Division of Statistics, Linköping University

Tuesday, May 12, 3.15 pm, 2026. Seminar in Mathematical Statistics.
The Risk Aversion Coefficient in the Tangency Portfolio: Statistical Insights from Normal and Skew-Normal Models
Stanislas Muhinyuza, School of Business and Economics, Linnæs University
Joint work with Muhammad Asif and Stepan Mazur (School of Business, Örebro University)
Abstract: The paper investigates the distributional properties of the sample estimator of the risk aversion coefficient in the tangency portfolio under two asset return models. The first model assumes that returns are independent and follow a multivariate normal distribution. The second model utilizes a matrix-variate closed skew-normal distribution to account for potential asymmetry and fat tails in the data. For both models, we derive the stochastic representation, as well as the mean, variance, and high-dimensional asymptotic distribution of the sample estimator. In addition, under the normality assumption, we obtain explicit expressions for the density and characteristic functions. The high-dimensional framework considers scenarios in which both the number of assets kn=k(n) and the sample size n tend to infinity, with their ratio cn=kn/n ⟶ c ∈ (0,1). A simulation study confirms that the proposed asymptotic distributions closely approximate the exact distributions even in finite samples, under both models.
Location: Hopningspunkten

The list of seminars in the series is available at http://www.ida.liu.se/divisions/stima/seminarier/StatSeminars.shtml .
Welcome! Krzysztof Bartoszek, Martin Singull

Tuesday, April 28, 1.30 pm (NEW TIME), 2026. Seminar in Statistics.
Quadratic subspaces in Statistics
Dietrich von Rosen, Department of Energy and Technology, Swedish University of Agricultural Sciences (SLU); and Department of Mathematics, Linköping University
Abstract:
Quadratic subspaces are useful, under a normality assumption, when estimating parameters in linearly structured covariance matrices when also their inverses are linearly structured. Different kind of applications will be considered. Location: Alan Turing .
The list of seminars in the series is available at http://www.ida.liu.se/divisions/stima/seminarier/StatSeminars.shtml .
Welcome! Krzysztof Bartoszek, Martin Singull

Tuesday, April 14, 3.15 pm, 2026. Seminar in Mathematical Statistics.
Some perspectives on separable covariance matrices
Joni Virta, Department of Mathematics and Statistics, University of Turku
Abstract: Separable (Kronecker) covariance structures are a widely used model for data with multiple modalities, e.g., samples of images or observations indexed by both temporal and measurement dimensions. In this talk, we give an overview of the separable covariance framework, covering its motivation, properties, and standard approaches to its estimation. We then discuss the problem of testing the separability assumption, including a recent extension to elliptical matrix-variate data. Finally, we explore Kronecker-core decompositions as a diagnostic tool for understanding deviations from separability. The talk assumes no prior familiarity with the topic.
Location: Hopningspunkten
The list of seminars in the series is available at http://www.ida.liu.se/divisions/stima/seminarier/StatSeminars.shtml .
Welcome! Krzysztof Bartoszek, Martin Singull

Friday, March 20, 2.00 pm , 2026. Seminar in Statistics, jointly with the Stochastic differential equations with R workshop ( https://www.ida.liu.se/~krzba67/include/YUIMA_2026LiU.html ).
Sparse Bayesian learning for inverse problems: Models, inference, and open problems
Jan Glaubitz, Department of Mathematics, Linköping University
Abstract:https://www.ida.liu.se/divisions/stima/seminarier/Abstracts/Glaubitz_Linkoping_YUIMA_seminar.pdf
Location: Ada Lovelace .
The list of seminars in the series is available at http://www.ida.liu.se/divisions/stima/seminarier/StatSeminars.shtml .
Welcome! Krzysztof Bartoszek, Martin Singull

IDA: Seminars in Statistics and Mathematical Statistics

Friday, March 20, 1.30 pm , 2026. Seminar in Statistics, jointly with the Stochastic differential equations with R workshop ( https://www.ida.liu.se/~krzba67/include/YUIMA_2026LiU.html ).
Diffusion differentiable resampling
Zheng Zhao Department of Computer and Information Science, Linköping University
Abstract: This work is concerned with differentiable resampling in the context of sequential Monte Carlo (e.g., particle filtering). We propose a new informative resampling method that is instantly differentiable, based on an ensemble score stochastic differential equation. We theoretically prove that our diffusion resampling method provides a consistent resampling distribution, and we show empirically that it outperforms the state-of-the-art differentiable resampling methods on multiple filtering and parameter estimation benchmarks. Finally, we show that it achieves competitive end-to-end performance when used in learning a complex dynamics-decoder model with high-dimensional image observations.
Location: Ada Lovelace .
The list of seminars in the series is available at http://www.ida.liu.se/divisions/stima/seminarier/StatSeminars.shtml .
Welcome! Krzysztof Bartoszek, Martin Singull

IDA: Seminars in Statistics and Mathematical Statistics

Thursday, March 19, 4.00 pm , 2026. Seminar in Statistics, jointly with the Stochastic differential equations with R workshop ( https://www.ida.liu.se/~krzba67/include/YUIMA_2026LiU.html ).
Asymptotic expansion (implementation in Python)
Emanuele Guidotti , Institute of Finance, University of Lugano (USI), Department of Wealth Creation, Lake Lucerne Institute
Abstract: A comprehensive framework is presented for constructing analytical approximations of functionals of diffusion processes using asymptotic expansions in small noise regimes. Building on the Malliavin calculus, high-order expansions are derived for the probability density function, cumulative distribution function, characteristic function, moments, and quantile function of general diffusion processes. The method systematically develops these expansions for joint, marginal, and conditional distributions. A formal computational scheme is proposed to compute expansion formulas of arbitrary order. This approach allows accurate approximations in models where direct analytical solutions are unavailable, and it is broadly applicable to problems in mathematical finance, filtering, and inference for stochastic systems. Implementation details in Python will be discussed, together with interoperability layers connecting Python code to R and YUIMA.
Location: Ada Lovelace .
The list of seminars in the series is available at http://www.ida.liu.se/divisions/stima/seminarier/StatSeminars.shtml .
Welcome! Krzysztof Bartoszek, Martin Singull

IDA: Seminars in Statistics and Mathematical Statistics

Wednesday, March 18, 4.00 pm , 2026. Seminar in Statistics, jointly with the Stochastic differential equations with R workshop ( https://www.ida.liu.se/~krzba67/include/YUIMA_2026LiU.html ).
On lead-lag estimation of non-synchronously observed point processes
Yuta Koike , Graduate School of Mathematical Sciences, University of Tokyo
Abstract: We introduce a new theoretical framework for analyzing lead-lag relationships between point processes, with a special focus on applications to high-frequency financial data. In particular, we are interested in lead-lag relationships between two sequences of order arrival timestamps. The seminal work of Dobrev and Schaumburg proposed model-free measures of cross-market trading activity based on cross-counts of timestamps. While their method is known to yield reliable results, it faces limitations because its original formulation inherently relies on discrete-time observations, an issue we address in this study. Specifically, we formulate the problem of estimating lead-lag relationships in two point processes as that of estimating the shape of the cross-pair correlation function (CPCF) of a bivariate stationary point process, a quantity well-studied in the neuroscience and spatial statistics literature. Within this framework, the prevailing lead-lag time is defined as the location of the CPCF's sharpest peak. Under this interpretation, the peak location in Dobrev and Schaumburg's cross-market activity measure can be viewed as an estimator of the lead-lag time in the aforementioned sense. We further propose an alternative lead-lag time estimator based on kernel density estimation and show that it possesses desirable theoretical properties and delivers superior numerical performance. Empirical evidence from high-frequency financial data demonstrates the effectiveness of our proposed method.
Location: Ada Lovelace .
The list of seminars in the series is available at http://www.ida.liu.se/divisions/stima/seminarier/StatSeminars.shtml .
Welcome! Krzysztof Bartoszek, Martin Singull

IDA: Seminars in Statistics and Mathematical Statistics

Tuesday, February 10, 1.30 pm (NEW TIME), 2026. Seminar in Statistics.
Beyond Tree Models: Mathematics of Reticulate Evolution
Joan Carles Pons Mayol, Computational Biology and Bioinformatics, Department of Mathematics and Computer Science, University of the Balearic Islands
Abstract: Accumulating evidence from genomics and metagenomics shows that evolutionary histories often involve reticulate events (hybridisation, recombination, horizontal gene transfer) that cannot be captured by trees, motivating the use of phylogenetic networks. In this talk I will outline the NET-INSIGHT project, which develops mathematical and algorithmic foundations for working with such networks via invariant-based representations, image characterisations that decide when an invariant is realisable by a network, and principled consensus constructions that summarise multiple reconstructions within structured network classes. I will also highlight an analytic-combinatorics perspective for enumeration and random generation of phylogenetic networks. Finally, the project explores the potential of machine-learning techniques as complementary tools, in particular for completing partially observed invariants and for learning consensus behaviour from collections of networks.
Location: Alan Turing .
The list of seminars in the series is available at http://www.ida.liu.se/divisions/stima/seminarier/StatSeminars.shtml .
Welcome! Krzysztof Bartoszek, Martin Singull

Tuesday, January 27, 1.30 pm (NEW TIME), 2026. Seminar in Statistics.
Estimating Abilities with an Elo-Informed Growth Model
Karl Sigfrid, Department of Statistics, Stockholm University
Abstract: An intelligent tutoring system aims to provide instructions and exercises tailored to the student's current level, and therefore needs to track the student's ability. Ability estimates can be updated based on the outcomes of practice exercises that are part of the learning process. We propose a new method for tracking abilities, based on the assumption that the abilities for a group of respondents who are all in the same stage of the learning process follow a distribution that can be estimated. Comparisons using both simulated data and real learning data show that the proposed method performs better than the standard Elo algorithm in a scenario with rapid ability growth. The method can lower the threshold for implementing robust intelligent tutoring systems.
Location: John von Neumann . (DIFFERENT ROOM)
The list of seminars in the series is available at http://www.ida.liu.se/divisions/stima/seminarier/StatSeminars.shtml .
Welcome! Krzysztof Bartoszek, Martin Singull

At the Division of Statistics, Linköping University , Sweden we have put out an announcement for a PhD student in Statistics position related to phylogenetic comparative methods (mathematically branching stochastic processes, esp. stochastic differential equations):

https://liu.se/en/work-at-liu/vacancies/28230

I would be grateful for spreading it out to anyone who could be interested. And of course I encourage everyone interested to apply!

Merry Christmas and a Happy New Year!

PhD student in Statistics We are looking for a PhD student in Statistics with placement at the Division of Statistics and Machine Learning, Department of Computer and Information Science.

At the Division of Statistics and Machine Learning, Department of Computer and Information Science, Linköping University, Sweden, 17th-20th March 2026, we will be hosting a workshop concerning stochastic differential equations and the YUIMA R package (Simulation and Inference for SDEs and Other Stochastic Processes, https://cran.r-project.org/web/packages/yuima/index.html ). The lectures will be given by members of the YUIMA team. The dates are fixed.
A similar event took place in summer 2019: https://yuimaproject.com/yss2019/ and in March 2023 in Linkoping.

Please feel free to spread information about the event around. If anyone would be interested in coming, they should e-mail Krzysztof Bartoszek directly (email is on the workshop's webpage). The registration deadline is 28th February 2026. However, we might end registration early if the number of interested participants exceeds our capacity.

PhD-students can choose to take an examination to obtain 3credits for the event. Examination will be through a hand-in assignment. Please let us know if you would be interested in this option.

We assume the participants are familiar with R. We are finalizing the programme but it will include:
Introduction to stochastic calculus (stochastic processes, Brownian motion, stochastic integral and SDE),
Simulation of diffusion processes I (Euler-Maruyama approximation and introduction to YUIMA: yuima object, simulation, plot,
Black-Scholes model), Poisson process and Compound Poisson processes, Inference for diffusion processes
(QMLE, quasi-Bayes estimation), Model selection for diffusion processes, YUIMA GUI, Levy processes and Levy driven SDE.
The final programme will be announced in due course of time.

The contents will include basic facts, laboratory sessions (participants work on their own laptops),
and more advanced research-oriented talks. If you have a related research topic and would be interested in presenting,
then please let us know.

More information on the workshop will be made available at https://www.ida.liu.se/~krzba67/include/YUIMA_2026LiU.html .

Stochastic differential equations with R workshop