University of Tasmania
Browse

File(s) not publicly available

A possible strategy for developing a model to account for attrition bias in a longitudinal cohort to investigate associations between exclusive breastfeeding and overweight and obesity at 20 years

journal contribution
posted on 2023-05-18, 17:53 authored by Wendy OddyWendy Oddy, Smith, GJ, Jacoby, P
Our objective was to develop a method that could be applied in a longitudinal cohort study to account for attrition bias in an investigation of exclusive breastfeeding and prevalence of overweight and obesity at 20 years. Participants were compared to non-participants to identify a priori good candidates to predict missing-ness. A logistic regression missing-ness model was developed where probabilities were calculated to generate a pseudo-population of survivors with similar distribution to the original cohort. Final analysis comprised a weighted logistic regression model for cessation of breastfeeding as predicted by overweight and obesity, adjusting for confounding factors, that incorporated generalised estimating equations as final predictive models. Following weighting and scaling in the generalised estimating equation model, the cessation of exclusive breastfeeding before 6 months, compared to 6 months or later was associated with an increased prevalence of overweight and obesity at 20 years (odds ratio 1.47; 95% confidence interval: 1.12-1.93; p = 0.005). Inverse probability weighting offers a possible solution when attrition threatens to bias the results of a study.

History

Publication title

Annals of Nutrition and Metabolism

Volume

65

Issue

2-3

Pagination

234-235

ISSN

0250-6807

Department/School

Menzies Institute for Medical Research

Publisher

Karger

Place of publication

Allschwilerstrasse 10, Basel, Switzerland, Ch-4009

Repository Status

  • Restricted

Socio-economic Objectives

Preventive medicine

Usage metrics

    University Of Tasmania

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC