Alexander Schnurr
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Alexander Schnurr has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Sebastian Rickelhoff
Department of Mathematics University of Siegen Walter-Flex-Straße 3 D-57072 Siegen Germany
5 shared publications - Annika Betken
Faculty of Mathematics Ruhr-Universität Bochum
4 shared publications - Svenja Fischer
Wageningen University & Research
4 shared publications - Anita Behme
Institut für Mathematische Stochastik Technische Universität Dresden 01062 Dresden Germany
3 shared publications Herold Dehling
3 shared publicationsDaniel Schulte
Department of Mathematics University of Siegen 57068 Siegen Germany
2 shared publications
Latest Publications
- Open Access
- 1 August 2026
- Published by AIP Publishing in Chaos: An Interdisciplinary Journal of Nonlinear Science
- Vol. 36 (8)
Depth patterns and their applications in animal tracking
We establish a definition of ordinal patterns for multivariate data sets based on the concept of Tukey’s halfspace depth. Given the definition of these depth patterns, we are interested in the probabilities of observing specific patterns in time series. For this, we consider the relative frequency of depth patterns as natural estimators for their occurrence probabilities. Depending on the choice of reference distribution and the relation between reference and data distribution, we distinguish different settings that are considered separately. Within these settings, we study the statistical properties of depth pattern probabilities, establishing consistency and asymptotic normality under the assumption of weakly dependent time series. Since our concept depends only on ordinal depth information, the resulting values are robust under small perturbations and measurement errors. We emphasize the applicability of our method by analyzing the depth patterns, which are found in seal pubs’ movement. We use our approach in order to choose an appropriate model out of a range of two-dimensional random walks, which are commonly used in mathematical biology.
- 1 August 2026
- Published by AIP Publishing in Chaos: An Interdisciplinary Journal of Nonlinear Science
- Vol. 36 (8)
Open AccessDepth patterns and their applications in animal tracking
We establish a definition of ordinal patterns for multivariate data sets based on the concept of Tukey’s halfspace depth. Given the definition of these depth patterns, we are interested in the probabilities of observing specific patterns in time series. For this, we consider the relative frequency of depth patterns as natural estimators for their occurrence probabilities. Depending on the choice of reference distribution and the relation between reference and data distribution, we distinguish different settings that are considered separately. Within these settings, we study the statistical properties of depth pattern probabilities, establishing consistency and asymptotic normality under the assumption of weakly dependent time series. Since our concept depends only on ordinal depth information, the resulting values are robust under small perturbations and measurement errors. We emphasize the applicability of our method by analyzing the depth patterns, which are found in seal pubs’ movement. We use our approach in order to choose an appropriate model out of a range of two-dimensional random walks, which are commonly used in mathematical biology.
- Open Access
- 29 April 2024
- Published by Springer Nature in Statistics in Biosciences
- Vol. 17 (2) , 442-478
The Bayesian Group-Sequential Predictive Evidence Value Design for Phase II Clinical Trials with Binary Endpoints
In clinical research, the initial efficacy of a new agent is typically assessed in a phase IIA study. Bayesian group-sequential designs are often based on predictive probability of trial success. In this paper, the novel Bayesian group-sequential predictive evidence value design is introduced, and we prove that the predictive probability approach is a special case of it. A comparison with Simon’s two-stage and competing Bayesian designs based on phase IIA cancer trials is provided. Results show that the novel design can improve operating characteristics such as the false-positive rate, probability of early stopping for futility and expected sample size of the trial. Given these advantages, the predictive evidence value design constitutes an important addition to the biostatistician’s toolbelt when planning a phase IIA trial the Bayesian way, in particular, when small sample sizes and a large probability for early termination under the null hypothesis are desired.
- 29 April 2024
- Published by Springer Nature in Statistics in Biosciences
- Vol. 17 (2) , 442-478
Open AccessThe Bayesian Group-Sequential Predictive Evidence Value Design for Phase II Clinical Trials with Binary Endpoints
In clinical research, the initial efficacy of a new agent is typically assessed in a phase IIA study. Bayesian group-sequential designs are often based on predictive probability of trial success. In this paper, the novel Bayesian group-sequential predictive evidence value design is introduced, and we prove that the predictive probability approach is a special case of it. A comparison with Simon’s two-stage and competing Bayesian designs based on phase IIA cancer trials is provided. Results show that the novel design can improve operating characteristics such as the false-positive rate, probability of early stopping for futility and expected sample size of the trial. Given these advantages, the predictive evidence value design constitutes an important addition to the biostatistician’s toolbelt when planning a phase IIA trial the Bayesian way, in particular, when small sample sizes and a large probability for early termination under the null hypothesis are desired.
- Open Access
Fixing a Minor Mistake in the Theory of Stochastic Integration and Differential Equations
When considering stochastic integration and the theory of stochastic differential equations, P. Protter's textbook \cite{protter} undoubtedly is a main piece of standard literature. Not only is it well-written, but it also contains various profound results regarding these fields. Unfortunately, Theorem 12 of Chapter V, which presents an equivalence to uniform convergence on compacts in probability, is found to be incorrect. Given that numerous important results rely on this theorem, this paper aims to present a corrected version of it.
Open AccessFixing a Minor Mistake in the Theory of Stochastic Integration and Differential Equations
When considering stochastic integration and the theory of stochastic differential equations, P. Protter's textbook \cite{protter} undoubtedly is a main piece of standard literature. Not only is it well-written, but it also contains various profound results regarding these fields. Unfortunately, Theorem 12 of Chapter V, which presents an equivalence to uniform convergence on compacts in probability, is found to be incorrect. Given that numerous important results rely on this theorem, this paper aims to present a corrected version of it.
- Open Access
A Comparison of Different Representations of Ordinal Patterns and Their Usability in Data Analysis
We describe and analyze different approaches to represent ordinal patterns. All of these can be found in the literature. The most important representations (plus sub-classes) are compared in terms of their applicability from different angles. Namely we consider digital implementation, inverse patterns and ties between values. At the end we provide a guideline on which occasions which representation should be used.
Open AccessA Comparison of Different Representations of Ordinal Patterns and Their Usability in Data Analysis
We describe and analyze different approaches to represent ordinal patterns. All of these can be found in the literature. The most important representations (plus sub-classes) are compared in terms of their applicability from different angles. Namely we consider digital implementation, inverse patterns and ties between values. At the end we provide a guideline on which occasions which representation should be used.
- Open Access
Operator-stable-like Processes
In the present paper, we introduce so-called operator-stable-like processes. Roughly speaking, they behave locally like operator-stable processes, but they need not to be homogenous in space. Having shown existence for this class of processes, we analyze maximal estimates, the existence of moments, the short- and long-time behavior of the sample paths and $p$-variation. The class introduced here includes stable-like processes as special case.
Open AccessOperator-stable-like Processes
In the present paper, we introduce so-called operator-stable-like processes. Roughly speaking, they behave locally like operator-stable processes, but they need not to be homogenous in space. Having shown existence for this class of processes, we analyze maximal estimates, the existence of moments, the short- and long-time behavior of the sample paths and $p$-variation. The class introduced here includes stable-like processes as special case.
- Open Access
- 19 December 2023
- Published by Springer Nature in Journal of Theoretical Probability
- Vol. 37 (3) , 2508-2533
The Time-Dependent Symbol of a Non-homogeneous Itô Process and Corresponding Maximal Inequalities
The probabilistic symbol is defined as the right-hand side derivative at time zero of the characteristic functions corresponding to the one-dimensional marginals of a time-homogeneous stochastic process. As described in various contributions to this topic, the symbol contains crucial information concerning the process. When leaving time-homogeneity behind, a modification of the symbol by inserting a time component is needed. In the present article, we show the existence of such a time-dependent symbol for non-homogeneous Itô processes. Moreover, for this class of processes, we derive maximal inequalities which we apply to generalize the Blumenthal–Getoor indices to the non-homogeneous case. These are utilized to derive several properties regarding the paths of the process, including the asymptotic behavior of the sample paths, the existence of exponential moments and the finiteness of p-variationa. In contrast to many situations where non-homogeneous Markov processes are involved, the space-time process cannot be utilized when considering maximal inequalities.
- 19 December 2023
- Published by Springer Nature in Journal of Theoretical Probability
- Vol. 37 (3) , 2508-2533
Open AccessThe Time-Dependent Symbol of a Non-homogeneous Itô Process and Corresponding Maximal Inequalities
The probabilistic symbol is defined as the right-hand side derivative at time zero of the characteristic functions corresponding to the one-dimensional marginals of a time-homogeneous stochastic process. As described in various contributions to this topic, the symbol contains crucial information concerning the process. When leaving time-homogeneity behind, a modification of the symbol by inserting a time component is needed. In the present article, we show the existence of such a time-dependent symbol for non-homogeneous Itô processes. Moreover, for this class of processes, we derive maximal inequalities which we apply to generalize the Blumenthal–Getoor indices to the non-homogeneous case. These are utilized to derive several properties regarding the paths of the process, including the asymptotic behavior of the sample paths, the existence of exponential moments and the finiteness of p-variationa. In contrast to many situations where non-homogeneous Markov processes are involved, the space-time process cannot be utilized when considering maximal inequalities.
- Open Access
- 13 December 2023
- Published by Springer Nature in Stochastic Environmental Research and Risk Assessment
- Vol. 38 (4) , 1235-1249
Multivariate motion patterns and applications to rainfall radar data
The classification of movement in space is one of the key tasks in environmental science. Various geospatial data such as rainfall or other weather data, data on animal movement or landslide data require a quantitative analysis of the probable movement in space to obtain information on potential risks, ecological developments or changes in future. Usually, machine-learning tools are applied for this task, as these approaches are able to classify large amounts of data. Yet, machine-learning approaches also have some drawbacks, e.g. the often required large training sets and the fact that the algorithms are often hard to interpret. We propose a classification approach for spatial data based on ordinal patterns. Ordinal patterns have the advantage that they are easily applicable, even to small data sets, are robust in the presence of certain changes in the time series and deliver interpretative results. They therefore do not only offer an alternative to machine-learning in the case of small data sets but might also be used in pre-processing for a meaningful feature selection. In this work, we introduce the basic concept of multivariate ordinal patterns and the corresponding limit theorem. A simulation study based on bootstrap demonstrates the validity of the results. The approach is then applied to two real-life data sets, namely rainfall radar data and the movement of a leopard. Both applications emphasize the meaningfulness of the approach. Clearly, certain patterns related to the atmosphere and environment occur significantly often, indicating a strong dependence of the movement on the environment.
- 13 December 2023
- Published by Springer Nature in Stochastic Environmental Research and Risk Assessment
- Vol. 38 (4) , 1235-1249
Open AccessMultivariate motion patterns and applications to rainfall radar data
The classification of movement in space is one of the key tasks in environmental science. Various geospatial data such as rainfall or other weather data, data on animal movement or landslide data require a quantitative analysis of the probable movement in space to obtain information on potential risks, ecological developments or changes in future. Usually, machine-learning tools are applied for this task, as these approaches are able to classify large amounts of data. Yet, machine-learning approaches also have some drawbacks, e.g. the often required large training sets and the fact that the algorithms are often hard to interpret. We propose a classification approach for spatial data based on ordinal patterns. Ordinal patterns have the advantage that they are easily applicable, even to small data sets, are robust in the presence of certain changes in the time series and deliver interpretative results. They therefore do not only offer an alternative to machine-learning in the case of small data sets but might also be used in pre-processing for a meaningful feature selection. In this work, we introduce the basic concept of multivariate ordinal patterns and the corresponding limit theorem. A simulation study based on bootstrap demonstrates the validity of the results. The approach is then applied to two real-life data sets, namely rainfall radar data and the movement of a leopard. Both applications emphasize the meaningfulness of the approach. Clearly, certain patterns related to the atmosphere and environment occur significantly often, indicating a strong dependence of the movement on the environment.
- 9 November 2023
- Published by American Mathematical Society (AMS) in Transactions of the American Mathematical Society
- Vol. 377 (2) , 905-919
On the rôle of singular functions in extending the probabilistic symbol to its most general class
The probabilistic symbol is the right-hand side derivative of the characteristic functions corresponding to the one-dimensional marginals of a stochastic process. This object, as long as the derivative exists, provides crucial information concerning the stochastic process. For a Lévy process, one obtains the characteristic exponent while the symbol of a (rich) Feller process coincides with the classical symbol which is well known from the theory of pseudodifferential operators. Leaving these classes behind, the most general class of processes for which the symbol still exists are Lévy-type processes. It has been an open question, whether further generalizations are possible within the framework of Markov processes. We answer this question in the present article: within the class of Hunt semimartingales, Lévy-type processes are exactly those for which the probabilistic symbol exists. Leaving Hunt behind, one can construct processes admitting a symbol. However, we show, that the applicability of the symbol might be lost for these processes. Surprisingly, in our proofs the upper and lower Dini derivatives corresponding to certain singular functions play an important rôle.
- 9 November 2023
- Published by American Mathematical Society (AMS) in Transactions of the American Mathematical Society
- Vol. 377 (2) , 905-919
On the rôle of singular functions in extending the probabilistic symbol to its most general class
The probabilistic symbol is the right-hand side derivative of the characteristic functions corresponding to the one-dimensional marginals of a stochastic process. This object, as long as the derivative exists, provides crucial information concerning the stochastic process. For a Lévy process, one obtains the characteristic exponent while the symbol of a (rich) Feller process coincides with the classical symbol which is well known from the theory of pseudodifferential operators. Leaving these classes behind, the most general class of processes for which the symbol still exists are Lévy-type processes. It has been an open question, whether further generalizations are possible within the framework of Markov processes. We answer this question in the present article: within the class of Hunt semimartingales, Lévy-type processes are exactly those for which the probabilistic symbol exists. Leaving Hunt behind, one can construct processes admitting a symbol. However, we show, that the applicability of the symbol might be lost for these processes. Surprisingly, in our proofs the upper and lower Dini derivatives corresponding to certain singular functions play an important rôle.
- Open Access
On the rôle of singular functions in extending the probabilistic symbol to its most general class
The probabilistic symbol is the right-hand side derivative of the characteristic functions corresponding to the one-dimensional marginals of a stochastic process. This object, as long as the derivative exists, provides crucial information concerning the stochastic process. For a L\'evy process, one obtains the characteristic exponent while the symbol of a (rich) Feller process coincides with the classical symbol which is well known from the theory of pseudodifferential operators. Leaving these classes behind, the most general class of processes for which the symbol still exists are L\'evy-type processes. It has been an open question, whether further generalizations are possible within the framework of Markov processes. We answer this question in the present article: within the class of Hunt semimartingales, L\'evy-type processes are exactly those for which the probabilistic symbol exists. Leaving quasi-continuity behind, one can construct processes admitting a symbol. However, we show, that the applicability of the symbol might be lost for these processes. Surprisingly, in our proofs the upper and lower Dini derivatives corresponding to certain singular functions play an important r\^ole.
Open AccessOn the rôle of singular functions in extending the probabilistic symbol to its most general class
The probabilistic symbol is the right-hand side derivative of the characteristic functions corresponding to the one-dimensional marginals of a stochastic process. This object, as long as the derivative exists, provides crucial information concerning the stochastic process. For a L\'evy process, one obtains the characteristic exponent while the symbol of a (rich) Feller process coincides with the classical symbol which is well known from the theory of pseudodifferential operators. Leaving these classes behind, the most general class of processes for which the symbol still exists are L\'evy-type processes. It has been an open question, whether further generalizations are possible within the framework of Markov processes. We answer this question in the present article: within the class of Hunt semimartingales, L\'evy-type processes are exactly those for which the probabilistic symbol exists. Leaving quasi-continuity behind, one can construct processes admitting a symbol. However, we show, that the applicability of the symbol might be lost for these processes. Surprisingly, in our proofs the upper and lower Dini derivatives corresponding to certain singular functions play an important r\^ole.
- Open Access
The Time-Dependent Symbol of a Non-Homogeneous Itô Process and corresponding Maximal Inequalities
The probabilistic symbol is defined as the right-hand side derivative at time zero of the characteristic functions corresponding to the one-dimensional marginals of a time-homogeneous stochastic process. As described in various contributions to this topic, the symbol contains crucial information concerning the process. When leaving time-homogeneity behind, a modification of the symbol by inserting a time component is needed. In the present article we show the existence of such a time-dependent symbol for non-homogeneous Itô processes. Moreover, for this class of processes we derive maximal inequalities which we apply to generalize the Blumenthal-Getoor indices to the non-homogeneous case. These are utilized to derive several properties regarding the paths of the process, including the asymptotic behavior of the sample patsh, the existence of exponential moments and the finiteness of p-variation. In contrast to many situations where non-homogeneous Markov processes are involved, the space-time process cannot be utilized when considering maximal inequalities.
Open AccessThe Time-Dependent Symbol of a Non-Homogeneous Itô Process and corresponding Maximal Inequalities
The probabilistic symbol is defined as the right-hand side derivative at time zero of the characteristic functions corresponding to the one-dimensional marginals of a time-homogeneous stochastic process. As described in various contributions to this topic, the symbol contains crucial information concerning the process. When leaving time-homogeneity behind, a modification of the symbol by inserting a time component is needed. In the present article we show the existence of such a time-dependent symbol for non-homogeneous Itô processes. Moreover, for this class of processes we derive maximal inequalities which we apply to generalize the Blumenthal-Getoor indices to the non-homogeneous case. These are utilized to derive several properties regarding the paths of the process, including the asymptotic behavior of the sample patsh, the existence of exponential moments and the finiteness of p-variation. In contrast to many situations where non-homogeneous Markov processes are involved, the space-time process cannot be utilized when considering maximal inequalities.