Model-based recursive partitioning (MOB) is a semi-parametric statistical approach allowing the identification of subgroups that can be combined with a broad range of outcome measures including continuous time-to-event outcomes. When time is measured on a discrete scale, methods and models need to account for this discreetness as otherwise subgroups might be spurious and effects biased. The test underlying the splitting criterion of MOB, the M-fluctuation test, assumes independent observations. However, for fitting discrete time-to-event models the data matrix has to be modified resulting in an augmented data matrix violating the independence assumption. We propose MOB for discrete Survival data (MOB-dS) which controls the type I error rate of the test used for data splitting and therefore the rate of identifying subgroups although none is present. MOB-ds uses a permutation approach accounting for dependencies in the augmented time-to-event data to obtain the distribution under the null hypothesis of no subgroups being present. Through simulations we investigate the type I error rate of the new MOB-dS and the standard MOB for different patterns of survival curves and event rates. We find that the type I error rates of the test is well controlled for MOB-dS, but observe some considerable inflations of the error rate for MOB. To illustrate the proposed methods, MOB-dS is applied to data on unemployment duration.
Method comparisons are essential to provide recommendations and guidance for applied researchers, who often have to choose from a plethora of available approaches. While many comparisons exist in the literature, these are often not neutral but favour a novel method. Apart from the choice of design and a proper reporting of the findings, there are different approaches concerning the underlying data for such method comparison studies. Most manuscripts on statistical methodology rely on simulation studies and provide a single real-world data set as an example to motivate and illustrate the methodology investigated. In the context of supervised learning, in contrast, methods are often evaluated using so-called benchmarking data sets, i.e. real-world data that serve as gold standard in the community. Simulation studies, on the other hand, are much less common in this context. The aim of this paper is to investigate differences and similarities between these approaches, to discuss their advantages and disadvantages and ultimately to develop new approaches to the evaluation of methods picking the best of both worlds. To this aim, we borrow ideas from different contexts such as mixed methods research and Clinical Scenario Evaluation.
The research on and application of artificial intelligence (AI) has triggered a comprehensive scientific, economic, social and political discussion. Here we argue that statistics, as an interdisciplinary scientific field, plays a substantial role both for the theoretical and practical understanding of AI and for its future development. Statistics might even be considered a core element of AI. With its specialist knowledge of data evaluation, starting with the precise formulation of the research question and passing through a study design stage on to analysis and interpretation of the results, statistics is a natural partner for other disciplines in teaching, research and practice. This paper aims at contributing to the current discussion by highlighting the relevance of statistical methodology in the context of AI development. In particular, we discuss contributions of statistics to the field of artificial intelligence concerning methodological development, planning and design of studies, assessment of data quality and data collection, differentiation of causality and associations and assessment of uncertainty in results. Moreover, the paper also deals with the equally necessary and meaningful extension of curricula in schools and universities.