Suppr超能文献

病例对照研究中病例与对照的简单最优加权

Simple optimal weighting of cases and controls in case-control studies.

作者信息

Rose Sherri, van der Laan Mark J

机构信息

University of California, Berkeley, CA, USA.

出版信息

Int J Biostat. 2008 Sep 29;4(1):Article 19. doi: 10.2202/1557-4679.1115.

Abstract

Researchers of uncommon diseases are often interested in assessing potential risk factors. Given the low incidence of disease, these studies are frequently case-control in design. Such a design allows a sufficient number of cases to be obtained without extensive sampling and can increase efficiency; however, these case-control samples are then biased since the proportion of cases in the sample is not the same as the population of interest. Methods for analyzing case-control studies have focused on utilizing logistic regression models that provide conditional and not causal estimates of the odds ratio. This article will demonstrate the use of the prevalence probability and case-control weighted targeted maximum likelihood estimation (MLE), as described by van der Laan (2008), in order to obtain causal estimates of the parameters of interest (risk difference, relative risk, and odds ratio). It is meant to be used as a guide for researchers, with step-by-step directions to implement this methodology. We will also present simulation studies that show the improved efficiency of the case-control weighted targeted MLE compared to other techniques.

摘要

罕见病研究人员通常对评估潜在风险因素感兴趣。鉴于疾病发病率较低,这些研究在设计上通常为病例对照研究。这种设计无需大量抽样就能获得足够数量的病例,并且可以提高效率;然而,这些病例对照样本随后会产生偏差,因为样本中病例的比例与目标人群的比例不同。分析病例对照研究的方法主要集中在使用逻辑回归模型,该模型提供的是比值比的条件估计而非因果估计。本文将演示如范德·兰(2008年)所述的患病率概率和病例对照加权目标最大似然估计(MLE)的用法,以便获得感兴趣参数(风险差、相对风险和比值比)的因果估计。它旨在作为研究人员的指南,提供实施该方法的逐步指导。我们还将展示模拟研究,结果表明与其他技术相比,病例对照加权目标MLE的效率更高。

相似文献

1
Simple optimal weighting of cases and controls in case-control studies.
Int J Biostat. 2008 Sep 29;4(1):Article 19. doi: 10.2202/1557-4679.1115.
2
Estimation based on case-control designs with known prevalence probability.
Int J Biostat. 2008;4(1):Article 17. doi: 10.2202/1557-4679.1114.
3
Why match? Investigating matched case-control study designs with causal effect estimation.
Int J Biostat. 2009 Jan 6;5(1):Article 1. doi: 10.2202/1557-4679.1127.
4
Doubly Robust and Efficient Estimation of Marginal Structural Models for the Hazard Function.
Int J Biostat. 2016 May 1;12(1):233-52. doi: 10.1515/ijb-2015-0036.
5
Targeted minimum loss based estimator that outperforms a given estimator.
Int J Biostat. 2012 May 18;8(1):Article 11. doi: 10.1515/1557-4679.1332.
7
Analysis of case-cohort designs with binary outcomes: Improving efficiency using whole-cohort auxiliary information.
Stat Methods Med Res. 2017 Apr;26(2):691-706. doi: 10.1177/0962280214556175. Epub 2014 Oct 26.
9
Double robust and efficient estimation of a prognostic model for events in the presence of dependent censoring.
Biostatistics. 2016 Jan;17(1):165-77. doi: 10.1093/biostatistics/kxv028. Epub 2015 Jul 29.
10
Collaborative targeted maximum likelihood for time to event data.
Int J Biostat. 2010;6(1):Article 21. doi: 10.2202/1557-4679.1249.

引用本文的文献

3
Mediation model with a categorical exposure and a censored mediator with application to a genetic study.
PLoS One. 2021 Oct 12;16(10):e0257628. doi: 10.1371/journal.pone.0257628. eCollection 2021.
4
6
From Clinical Phenotype to Genotypic Modelling: Incidence and Prevalence of Recessive Dystrophic Epidermolysis Bullosa (RDEB).
Clin Cosmet Investig Dermatol. 2019 Dec 24;12:933-942. doi: 10.2147/CCID.S232547. eCollection 2019.
7
Estimating treatment effects with machine learning.
Health Serv Res. 2019 Dec;54(6):1273-1282. doi: 10.1111/1475-6773.13212. Epub 2019 Oct 10.
8
Matching and Imputation Methods for Risk Adjustment in the Health Insurance Marketplaces.
Stat Biosci. 2017 Dec;9(2):525-542. doi: 10.1007/s12561-015-9135-7. Epub 2015 Aug 5.
9
Natural history of diseases: Statistical designs and issues.
Clin Pharmacol Ther. 2016 Oct;100(4):353-61. doi: 10.1002/cpt.423. Epub 2016 Aug 18.
10
Predictive modeling in pediatric traumatic brain injury using machine learning.
BMC Med Res Methodol. 2015 Mar 17;15:22. doi: 10.1186/s12874-015-0015-0.

本文引用的文献

1
Estimation based on case-control designs with known prevalence probability.
Int J Biostat. 2008;4(1):Article 17. doi: 10.2202/1557-4679.1114.
2
Targeted maximum likelihood based causal inference: Part I.
Int J Biostat. 2010;6(2):Article 2. doi: 10.2202/1557-4679.1211.
3
Why match? Investigating matched case-control study designs with causal effect estimation.
Int J Biostat. 2009 Jan 6;5(1):Article 1. doi: 10.2202/1557-4679.1127.
5
On the estimation and use of propensity scores in case-control and case-cohort studies.
Am J Epidemiol. 2007 Aug 1;166(3):332-9. doi: 10.1093/aje/kwm069. Epub 2007 May 15.
6
Causal analysis of case-control data.
Epidemiol Perspect Innov. 2006 Jan 27;3:2. doi: 10.1186/1742-5573-3-2.
9
Statistics in epidemiology: the case-control study.
J Am Stat Assoc. 1996 Mar;91(433):14-28. doi: 10.1080/01621459.1996.10476660.
10
The case-control study as data missing by design: estimating risk differences.
Epidemiology. 1996 Mar;7(2):144-50. doi: 10.1097/00001648-199603000-00007.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验