To content
A04

Statistical monitoring of spatio-temporal processes

A04 develops methodology for online monitoring in spatio-temporal models and timely detection of structural alterations. It develops robust procedures, considers tail behavior in form of, e.g., extreme quantiles and investigates high-dimensional scenarios with many variables. The long-term goal is the development of robust monitoring tools for various classes of nonlinear spatio-temporal processes and for high-dimensional mixed-frequency data.

Project Leaders

Prof. Dr. Roland Fried
Department of Statistics - Chair of Mathematical Statistics and Applications in Science
TU Dortmund University

Prof. Dr. Vasyl Golosnoy
Faculty of Management and Economics - Chair of Statistics and Econometrics
Ruhr University Bochum

Summary

We develop novel methods for online monitoring of the validity and the stability of complex spatio-temporal models (STMs) with a particular focus on applications in energy and transport. Online monitoring is conducted using statistical decision rules (so-called control charts). These charts evaluate at every new time point whether the model is still adequate or not by comparing a control statistic to critical limits, which need to be chosen such that certain performance criteria are met concerning both the frequency of false alarms in the former and the detection delay in the latter case. By designing monitoring tools for STMs we confront the challenges of finding appropriate sparse statistical representations for these complex modeling scenarios and deriving their statistical properties. We consider STMs in various settings where we (a) incorporate autoregressive features for both space (e.g., the network structure) and time, (b) develop procedures that are robust with respect to restrictive distributional assumptions, (c) consider quantiles and the tail behaviour of spatial data, and (d) treat multivariate and high-dimensional settings and apply appropriate dimension reduction techniques for making STMs empirically tractable. Our methods will enable a timely detection of changes in STM parameters and more generally of model deficiencies. This is of essential importance for using such models in applications, in particular for adequate prediction.

Flossdorf, J., R. Fried, and C. Jentsch (2023). Online monitoring of dynamic networks using flexible multivariate control charts. Social Network Analysis and Mining 13, 489–502. doi: 10.1007/s13278-023-01091-y.

Golosnoy, V., B. Hildebrandt, S. Köhler, W. Schmid, et al. (2023). Control charts for measurement error models. AStA Advances in Statistical Analysis. doi: 10.1007/s10182-022-00462-8.

Lilienthal, J., L. Zanger, A. Bücher, and R. Fried (2022). A note on statistical tests for homogeneities in multivariate extreme value models for block maxima. Environmetrics 33. doi: 10.1002/env.2746.

Golosnoy, V., S. Köhler, W. Schmid, and M. Seifert (2021). Testing for parameter changes in linear state space models. Applied Stochastic Models in Business and Industry 37, 1060–1079. doi: 10.1002/asmb.2636.

Golosnoy, V. and M. Seifert (2021). Monitoring mean changes in persistent multivariate time series. Statistics 55, 475–488. doi: 10.1080/02331888.2021.1949013.

Abbas, S. and R. Fried (2020). Robust control charts for the mean of a locally linear time series. Journal of Statistical Computation and Simulation 90, 2741–2765. doi: 10.1080/00949655.2020.1788562.

Golosnoy, V., W. Schmid, M. I. Seifert, and T. Lazariv (2020). Statistical inferences for realized portfolio weights. Econometrics and Statistics 14, 49–62. doi: 10.1016/j.ecosta.2018.08.003.

Golosnoy, V. (2018). Sequential monitoring of portfolio betas. Statistical Papers 59, 663–684. doi: 10.1007/s00362-016-0783-6.

Lilienthal, J., R. Fried, and A. Schumann (2018). Homogeneity testing for skewed and cross-correlated data in regional flood frequency analysis. Journal of Hydrology 556, 557–571. doi: 10.1016/j.jhydrol.2017.10.056.

Borowski, M., D. Busse, and R. Fried (2015). Robust online-surveillance of trend-coherence in multivariate data streams: the similar trend monitoring (STM) procedure. Statistics and Computing 25, 913–928. doi: 10.1007/s11222-014-9462-4.