Tutorial in biostatistics: Analyzing associations between total plasma homocysteine and B vitamins using optimal categorization and segmented regression

Heejung Bang, Madhu Mazumdar, J. David Spence

Research output: Contribution to journalArticle

27 Scopus citations

Abstract

Data analysts consider standard regression models (e.g., generalized linear model) or nonparametric smoothing techniques (e.g., loess or splines) when examining the association between two variables. Before this step, a quantile-based summarization is typically used for exploring the exposure-response relationship. Unfortunately, these exploratory approaches may not be optimal or efficient for guiding the formal analysis in many biological and nutritional data settings. We suggest a recently developed method for selection of cutpoints as a tool of data summary and segmented regression as a modeling approach in the analysis of plasma total homocysteine and related vitamins. These methods are often complementary in discovering the underlying complex pattern of association.

Original languageEnglish (US)
Pages (from-to)188-200
Number of pages13
JournalNeuroepidemiology
Volume27
Issue number4
DOIs
StatePublished - Dec 2006
Externally publishedYes

Keywords

  • Changepoint
  • Folate
  • Homocysteine
  • Optimal categorization
  • Segmented regression
  • Vitamin B

ASJC Scopus subject areas

  • Epidemiology
  • Clinical Neurology

Fingerprint Dive into the research topics of 'Tutorial in biostatistics: Analyzing associations between total plasma homocysteine and B vitamins using optimal categorization and segmented regression'. Together they form a unique fingerprint.

  • Cite this