Journal of Statistical Theory and Practice最新文献

Strong statistical voice is defined as the ability to advocate and negotiate for good and ethical statistical practices, including integrating and resolving differing scientific approaches. This skill is crucial for biostatisticians who work on biomedical research teams, as it ensures the integrity and accuracy of statistical analyses and fosters productive collaborations with non-statisticians. Despite its importance, new graduates often lack targeted training opportunities. This manuscript presents a scalable training approach through the development of online videos. Preliminary didactic materials focused on two key applications: providing written comments on manuscripts and engaging in study design discussions. To evaluate this training approach, a survey was conducted among biostatistics staff in the Duke Biostatistics, Epidemiology, and Research Design Core. The survey results indicated that all respondents strongly agreed on the importance of strong statistical voice in biostatistics practice. The clarity of the training materials and examples received positive feedback, though suggestions for improvement included enhancing video engagement and providing more hands-on training. This information will guide the development of formal training videos embedded within a mentored training program that aims to teach biostatisticians and other quantitative scientists how to effectively work on teams in biomedical research.

Rigorous and transparent research practices are essential for trustworthy scientific findings, particularly in observational studies where data-driven analyses carry risks of questionable research practices. This paper introduces a statistical analysis plan (SAP) template specifically designed for observational research, an area where guidance on SAP development is crucially lacking. The template offers clear guidelines for prespecifying key aspects of the analysis. The guidance encompasses essential SAP components, including study objectives, measures and variables, and analytical methods, as well as administrative details to support documentation and reproducibility. Designed for broad useability, the template is intended to support researchers, statisticians, students, and interdisciplinary teams across clinical, academic, industry, and government sectors. By adopting this template, researchers can strengthen study integrity, reduce ad hoc analytic modifications, demonstrate the avoidance of questionable research practices such as p-hacking, and contribute to robust and reliable findings in observational research.

Environmental DNA (eDNA) surveys offer a revolutionary approach to species monitoring by detecting DNA traces left by organisms in environmental samples, such as water and soil. These surveys provide a cost-effective, non-invasive, and highly sensitive alternative to traditional methods that rely on direct observation of species, especially for protected or invasive species. Quantitative PCR (qPCR) is a technique used to amplify and quantify a targeted DNA molecule, making it a popular tool for monitoring focal species. Modelling of qPCR data has so far focused on inferring species presence/absence at surveyed sites. However, qPCR output is also informative regarding DNA concentration of the species in the sample, and hence, with the appropriate modelling approach, in the environment. In this paper, we introduce a modelling framework that infers DNA concentration at surveyed sites across time and space, and as a function of covariates, from qPCR output. Our approach accounts for contamination and inhibition in lab analyses, addressing biases particularly notable at low DNA concentrations, and for the inherent stochasticity in the corresponding data. Additionally, we incorporate heteroscedasticity in qPCR output, recognizing the increased variance of qPCR data at lower DNA concentrations. We validate our model through a simulation study, comparing its performance against models that ignore contamination/inhibition and variance heterogeneity. Further, we apply the model to three case studies involving aquatic and semi-aquatic species surveys in the UK. Our findings demonstrate improved accuracy and robustness in estimating DNA concentrations, offering a refined tool for ecological monitoring and conservation efforts.

Supplementary information: The online version contains supplementary material available at 10.1007/s42519-025-00477-9.

In discrete choice experiments, the information matrix depends on the model parameters. Therefore designing optimally informative experiments for arbitrary initial parameters often yields highly nonlinear optimization problems and makes optimal design infeasible. To overcome such challenges, we connect design theory for discrete choice experiments with Laplacian matrices of undirected graphs, resulting in complexity reduction and feasibility of optimal design. We rewrite the D-optimality criterion in terms of Laplacians via Kirchhoff's matrix tree theorem, and show that its dual has a simple description via the Cayley-Menger determinant of the Farris transform of the Laplacian matrix. This results in a drastic reduction of complexity and allows us to implement a gradient descent algorithm to find locally D-optimal designs. For the subclass of Bradley-Terry paired comparison models, we find a direct link to maximum likelihood estimation for Laplacian-constrained Gaussian graphical models. Finally, we study the performance of our algorithm and demonstrate its application to real and simulated data.

In this article, we develop a weighted approach to estimation for right-censored time to event data in the presence of external predictions available from a prediction model. There are several advantages to the proposed approach. First, the method allows for arbitrary forms for the external prediction model. Second, the methodology can be fit easily using standard software packages that allow for subject-specific weights. Third, all that is needed from the external models are access to predictions and not the actually prediction equation. A complication is that inference becomes challenging, so we develop new theoretical results along with a perturbation-based method for inference. The methodology is applied to three publicly available datasets.

In this paper, we propose a novel deep neural network (DNN) architecture with fractal structure and attention blocks. The new method is tested to identify and segment 2D and 3D brain tumor masks in normal and pathological neuroimaging data. To circumvent the problem of limited 3D volumetric datasets with raw and ground truth tumor masks, we utilized data augmentation using affine transformations to significantly expand the training data prior to estimating the network model parameters. The proposed Attention-based Fractal Unet (AFUnet) technique combines benefits of fractal convolutional networks, attention blocks, and the encoder-decoder structure of Unet. The AFUnet models are fit on training data and their performance is assessed on independent validation and testing datasets. The Dice score is used to measure and contrast the performance of AFUnet against alternative methods, such as Unet, attention Unet, and several other DNN models with relative number of parameters. In addition, we explore the effects of the network depth to the AFUnet prediction accuracy. The results suggest that with a few network structure iterations, the attention-based fractal Unet achieves good performance. Although deeper nested network structure certainly improves the prediction accuracy, this comes with a very substantial computational cost. The benefits of fitting deeper AFUnet models are relative to the extra time and computational demands. Some of the AFUnet networks outperform current state-of-the-art models and achieve highly accurate and realistic brain-tumor boundary segmentation (contours in 2D and surfaces in 3D). In our experiments, the sensitivity of the Dice score to capture significant inter-models differences is marginal. However, there is improved validation loss during long periods of AFUnet training. The lower binary cross entropy loss suggests that AFUNet is superior in finding true negative voxels (i.e., identifying normal tissue), which suggests the new method is more conservative. This approach may be generalized to higher dimensional data, e.g., 4D fMRI hypervolumes, and applied for a wide range of signal, image, volume, and hypervolume segmentation tasks.