1467-9868.2005.00485.x.

Wang, H., M. Yang, and J. Stufken (2019a). Information-Based Optimal Subdata Selection for Big Data Linear Regression. Journal of the American Statistical Association 114, 393–405. doi: 10.1080/01621459.2017.1408468.

Wang, Y., A. W. Yu, and A. Singh (2017). On computationally tractable selection of experiments in measurement-constrained regression models. Journal of Machine Learning Research 18, 1–41. url: http://jmlr.org/papers/v18/17-175.html.

Wang, Y., Y. Yuan, Y. Ma, and G. Wang (2019b). Time-dependent graphs: Definitions, applications, and algorithms. Data Science and Engineering 4, 352–366. doi: 10.1007/s41019-019-00105-0.

Wikle, C. K. and J. A. Royle (1999). Space: Time dynamic design of environmental monitoring networks. Journal of Agricultural, Biological, and Environmental Statistics 4, 489–507. doi: 10.2307/1400504.

Wikle, C. K. and J. A. Royle (2005). Dynamic design of ecological monitoring networks for non-Gaussian spatio-temporal data. Environmetrics 16, 507–522. doi: 10.1002/env.718.

Zheng, Y. and B. H. Aukema (2010). Hierarchical dynamic modeling of outbreaks of mountain pine beetle using partial differential equations. Environmetrics 21, 801–816. doi: 10.1002/env.1058.

Zimmerman, D. L. and D. A. Harville (1991). A Random Field Approach to the Analysis of Field-Plot Experiments and Other Spatial Experiments. Biometrics 47, 223–239. doi: 10.2307/2532508.

Zimmerman, D. L. and J. Li (2012). Model-Based Frequentist Design for Univariate and Multivariate Geostatistics. Spatio-Temporal Design. Ed. by J. Mateu and W. G. Müller. 1st ed. Wiley, 37–53. doi: 10.1002/9781118441862.ch2.

To top of page