Correcting for multivariate measurement error by regression calibration in meta‐analyses of epidemiological studies

Within-person variability in measured values of multiple risk factors can bias their associations with disease. The multivariate regression calibration (RC) approach can correct for such measurement error and has been applied to studies in which true values or independent repeat measurements of the risk factors are observed on a subsample. We extend the multivariate RC techniques to a meta-analysis framework where multiple studies provide independent repeat measurements and information on disease outcome. We consider the cases where some or all studies have repeat measurements, and compare study-specific, averaged and empirical Bayes estimates of RC parameters. Additionally, we allow for binary covariates (e.g. smoking status) and for uncertainty and time trends in the measurement error corrections. Our methods are illustrated using a subset of individual participant data from prospective long-term studies in the Fibrinogen Studies Collaboration to assess the relationship between usual levels of plasma fibrinogen and the risk of coronary heart disease, allowing for measurement error in plasma fibrinogen and several confounders.

[1]  S. Pocock,et al.  The variability of serum cholesterol measurements: implications for screening and monitoring. , 1990, Journal of clinical epidemiology.

[2]  S. Ebrahim,et al.  'Mendelian randomization': can genetic epidemiology contribute to understanding environmental determinants of disease? , 2003, International journal of epidemiology.

[3]  N E Day,et al.  European Prospective Investigation into Cancer and Nutrition (EPIC): study populations and data collection , 2002, Public Health Nutrition.

[4]  Theo Stijnen,et al.  Advanced methods in meta‐analysis: multivariate approach and meta‐regression , 2002, Statistics in medicine.

[5]  T. Cole,et al.  Statistical issues in life course epidemiology. , 2006, American journal of epidemiology.

[6]  B Rosner,et al.  Correction of logistic regression relative risk estimates and confidence intervals for measurement error: the case of multiple covariates measured with error. , 1990, American journal of epidemiology.

[7]  R. Collins,et al.  Age-specific relevance of usual blood pressure to vascular mortality: a meta-analysis of individual data for one million adults in 61 prospective studies , 2002, The Lancet.

[8]  R. Collins,et al.  Underestimation of risk associations due to regression dilution in long-term follow-up of prospective studies. , 1999, American journal of epidemiology.

[9]  D. Altman,et al.  Measuring inconsistency in meta-analyses , 2003, BMJ : British Medical Journal.

[10]  Roderick J. A. Little,et al.  Statistical Analysis with Missing Data: Little/Statistical Analysis with Missing Data , 2002 .

[11]  David Clayton,et al.  Epidemiological methods for studying genes and environmental factors in complex diseases , 2001, The Lancet.

[12]  B Rosner,et al.  Correction of logistic regression relative risk estimates and confidence intervals for systematic within-person measurement error. , 2006, Statistics in medicine.

[13]  C Frost,et al.  Correcting for measurement error in binary and continuous variables using replicates , 2001, Statistics in medicine.

[14]  Alicja R. Rudnicka,et al.  Collaborative meta-analysis of prospective studies of plasma fibrinogen and cardiovascular disease , 2004, European journal of cardiovascular prevention and rehabilitation : official journal of the European Society of Cardiology, Working Groups on Epidemiology & Prevention and Cardiac Rehabilitation and Exercise Physiology.

[15]  S L Normand,et al.  Meta-analysis: formulating, evaluating, combining, and reporting. , 1999, Statistics in medicine.

[16]  I. White,et al.  The effect of measurement error in risk factors that change over time in cohort studies: do simple methods overcorrect for 'regression dilution'? , 2005, International journal of epidemiology.

[17]  L. Smeeth,et al.  Limits to causal inference based on Mendelian randomization: a comparison with randomized controlled trials. , 2006, American journal of epidemiology.

[18]  M. Woodward,et al.  Cohort profile: the Asia Pacific Cohort Studies Collaboration. , 2006, International journal of epidemiology.

[19]  S. Thompson,et al.  Correcting for regression dilution bias: comparison of methods for a single predictor variable , 2000 .

[20]  M. Hughes,et al.  Regression dilution in the proportional hazards model. , 1993, Biometrics.

[21]  H Tunstall-Pedoe,et al.  Plasma fibrinogen level and the risk of major cardiovascular diseases and nonvascular mortality: an individual participant meta-analysis. , 2005, JAMA.

[22]  James R. Carpenter,et al.  Test inversion bootstrap confidence intervals , 1999 .

[23]  H Tunstall-Pedoe,et al.  The Emerging Risk Factors Collaboration: analysis of individual data on lipid, inflammatory and other markers in over 1.1 million participants in 104 prospective studies of cardiovascular diseases , 2007, European Journal of Epidemiology.

[24]  M. Law,et al.  Systematic underestimation of association between serum cholesterol concentration and ischaemic heart disease in observational studies: data from the BUPA study , 1994, BMJ.

[25]  S G Thompson,et al.  Systematic Review: Why sources of heterogeneity in meta-analysis should be investigated , 1994, BMJ.

[26]  J. Danesh,et al.  Regression dilution methods for meta-analysis: assessing long-term variability in plasma fibrinogen among 27,247 adults in 15 prospective studies. , 2006, International journal of epidemiology.

[27]  A. Phillips,et al.  How independent are "independent" effects? Relative risk estimation when correlated exposures are measured imprecisely. , 1991, Journal of clinical epidemiology.

[28]  R. Carroll,et al.  Measurement error, instrumental variables and corrections for attenuation with applications to meta-analyses. , 1994, Statistics in medicine.

[29]  R. Collins,et al.  Blood pressure, stroke, and coronary heart disease Part 1, prolonged differences in blood pressure: prospective observational studies corrected for the regression dilution bias , 1990, The Lancet.

[30]  B Rosner,et al.  Correction of logistic regression relative risk estimates and confidence intervals for random within-person measurement error. , 1992, American journal of epidemiology.