Certain practical and theoretical challenges surround the estimation of finite mixture models. One such challenge is how to determine the number of components when this is not assumed a priori. Available methods in the literature are primarily numerical and lack any substantial visualization component. Traditional numerical methods include the calculation of information criteria and bootstrapping approaches; however, such methods have known technical issues regarding the necessary regularity conditions for testing the number of components. The ability to visualize an appropriate number of components for a finite mixture model could serve to supplement the results from traditional methods or provide visual evidence when results from such methods are inconclusive. Our research fills this gap through development of a visualization tool, which we call a mixturegram. This tool is easy to implement and provides a quick way for researchers to assess the number of components for their hypothesized mixture model. Mixtures of univariate or multivariate data can be assessed. We validate our visualization assessments by comparing with results from information criteria and an ad hoc selection criterion based on calculations used for the mixturegram. We also construct the mixturegram for two datasets.
26 May 2023 in Computational Statistics & Data Analysis
Recent advances in sequencing technologies have allowed the collection of massive genome‐wide information that substantially enhances the diagnosis and prognosis of head and neck cancer. Identifying predictive markers for survival time is crucial for devising prognostic systems and learning the underlying molecular drivers of the cancer course. In this paper, we introduce ‐KIDS, a model‐free feature screening procedure with false discovery rate (FDR) control for ultrahigh‐dimensional right‐censored data, which is robust against unknown censoring mechanisms. Specifically, our two‐stage procedure initially selects a set of important features with a dual screening mechanism using nonparametric reproducing‐kernel‐based ANOVA statistics, followed by identifying a refined set of features under FDR control through a unified knockoff procedure. The finite sample properties of our method and its novelty (in light of existing alternatives) are evaluated via simulation studies. Furthermore, we illustrate our methodology via application to a motivating right‐censored head and neck (HN) cancer survival data derived from The Cancer Genome Atlas, with further validation on a similar HN cancer data from the Gene Expression Omnibus database. The methodology can be implemented using the R package aKIDS , which is available on GitHub .
Background: Discovering clinically useful molecular markers for predicting the survival of patients diagnosed with non–muscle-invasive bladder cancer can provide insights into cancer dynamics and improve treatment outcomes. However, the presence of competing risks (CR) endpoints complicates the estimation and inferential framework. There is also a lack of statistical analysis tools and software for coping with the high-throughput nature of these data, in terms of marker screening and selection. Aims: To propose a gene screening procedure for proportional subdistribution hazards regression under a CR framework, and illustrate its application in using molecular profiling to predict survival for non-muscle invasive bladder carcinoma. Methods: Tumors from 300 patients diagnosed with bladder cancer were analyzed for genomic abnormalities while controlling for clinically important covariates. Genes with expression patterns that were associated with survival were identified through a screening procedure based on proportional subdistribution hazards regression. A molecular predictor of risk was constructed and examined for prediction accuracy. Results: A six-gene signature was found to be a significant predictor associated with survival of non–muscle-invasive bladder cancer, subject to competing risks after adjusting for age, gender, reevaluated WHO grade, stage and BCG/MMC treatment (p-value < 0.001). Conclusion: The proposed gene screening procedure can be used to discover molecular determinants of survival for non–muscle-invasive bladder cancer and in general facilitate high-throughput competing risks data analysis with easy implementation.