Scientific Data Services

Talk on "Breaking up is hard (to model): Joint models for longitudinal and time-to-event data on divorce data and rare events"

Scientific Data Services — Thu, 13 Nov 2025 14:07:38 +0100

"Breaking up is hard (to model): Joint models for longitudinal and time-to-event data on divorce data and rare events" is the title of Sophie Potts talk, which is being organised by the "Zentrum of Statistik" at Bielefeld University. It will take place on Tuesday, 18 November 2025 from 12:00 - 13:00 in W9-109.

In time-to-event analyses in social sciences, endogenous time-varying variables often occur, where the event status is correlated with the covariate’s trajectory. Ignoring this causes biased estimates. In biostatistics, this is addressed with joint models for longitudinal and time-to-event data, which handle endogeneity correctly. Despite their usefulness, joint models remain rare in social sciences. We give an introduction to this method, highlight its advantages for social sciences, and demonstrate it with an example on marital satisfaction and dissolution, comparing results with classical time-to-event models. In a second part, we address rare events in joint models. Standard estimation struggles with few events and imbalanced designs, leading to monotone likelihood. Firth’s correction, which adjusts the score function, provides stable estimates even with very small event counts. We extend this correction to joint models, enabling their use in rare event studies, particularly in observational data where event numbers cannot be controlled.

Talk on "The more, the merrier: the role of exogeneity in global state space models"

Scientific Data Services — Tue, 28 Oct 2025 14:16:53 +0100

"The more, the merrier: the role of exogeneity in global state space models" is the title of Prof. Dr. Dietmar Bauer talk, which is being organised by the "Zentrum of Statistik" at Bielefeld University. It will take place on Tuesday, 4 November 2025 from 12:00 - 13:00 in W9-109.

Often multivariate time series data has matrix time series structure such that at each point in time the same variables are observed for a number of individual entities. Joint unrestricted modelling using vector autoregressions (VAR) contains a prohibitively large number of parameters. This can be countered in a number of fashions (for example, MaTS, aDFM, Bayesian VARs). These approaches, however, do not include structural information on the relations between the various individuals. The global VAR approach of Pesaran and co-workers provides a different idea: It partitions the model into regional models, each of which is estimated and specified separately, allowing for the imposition of structural relations. Partitioning uses heavily different exogeneity concepts. In this talk we examine the implications of these exogeneity concepts. We also propose how to proceed, if exogeneity is violated.

Talk on "Data-Driven Approaches for Reducing Food Waste in Grocery Retailing"

Scientific Data Services — Tue, 14 Oct 2025 14:39:28 +0200

"Data-Driven Approaches for Reducing Food Waste in Grocery Retailing" is the title of Dr. David Winkelmann talk, which is being organised by the "Zentrum of Statistik" at Bielefeld University. It will take place on Tuesday, 21 October 2025 from 12:00 - 13:00 in W9-109.

Grocery retailers face the trade-off between overstocking, potentially generating food waste, and risking customer dissatisfaction through stock outs. To ensure high service levels, many retailers accept excess inventory, contributing to the approximately 11 million tons of food discarded annually in Germany, over 10% of which originates in the retail sector. In collaboration with the German government, major retailers have therefore committed to halving food waste by 2030. Achieving this goal requires more accurate demand forecasts that capture operational complexities. While demand forecasting has been widely studied by the scientific literature, specific challenges remain. For example, retailers frequently apply price reductions to units nearing expiration: such discounts stimulate short-term customer demand and mitigate the risk for food waste, but if these inflated sales figures are not modelled appropriately, forecasts systematically overestimate future demand and perpetuate overstocking. Using data from a major European grocery retailer, this study aims to contribute to the reduction of food waste in the retail sector by improving forecasts for these specific challenges.

Talk on "New directions for knowledge tracing models"

Scientific Data Services — Thu, 3 Jul 2025 20:46:13 +0200

"New directions for knowledge tracing models" is the title of Prof. Dr. Benjamin Paaßen talk, which is being organised by the "Zentrum of Statistik" at Bielefeld University. It will take place on Tuesday, 8 July 2025 from 12:00 Uhr - 13:00 in W9-109.

Knowledge Tracing (KT) is the attempt to estimate student learning from observed behavior over time. This is typically performed with latent variable models (especially Hidden Markov Models) where the latent variable is student learning and the observed variable are data acquired from student behavior in e-learning systems, especially their success on exercises. The talk will introduce KT, cover the most prominent classic KT models, shortly discuss current machine learning research into KT, and propose potential new directions for KT research that is more compelling both from a modeling perspective and from the perspective of educational utility.

ReproducibiliTea Meeting

Scientific Data Services — Tue, 1 Jul 2025 15:15:48 +0200

“ReproducibiliTea” is an informal meeting of scholars interested in topics such as Open Science, reproducible research, and good scientific practice. It is organized by Katja Politt at the Bielefeld University. It will take place on Friday, 4 July 2025 at 12:00 (noon) in V4-116.

“ReproducibiliTea” is a monthly informal meeting, focused on topics such as Open Science, reproducible research and good scientific practice.

Each session features a group discussion of a selected paper. The discussion can take place in either English or German. The paper for the present discussion is:

"The role of environmental ethics and sustainability in research ethics for linguistics: what is currently available in terms of guidance and how might that be improved?" by Eisenbeiß et al. (2025) (https://doi.org/10.1515/ling-2023-0203 ).

Everybody is welcome to join and discuss, the participation is also possible via Zoom, the Zoom link can be found at https://burst.pages.ub.uni-bielefeld.de/burst/.

Talk on "Estimation of Latent Group Structures in Time-Varying Panel Data Models"

Scientific Data Services — Tue, 24 Jun 2025 23:13:51 +0200

"Estimation of Latent Group Structures in Time-Varying Panel Data Models" is the title of Paul Heimerl talk, which is being organised by the "Zentrum of Statistik" at Bielefeld University. It will take place on Tuesday, 24 June 2025 from 12:00 Uhr - 13:00 Uhr in W9-109.

We introduce a panel data model where coefficients vary both over time and the cross-section. Slope coefficients change smoothly over time and follow a latent group structure, being homogeneous within but heterogeneous across groups. The group structure is identified using a pairwise adaptive group fused-Lasso penalty. The trajectories of time-varying coefficients are estimated via polynomial spline functions. We derive the asymptotic distributions of the penalized and post-selection estimators and show their oracle efficiency. A simulation study demonstrates excellent finite sample properties. An application to the pace of microclimate change highlights the relevance of addressing cross-sectional heterogeneity and time-variance in empirical settings.

Talk on "More on Uncertainty in Machine Learning"

Scientific Data Services — Thu, 5 Jun 2025 23:18:38 +0200

"More on Uncertainty in Machine Learning" is the title of Prof. Dr. Göran Kauermann talk, which is being organised by the "Zentrum of Statistik" at Bielefeld University. It will take place on Tuesday, 10 June 2025 from 12:00 Uhr - 13:00 Uhr in W9-109.

The quantification of uncertainty is continuously gaining interest in the machine learning community. Tackling this question can be done with statistical tools, getting back to the foundation of statistics, namely how to cope with uncertainty and ignorance. The talk extends our previous work on this topic and presents some new results and insights. We discuss different sources of uncertainty and advocate an increased use of statistics and statistical methods in the machine learning world. To showcase our view we look at ambiguity in computer linguistics, we sketch the use of statistics in network weight reconstruction and focus on labelling ambiguity. While these examples are heterogeneous, the data centric view and hence its statistical foundation serves as common thread.

Talk on "Advances in gradient boosting approaches for geoadditive models"

Scientific Data Services — Wed, 21 May 2025 13:06:02 +0200

"Advances in gradient boosting approaches for geoadditive models" is the title of Lars Knieper talk, which is being organised by the "Zentrum für Statistik" at Bielefeld University. It will take place on Tuesday, 27 May 2025 from 12:00 to 13:00 in W9-109.

One of the key features of model-based component-wise gradient boosting is a data-driven variable selection mechanism which takes place while estimating the effects simultaneously. When spatial effects, of areal or point-reference data, are included as a potential model-component a drastic increase of chosen fixed effects can be observed. This is accompanied by a high selection frequency of the spatial component without achieving an impactful reduction of the loss function. To address this ineffective variable selection, we propose to eliminate the competition between fixed and spatial effects by separating the spatial part from the component-wise mechanism and ensuring complete estimation in each iteration. Additionally, we suggest using spatial cross-validation, which accounts for the auto-correlated structure of spatial data when constructing folds. Our approach is applied to yield deviation estimates of coffee farmers in Colombia, resulting in a sparser model with improved predictive performance. In addition, there will be an extended outlook on spatial confounding—an estimation bias arising from collinearity between fixed and spatial effects—which tends to be more pronounced in gradient boosting than in maximum likelihood approaches. A straightforward remedy, known as Spatial+, proves effective in mitigating this issue.

Talk on "Insights from cognitive neuroscience – statistical models to understand behavior"

Scientific Data Services — Wed, 7 May 2025 22:55:58 +0200

"Insights from cognitive neuroscience – statistical models to understand behavior" is the title of Prof. Dr. Christoph Kayser talk, which is being organised by the "Zentrum of Statistik" at Bielefeld University. It will take place on Tuesday, 13 May 2025 from 12:00 Uhr - 13:00 Uhr in W9-109.

In this talk I will present studies on how we (and our brain) combine multisensory signals to guide behavior. The talk will focus on examples such as spatial ventriloquism and multisensory perceptual decision making, but also speak more broadly about how well we can explain behavior in typical laboratory tasks. The goal of the presentation is to illustrate the different types of statistical models employed in these studies, including Bayesian approaches and drift-diffusion (random walk) models and how they can be used to understand behavior, but also how we can link them to neural processes in the brain.

Talk on "When to Collect Data? A Sobol Index Strategy for Model-Based Experimental Design"

Scientific Data Services — Fri, 25 Apr 2025 19:54:46 +0200

“When to Collect Data? A Sobol Index Strategy for Model-Based Experimental Design” is the title of Houda Yaqine talk, which is being organised by the "Zentrum für Statistik" at Bielefeld University. It will take place on Tuesday, 29 April 2025 from 12:00 to 13:00 in W9-109.

Optimizing measurement timing in experimental studies is crucial for reducing animal sacrifices, especially when investigating systems characterized by ordinary differential equations (ODEs). Conventional sampling strategies frequently collect excessive data points without substantially improving parameter estimation accuracy. Our research introduces a new experimental design framework that analyzes the temporal evolution of variance-based sensitivities in ODE-driven processes. By integrating time-dependent Sobol indices with underlying system dynamics, this approach identifies the most informative sampling points, particularly during phases where parameter interactions are the primary contributors to system variance. Both theoretical analyses and computational experiments confirm that our strategically selected measurement times yield better parameter estimation outcomes compared to traditional protocols.

Talk on “Bayesian Penalized Transformation Models for Structured Additive Regression on the Location and Scale of Arbitrary Distributions“

Scientific Data Services — Thu, 9 Jan 2025 12:11:34 +0100

“Bayesian Penalized Transformation Models for Structured Additive Regression on the Location and Scale of Arbitrary Distributions” is the title of Johannes Brachem's lecture, which is being organised by the "Zentrum für Statistik" at Bielefeld University. It will take place on Tuesday, 14 January 2025 from 12:00 to 13:00 in W9-109.

Penalized transformation models (PTMs) are a novel form of distribution-free location-scale regression. In PTMs, the shape of the response’s conditional distribution is estimated directly from the data, and structured additive predictors are placed on its location and scale. The core of the model is a monotonically increasing transformation function that relates the response distribution to a reference distribution. The transformation function is equipped with a smoothness prior that regularizes how much the estimated distribution diverges from the reference distribution. These models can be seen as a bridge between conditional transformation models and generalized additive models for location, scale and shape. Markov chain Monte Carlo inference for PTMs can be conducted with the No-U-Turn sampler and offers straightforward uncertainty quantification for the conditional distribution as well as for the covariate effects.

Talk on "The Sum Score Model: Specifying and Testing Equally Weighted Composites Using Structural Equation Modeling"

Scientific Data Services — Sun, 14 Jul 2024 10:52:48 +0200

"The Sum Score Model: Specifying and Testing Equally Weighted Composites Using Structural Equation Modeling" is the title of Dr. Tamara Schamberger's lecture, which is being organised by the "Zentrum für Statistik" at Bielefeld University. It will take place on Tuesday, 16 July 2024 from 12:00 to 13:00 in W9-109. Dr. Schamberger will present a new method for incorporating sum scores into structural equation modelling (SEM). The approach overcomes current limitations, replicates results of existing methods, and accounts for random measurement errors in the variables forming the sum score.

Talk on Modified Nonlinear Least Squares Estimation and Inference - ZeSt Colloquium

Scientific Data Services — Mon, 12 Jun 2023 14:34:12 +0200

Karsten Reichold from the Department of Statistics at the Technical University of Dortmund will give a talk on "Smooth Transition Cointegrating Regressions: Modified Nonlinear Least Squares Estimation and Inference" at the ZeSt Colloquium. The talk will take place on Tuesday, 13 June 2023 from 12:00 to 13:00 at the University of Bielefeld, room W9-109.

more...