Cherry-picking for complex data: robust structure discovery.

Philos Trans A Math Phys Eng Sci

Department of Statistical Science, Duke University, Durham, NC 27705, USA.

Published: November 2009

Complex data often arise as a superposition of data generated from several simpler models. The traditional strategy for such cases is to use mixture modelling, but it can be problematic, especially in higher dimensions. This paper considers an alternative approach, emphasizing data exploration and robustness to model misspecification. The strategy is applied to problems in regression, cluster analysis and multidimensional scaling. The approach is illustrated through simulation and the analysis of several datasets.

Download full-text PDF

Source
http://dx.doi.org/10.1098/rsta.2009.0119DOI Listing

Publication Analysis

Top Keywords

complex data
8
cherry-picking complex
4
data
4
data robust
4
robust structure
4
structure discovery
4
discovery complex
4
data superposition
4
superposition data
4
data generated
4

Similar Publications

Background: Sensory disorders of the inferior alveolar nerve, often arising from dental procedures, markedly impact the quality of life of patients. This article proposes a scoping review to analyze emerging trends in pharmacological treatment for these disorders, addressing scientific gaps and clinical practices.

Material And Methods: The review followed the PRISMA-ScR protocol, conducting data searches across various databases, including PubMed and Cochrane, until March 2024.

View Article and Find Full Text PDF

Tumors are complex ecosystems of interacting cell types. The concept of cancer hallmarks distills this complexity into underlying principles that govern tumor growth. Here, we explore the spatial distribution of cancer hallmarks across 63 primary untreated tumors from 10 cancer types using spatial transcriptomics.

View Article and Find Full Text PDF

Access to information about chemicals in products and articles is critical for supporting enforcement of chemical regulations, assessing risks from chemicals, allowing informed consumer choices, and enabling product circularity. In this work, we identified and evaluated available databases (DBs) on chemicals in products and articles from the literature using a defined protocol and from European national market surveillance authorities, nongovernmental agencies, and industrial sector groups using questionnaires. This is the first comprehensive review of DBs that provide information about chemicals in products and articles.

View Article and Find Full Text PDF

Introduction: Prostate cancer (PCa) is the commonest urologic cancer worldwide and the leading cause of male cancer deaths in Nigeria. In Nigeria, orchidectomy remains the primary androgen deprivation therapy. Dihydrotestosterone (DHT) is the active prostatic androgen, but its relationship with PCa severity has not been extensively studied in Africa.

View Article and Find Full Text PDF

Introduction: The present study aimed to explore the epidemiologic threats and factors associated with the coronavirus disease 2019 (COVID-19)-associated mucormycosis (CAM) epidemic that emerged in Egypt during the second COVID-19 wave. The study also aimed to explore the diagnostic features and the role of surgical interventions of CAM on the outcome of the disease in a central referral hospital.

Methodology: The study included 64 CAM patients from a referral hospital for CAM and a similar number of matched controls from COVID-19 patients who did not develop CAM.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!