Likelihood-based methods for estimating the association between a health outcome and left- or interval-censored longitudinal exposure data†
Corresponding Author
Kathleen A. Wannemuehler
Division of Foodborne, Bacterial and Mycotic Diseases, National Center for Zoonotic, Vectorborne and Enteric Diseases, Centers for Disease Control and Prevention, Atlanta, GA, U.S.A.
Division of Foodborne, Bacterial and Mycotic Diseases, National Center for Zoonotic, Vectorborne and Enteric Diseases, Centers for Disease Control and Prevention, Atlanta, GA, U.S.A.Search for more papers by this authorRobert H. Lyles
Department of Biostatistics and Bioinformatics, The Rollins School of Public Health of Emory University, Atlanta, GA, U.S.A.
Search for more papers by this authorAmita K. Manatunga
Department of Biostatistics and Bioinformatics, The Rollins School of Public Health of Emory University, Atlanta, GA, U.S.A.
Search for more papers by this authorMetrecia L. Terrell
Department of Epidemiology, The Rollins School of Public Health of Emory University, Atlanta, GA, U.S.A.
Search for more papers by this authorMichele Marcus
Department of Epidemiology, The Rollins School of Public Health of Emory University, Atlanta, GA, U.S.A.
Department of Environmental and Occupational Health, The Rollins School of Public Health of Emory University, Atlanta, GA, U.S.A.
Search for more papers by this authorCorresponding Author
Kathleen A. Wannemuehler
Division of Foodborne, Bacterial and Mycotic Diseases, National Center for Zoonotic, Vectorborne and Enteric Diseases, Centers for Disease Control and Prevention, Atlanta, GA, U.S.A.
Division of Foodborne, Bacterial and Mycotic Diseases, National Center for Zoonotic, Vectorborne and Enteric Diseases, Centers for Disease Control and Prevention, Atlanta, GA, U.S.A.Search for more papers by this authorRobert H. Lyles
Department of Biostatistics and Bioinformatics, The Rollins School of Public Health of Emory University, Atlanta, GA, U.S.A.
Search for more papers by this authorAmita K. Manatunga
Department of Biostatistics and Bioinformatics, The Rollins School of Public Health of Emory University, Atlanta, GA, U.S.A.
Search for more papers by this authorMetrecia L. Terrell
Department of Epidemiology, The Rollins School of Public Health of Emory University, Atlanta, GA, U.S.A.
Search for more papers by this authorMichele Marcus
Department of Epidemiology, The Rollins School of Public Health of Emory University, Atlanta, GA, U.S.A.
Department of Environmental and Occupational Health, The Rollins School of Public Health of Emory University, Atlanta, GA, U.S.A.
Search for more papers by this authorThis article is a U.S. Government work and is in the public domain in the U.S.A.
Abstract
The Michigan Female Health Study (MFHS) conducted research focusing on reproductive health outcomes among women exposed to polybrominated biphenyls (PBBs). In the work presented here, the available longitudinal serum PBB exposure measurements are used to obtain predictions of PBB exposure for specific time points of interest via random effects models. In a two-stage approach, a prediction of the PBB exposure is obtained and then used in a second-stage health outcome model. This paper illustrates how a unified approach, which links the exposure and outcome in a joint model, provides an efficient adjustment for covariate measurement error. We compare the use of empirical Bayes predictions in the two-stage approach with results from a joint modeling approach, with and without an adjustment for left- and interval-censored data. The unified approach with the adjustment for left- and interval-censored data resulted in little bias and near-nominal confidence interval coverage in both the logistic and linear model setting. Published in 2010 by John Wiley & Sons, Ltd.
References
- 1 Fuller WA. Measurement Error Models. Wiley: New York, 1987.
10.1002/9780470316665 Google Scholar
- 2 Carroll RJ, Ruppert D, Stefanski LA. Measurement Error in Nonlinear Models. Chapman & Hall: New York, 1995.
10.1007/978-1-4899-4477-1 Google Scholar
- 3 Carroll RJ. Covariance analysis in generalized linear measurement error models. Statistics in Medicine 1989; 8: 1075–1093.
- 4 Thomas D, Stram D, Dwyer J. Exposure measurement error: influence on exposure-disease relationships and methods of correction. Annual Review of Public Health 1993; 14: 69–93.
- 5 Thurigen D, Spiegelman D, Blettner M, Heuer C, Brenner H. Measurement error correction using validation data: a review of methods and their applicability in case–control studies. Statistical Methods in Medical Research 2000; 9(5): 447–474.
- 6 Blanck HM, Marcus M, Hertzberg VS, Tolbert PE, Rubin C, Henderson AK, Zhang RH. Determinants of polybrominated biphenyl serum decay among women in the michigan pbb cohort. Environmental Health Perspectives 2000; 108: 147–152.
- 7 Blanck HM, Marcus M, Rubin C, Tolbert PE, Hertzberg VS, Henderson AK, Zhang RH. Growth in girls exposed in utero and postnatally to polybrominated biphenyls and polychlorinated biphenyls. Epidemiology 2002; 13: 205–210.
- 8 Wannemuehler KA, Lyles RH. A unified model for covariate measurement error adjustment in an occupational health study while accounting for non-detectable exposures. Journal of the Royal Statistical Society Series C—Applied Statistics 2005; 54(1): 259–271.
- 9 Hornung RW, Reed LD. Estimation of average concentration in the presence of nondetectable values. Applied Occupational and Environmental Hygiene 1990; 5: 46–51.
- 10 Hughes JP. Mixed effects models with censored data with application to HIV RNA levels. Biometrics 1999; 55: 625–629.
- 11 Jacqmin-Gadda H, Thiébaut R, Chêne G, Commenges D. Analysis of left-censored longitudinal data with application to viral load in HIV infection. Biostatistics 2000; 1: 355–368.
- 12 Lyles RH, Lyles CM, Taylor DJ. Random regression models for human immunodeficiency virus ribonucleic acid data subject to left censoring and informative drop-outs. Applied Statistics 2000; 49: 485–497.
- 13 Albert PS. Modeling longitudinal biomarker data from multiple assays that have different known detection limits. Biometrics 2008; 64: 527–537.
- 14 Wu MC, Carroll RJ. Estimation and comparison of changes in the presence of informative right censoring by modeling the censoring process. Biometrics 1988; 44: 175–188.
- 15 DeGruttola V, Tu XM. Modeling progression of CD4-lymphocyte count and its relationship to survival time. Biometrics 1994; 50: 1003–1014.
- 16 Tsonaka R, Verbeke G, Lesaffre E. A semi-parametric shared paramter model to handle nonmonotone nonignorable missingness. Biometrics 2009; 65: 81–87.
- 17 Heitjan DF, Rubin DB. Ignorability and coarse data. The Annals of Statistics 1991; 19: 2244–2253.
- 18 Carter LJ. Michigan's PBB incident: chemical mix-up leads to disaster. Science 1976; 192: 240–243.
- 19 Fries GF. The PBB episode in michigan: an overall appraisal. CRC Critical Review Toxicology 1988; 16: 105–156.
- 20 Blanck HM, Marcus M, Tolbert PE, Rubin C, Henderson AK, Hertzberg VS, Zhang RH, Cameron L. Age at menarche and tanner stage in girls exposed in utero and postnatally to polybrominated biphenyl. Epidemiology 2000; 11: 641–647.
- 21 Davis SI, Blanck HM, Hertzberg VS, Tolbert PE, Rubin C, Cameron LL, Henderson AK, Marcus M. Menstrual function among women exposed to polybrominated biphenyls: a follow-up prevalence study. Environmental Health: A Global Access Science Source 2005; 4: 1–14.
- 22 Brenner PF. Differential diagnosis of abnormal uterine bleeding. American Journal of Obstetrics and Gynecology 1996; 175: 766–769.
- 23 Small CM, Manatunga AK, Klein M, Feigelson HS, Dominguez CE, McChesney R, Marcus M. Menstrual cycle characteristics. Epidemiology 2006; 17: 52–60.
- 24 Terrell ML, Manatunga AK, Small CM, Cameron LL, Wirth J, Blanck HM, Lyles RH, Marcus M. A decay model for assessing polybrominated biphenyl exposure among women in the Michigan longterm PBB study. Journal of Exposure Science and Environmental Epidemiology. DOI: 10.1038/sj.jes.7500633 2008.
- 25 Laird NM, Ware JH. Random-effects models for longitudinal data. Biometrics 1982; 38: 963–974.
- 26 SAS. SAS/STAT: MIXED Procedure. SAS OnlineDoc 9.1.3. SAS Institute Inc.: Cary, NC, 2004.
- 27 Diggle PJ, Liang KY, Zeger SL. Analyis of Longitudinal Data. Oxford University Press: New York, 1994.
- 28 Singer JD, Willett JB. Applied Longitudinal Data Analysis. Oxford University Press: New York, 2003.
10.1093/acprof:oso/9780195152968.001.0001 Google Scholar
- 29 Searle SR, Casella G, McCulloch CE. Variance Components. Wiley: New York, 1992.
10.1002/9780470316856 Google Scholar
- 30 McCullagh P, Nelder JA. Generalized Linear Models ( 2nd edn). Chapman & Hall, CRC: Boca Raton, 1989.
- 31 Clayton D. Models for the longitudinal analysis of cohort and case–control studies with inaccurately measured exposures. In Statistical Models for Longitudinal Studies of Health, JH Dwyer (ed.). Oxford University Press: Oxford, 1992; 301–325.
- 32 SAS. SAS/STAT: NLMIXED Procedure. SAS OnlineDoc 9.1.3. SAS Institute Inc.: Cary, NC, 2004.
- 33 Lange N, Ryan L. Assessing normality in random effects models. Annals of Statistics 1989; 17: 624–642.
- 34 Verbeke G, Mohlenberghs G. Linear Mixed Models for Longitudinal Data. Springer: New York, 2000.
- 35 Liang KY, Liu XH. Estimating equations in generalized linear models with measurement error. In Estimating Functions, V Godambe (ed.). Oxford University Press: U.S.A., 1991; 47–63.
