Biometrical Journal

Benedetti, Marco H.; Lu, Bo; Zhu, Motao

doi: 10.1002/bimj.70012pmid: 39607313

A concern surrounding marijuana legalization is that driving after marijuana use may become more prevalent. Survey data are valuable for estimating policy effects, however their observational nature and unequal sampling probabilities create challenges for causal inference. To estimate population‐level effects using survey data, we propose a matched design and implement sensitivity analyses to quantify how robust conclusions are to unmeasured confounding. Both theoretical justification and simulation studies are presented. We found no support that marijuana legalization increased tolerant behaviors and attitudes toward driving after marijuana use, and these conclusions seem moderately robust to unmeasured confounding.

Nassiri, Vahid; Tekle, Fetene; Tatikola, Kanaka; Geys, Helena

doi: 10.1002/bimj.70004pmid: 39555694

Class imbalance is a known issue in classification tasks that can lead to predictive bias toward dominant classes. This paper introduces a novel straightforward Bayesian framework that adjusts posterior probabilities to counteract the bias introduced by imbalanced data sets. Instead of relying on the mean posterior distribution of class probabilities, we propose a method that scales the posterior probability of each class according to their representation in the training data.

Dattner, Itai; Gugushvili, Shota; Laskorunskyi, Oleksandr

doi: 10.1002/bimj.70013pmid: 39607306

Ordinary differential equations (ODEs) are foundational tools in modeling intricate dynamics across a gamut of scientific disciplines. Yet, a possibility to represent a single phenomenon through multiple ODE models, driven by different understandings of nuances in internal mechanisms or abstraction levels, presents a model selection challenge. This study introduces a testing‐based approach for ODE model selection amidst statistical noise. Rooted in the model misspecification framework, we adapt classical statistical paradigms (Vuong and Hotelling) to the ODE context, allowing for the comparison and ranking of diverse causal explanations without the constraints of nested models. Our simulation studies numerically investigate the statistical properties of the test, demonstrating its attainment of the nominal size and power across various settings. Real‐world data examples further underscore the algorithm's applicability in practice. To foster accessibility and encourage real‐world applications, we provide a user‐friendly Python implementation of our model selection algorithm, bridging theoretical advancements with hands‐on tools for the scientific community.

Golchi, Shirin; Willard, James J.

doi: 10.1002/bimj.70002pmid: 39473126

Bayesian inference and the use of posterior or posterior predictive probabilities for decision making have become increasingly popular in clinical trials. The current practice in Bayesian clinical trials relies on a hybrid Bayesian‐frequentist approach where the design and decision criteria are assessed with respect to frequentist operating characteristics such as power and type I error rate conditioning on a given set of parameters. These operating characteristics are commonly obtained via simulation studies. The utility of Bayesian measures, such as “assurance,” that incorporate uncertainty about model parameters in estimating the probabilities of various decisions in trials has been demonstrated. However, the computational burden remains an obstacle toward wider use of such criteria. In this article, we propose methodology which utilizes large sample theory of the posterior distribution to define parametric models for the sampling distribution of the posterior summaries used for decision making. The parameters of these models are estimated using a small number of simulation scenarios, thereby refining these models to capture the sampling distribution for small to moderate sample size. The proposed approach toward the assessment of conditional and marginal operating characteristics and sample size determination can be considered as simulation‐assisted rather than simulation‐based. It enables formal incorporation of uncertainty about the trial assumptions via a design prior and significantly reduces the computational burden for the design of Bayesian trials in general.

Colicino, Elena; Ascari, Roberto; Saddiki, Hachem; Merced‐Nieves, Francheska; Foppa Pedretti, Nicolò; Huddleston, Kathi; Wright, Robert O; Wright, Rosalind J; ,

doi: 10.1002/bimj.202300270pmid: 39473136

doi: 10.1002/bimj.202470008pmid: N/A

Li, Isabel; Ma, Jun; Liquet, Benoit

doi: 10.1002/bimj.202300203pmid: 39508209

In practical survival analysis, the situation of no event for a patient can arise even after a long period of waiting time, which means a portion of the population may never experience the event of interest. Under this circumstance, one remedy is to adopt a mixture cure Cox model to analyze the survival data. However, if there clearly exhibits an acceleration (or deceleration) factor among their survival times, then an accelerated failure time (AFT) model will be preferred, leading to a mixture cure AFT model. In this paper, we consider a penalized likelihood method to estimate the mixture cure semiparametric AFT models, where the unknown baseline hazard is approximated using Gaussian basis functions. We allow partly interval‐censored survival data which can include event times and left‐, right‐, and interval‐censoring times. The penalty function helps to achieve a smooth estimate of the baseline hazard function. We will also provide asymptotic properties to the estimates so that inferences can be made on regression parameters and hazard‐related quantities. Simulation studies are conducted to evaluate the model performance, which includes a comparative study with an existing method from the smcure R package. The results show that our proposed penalized likelihood method has acceptable performance in general and produces less bias when faced with the identifiability issue compared to smcure. To illustrate the application of our method, a real case study involving melanoma recurrence is conducted and reported. Our model is implemented in our R package aftQnp which is available from https://github.com/Isabellee4555/aftQnP.

Unseld, Theresa; Bluhmki, Tobias; Beyersmann, Jan; Beck, Evelin; Padberg, Stephanie; Stegherr, Regina

doi: 10.1002/bimj.202400083pmid: 39470119

Landmarking is an alternative to complex multistate models when the aim is to calculate dynamic predictions. We develop the concept of landmarking for the case of left truncation and competing risks from the application background of drug safety assessment in pregnancy. The method is illustrated with a cohort study of the German Embryotox Pharmacovigilance Institute in Berlin to assess if the risk or the cumulative incidence of adverse pregnancy outcomes, like spontaneous abortions (SABs), is increased in fluoroquinolone‐exposed women. Furthermore, we conduct an extensive simulation study to compare the dynamic predictions and coefficient estimates obtained by landmarking to those from nonparametric multistate models and classical time‐dependent covariate Cox regression. The results from the simulation study indicate that attenuation of the effects is present in the landmark estimates, also in the complex setting considered here, but the estimates are still close to those from the multistate models. Regarding the Berlin fluoroquinolone data, the fluoroquinolone exposure of a pregnant woman in the first trimester seems to increase her cumulative incidence of elective termination of pregnancy over women never exposed before, but there is no evidence of a significantly increased risk or cumulative incidence in exposed women for SABs. This supports previous results on the same data, which were driven from an analysis without landmarking methods.

Micheloud, Charlotte; Held, Leonhard

doi: 10.1002/bimj.202300232pmid: 39473139

Replication studies are increasingly conducted to assess the credibility of scientific findings. Most of these replication attempts target studies with a superiority design, but there is a lack of methodology regarding the analysis of replication studies with alternative types of designs, such as equivalence. In order to fill this gap, we propose two approaches, the two‐trials rule and the sceptical two one‐sided tests (TOST) procedure, adapted from methods used in superiority settings. Both methods have the same overall Type‐I error rate, but the sceptical TOST procedure allows replication success even for nonsignificant original or replication studies. This leads to a larger project power and other differences in relevant operating characteristics. Both methods can be used for sample size calculation of the replication study, based on the results from the original one. The two methods are applied to data from the Reproducibility Project: Cancer Biology.

Chen, Jinmei; Li, Lixin; Feng, Yuhao; Chow, Shein‐Chung; Tan, Ming; Pan, Jianhong; Chen, Pingyan; Wu, Ying

doi: 10.1002/bimj.70003pmid: 39555687

External data (e.g., real‐world data (RWD) and historical data) have become more readily available. This has led to rapidly increasing interest in exploring and evaluating ways of utilizing external data to facilitate traditional clinical trials (TCT), especially for rare diseases with high unmet medical needs where a TCT would be impractical and/or unethical. In this article, we focus on hybrid studies that incorporate external data into randomized clinical trials to augment the control arm and explore a complex innovative design. A sequential adaptive design conducts multiple interim assessments to improve the accuracy of estimates of agreement between external data and current data. At each interim assessment, we apply the inverse probability weighted power prior (IPW‐PP) method to adaptively borrow information from external data to account for confounding and heterogeneity. The randomization ratio is dynamically adjusted during the interim assessment based on accumulatively augmented information to reduce the sample size of the current trial. Additionally, the proposed design can be extended to allow interim analyses for early efficacy/futility stopping, that is, early assessment of trial success or failure based on accumulated data, potentially reducing ineffective treatment exposure and unnecessary time and resources. The performance of the proposed method and design is evaluated via extensive simulation studies. The sequential adaptive design and IPW‐PP approach having desirable properties are implemented.