Literature DB >> 19667054

Estimating the odds ratio when exposure has a limit of detection.

Stephen R Cole1, Haitao Chu, Lei Nie, Enrique F Schisterman.   

Abstract

BACKGROUND: In epidemiologic research, little emphasis has been placed on methods to account for left-hand censoring of 'exposures' due to a limit of detection (LOD).
METHODS: We calculate the odds of anti-HIV therapy naiveté in 45 HIV-infected men as a function of measured log(10) plasma HIV RNA viral load using five approaches including ad hoc methods as well as a maximum likelihood estimate (MLE). We also generated simulations of a binary outcome with 10% incidence and a 1.5-fold increased odds per log increase in a log-normally distributed exposure with 25, 50 and 75% of exposure data below LOD. Simulated data were analysed using the same five methods, as well as the full data.
RESULTS: In the example, the estimated odds ratio (OR) varied by 1.22-fold across methods, from 1.45 to 1.77 per log(10) copies of viral load and the standard error for the log OR varied by 1.52-fold across methods, from 0.31 to 0.47. In the simulations, use of full data or the MLE was unbiased with appropriate confidence interval (CI) coverage. However, as the proportion of exposure below LOD increased, substituting LOD, LOD/ radical 2 or LOD/2 was increasingly biased with increasingly inappropriate CI coverage. Finally, exclusion of values below LOD was unbiased but imprecise.
CONCLUSIONS: In this example and the settings explored by simulation, and among methods readily available to investigators (i.e. sans full data), the MLE provided an unbiased and appropriately precise estimate of the exposure-outcome OR.

Entities:  

Mesh:

Substances:

Year:  2009        PMID: 19667054      PMCID: PMC2786252          DOI: 10.1093/ije/dyp269

Source DB:  PubMed          Journal:  Int J Epidemiol        ISSN: 0300-5771            Impact factor:   7.196


  19 in total

1.  Maximum likelihood inference for left-censored HIV RNA data.

Authors:  H S Lynn
Journal:  Stat Med       Date:  2001-01-15       Impact factor: 2.373

2.  Clinical trials using HIV-1 RNA-based primary endpoints: statistical analysis and potential biases.

Authors:  I C Marschner; R A Betensky; V DeGruttola; S M Hammer; D R Kuritzkes
Journal:  J Acquir Immune Defic Syndr Hum Retrovirol       Date:  1999-03-01

3.  Mixed effects models with censored data with application to HIV RNA levels.

Authors:  J P Hughes
Journal:  Biometrics       Date:  1999-06       Impact factor: 2.571

4.  Inference for a linear regression model with an interval-censored covariate.

Authors:  Guadalupe Gómez; Anna Espinal; Stephen W Lagakos
Journal:  Stat Med       Date:  2003-02-15       Impact factor: 2.373

5.  ROC analysis for markers with mass at zero.

Authors:  Enrique F Schisterman; Benjamin Reiser; David Faraggi
Journal:  Stat Med       Date:  2006-02-28       Impact factor: 2.373

6.  Bayesian perspectives for epidemiological research: I. Foundations and basic methods.

Authors:  Sander Greenland
Journal:  Int J Epidemiol       Date:  2006-01-30       Impact factor: 7.196

7.  Youden Index and the optimal threshold for markers with mass at zero.

Authors:  Enrique F Schisterman; David Faraggi; Benjamin Reiser; Jessica Hu
Journal:  Stat Med       Date:  2008-01-30       Impact factor: 2.373

8.  Linear regression with an independent variable subject to a detection limit.

Authors:  Lei Nie; Haitao Chu; Chenglong Liu; Stephen R Cole; Albert Vexler; Enrique F Schisterman
Journal:  Epidemiology       Date:  2010-07       Impact factor: 4.822

9.  A controlled trial of two nucleoside analogues plus indinavir in persons with human immunodeficiency virus infection and CD4 cell counts of 200 per cubic millimeter or less. AIDS Clinical Trials Group 320 Study Team.

Authors:  S M Hammer; K E Squires; M D Hughes; J M Grimes; L M Demeter; J S Currier; J J Eron; J E Feinberg; H H Balfour; L R Deyton; J A Chodakewitz; M A Fischl
Journal:  N Engl J Med       Date:  1997-09-11       Impact factor: 91.245

10.  Determining the effect of highly active antiretroviral therapy on changes in human immunodeficiency virus type 1 RNA viral load using a marginal structural left-censored mean model.

Authors:  Stephen R Cole; Miguel A Hernán; Kathryn Anastos; Beth D Jamieson; James M Robins
Journal:  Am J Epidemiol       Date:  2007-05-02       Impact factor: 4.897

View more
  45 in total

1.  Serum cotinine and whole blood folate concentrations in pregnancy.

Authors:  Adila Prasodjo; Christine M Pfeiffer; Zia Fazili; Yingying Xu; Stacey Liddy; Kimberly Yolton; David A Savitz; Bruce P Lanphear; Joseph M Braun
Journal:  Ann Epidemiol       Date:  2014-04-24       Impact factor: 3.797

2.  Attention-deficit/hyperactivity disorder and urinary metabolites of organophosphate pesticides.

Authors:  Maryse F Bouchard; David C Bellinger; Robert O Wright; Marc G Weisskopf
Journal:  Pediatrics       Date:  2010-05-17       Impact factor: 7.124

3.  Correlated biomarker measurement error: an important threat to inference in environmental epidemiology.

Authors:  A Z Pollack; N J Perkins; S L Mumford; A Ye; E F Schisterman
Journal:  Am J Epidemiol       Date:  2012-12-07       Impact factor: 4.897

4.  Paraben exposures and asthma-related outcomes among children from the US general population.

Authors:  Lesliam Quirós-Alcalá; Nadia N Hansel; Meredith C McCormack; Elizabeth C Matsui
Journal:  J Allergy Clin Immunol       Date:  2018-09-05       Impact factor: 10.793

5.  Estimating Outcome-Exposure Associations when Exposure Biomarker Detection Limits vary Across Batches.

Authors:  Jonathan Boss; Bhramar Mukherjee; Kelly K Ferguson; Amira Aker; Akram N Alshawabkeh; José F Cordero; John D Meeker; Sehee Kim
Journal:  Epidemiology       Date:  2019-09       Impact factor: 4.822

Review 6.  Measurement Error and Environmental Epidemiology: a Policy Perspective.

Authors:  Jessie K Edwards; Alexander P Keil
Journal:  Curr Environ Health Rep       Date:  2017-03

7.  The missing indicator approach for censored covariates subject to limit of detection in logistic regression models.

Authors:  Sy Han Chiou; Rebecca A Betensky; Raji Balasubramanian
Journal:  Ann Epidemiol       Date:  2019-08-13       Impact factor: 3.797

8.  Maximum likelihood estimation in generalized linear models with multiple covariates subject to detection limits.

Authors:  Ryan C May; Joseph G Ibrahim; Haitao Chu
Journal:  Stat Med       Date:  2011-06-28       Impact factor: 2.373

9.  Estimation of exposure distribution adjusting for association between exposure level and detection limit.

Authors:  Yuchen Yang; Brent J Shelton; Thomas T Tucker; Li Li; Richard Kryscio; Li Chen
Journal:  Stat Med       Date:  2017-05-16       Impact factor: 2.373

10.  Associations of blood and urinary mercury with hypertension in U.S. adults: the NHANES 2003-2006.

Authors:  Sung Kyun Park; Sunghee Lee; Niladri Basu; Alfred Franzblau
Journal:  Environ Res       Date:  2013-03-06       Impact factor: 6.498

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.