Tutorial in Biostatistics: Analyzing Associations between Total Plasma Homocysteine and B Vitamins Using Optimal Categorization and Segmented Regression
- 1 December 2006
- journal article
- Published by S. Karger AG in Neuroepidemiology
- Vol. 27 (4), 188-200
- https://doi.org/10.1159/000096149
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
This publication has 37 references indexed in Scilit:
- HomocysteineStroke, 2006
- Estimation in a change-point hazard regression modelStatistics & Probability Letters, 2006
- Vitamin Intervention for Stroke Prevention TrialStroke, 2005
- Vitamin B12, homocysteine and carotid plaque in the era of folic acid fortification of enriched cereal grain productsCMAJ : Canadian Medical Association Journal, 2005
- Estimating regression models with unknown break‐pointsStatistics in Medicine, 2003
- Using Segmented Regression Models to Fit Soil Nutrient and Soybean Grain Yield Changes due to LimingJournal of Agricultural, Biological and Environmental Statistics, 2003
- Digestible Lysine Requirements of Male Turkeys During the 12 to 18 Week PeriodInternational Journal of Poultry Science, 2003
- Dose-Response and Trend Analysis in EpidemiologyEpidemiology, 1995
- A Note on Continuous and Discontinuous Segmented RegressionsTechnometrics, 1980