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 Citations (Scopus)

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

Fingerprint

Biostatistics
Vitamin B Complex
Homocysteine
Vitamins
Linear Models

Keywords

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

ASJC Scopus subject areas

  • Epidemiology
  • Clinical Neurology

Cite this

Tutorial in biostatistics : Analyzing associations between total plasma homocysteine and B vitamins using optimal categorization and segmented regression. / Bang, Heejung; Mazumdar, Madhu; Spence, J. David.

In: Neuroepidemiology, Vol. 27, No. 4, 12.2006, p. 188-200.

Research output: Contribution to journalArticle

@article{8fb9b0320afa4f26ab451bc15819ccc9,
title = "Tutorial in biostatistics: Analyzing associations between total plasma homocysteine and B vitamins using optimal categorization and segmented regression",
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.",
keywords = "Changepoint, Folate, Homocysteine, Optimal categorization, Segmented regression, Vitamin B",
author = "Heejung Bang and Madhu Mazumdar and Spence, {J. David}",
year = "2006",
month = "12",
doi = "10.1159/000096149",
language = "English (US)",
volume = "27",
pages = "188--200",
journal = "Neuroepidemiology",
issn = "0251-5350",
publisher = "S. Karger AG",
number = "4",

}

TY - JOUR

T1 - Tutorial in biostatistics

T2 - Analyzing associations between total plasma homocysteine and B vitamins using optimal categorization and segmented regression

AU - Bang, Heejung

AU - Mazumdar, Madhu

AU - Spence, J. David

PY - 2006/12

Y1 - 2006/12

N2 - 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.

AB - 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.

KW - Changepoint

KW - Folate

KW - Homocysteine

KW - Optimal categorization

KW - Segmented regression

KW - Vitamin B

UR - http://www.scopus.com/inward/record.url?scp=33845765716&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845765716&partnerID=8YFLogxK

U2 - 10.1159/000096149

DO - 10.1159/000096149

M3 - Article

VL - 27

SP - 188

EP - 200

JO - Neuroepidemiology

JF - Neuroepidemiology

SN - 0251-5350

IS - 4

ER -