Correcting for measurement error in binary and continuous variables using replicates

Measurement error in exposures and confounders leads to bias in regression coefficients. It is possible to adjust for this bias if true values or independent replicates are observed on a subsample. We extend a method suitable for quantitative variables to the situation where both binary and quantitative variables are present. Binary variables with independent replicates introduce two extra problems: (i) the error is correlated with the true value, and (ii) the measurement error probabilities are unidentified if only two replicates are available. We show that - under plausible assumptions - adjustment for error in binary confounders does not need to address these problems. The regression coefficient for a binary exposure is overadjusted if methods for continuous variables are used. Correct adjustment is possible either if three replicates are available, or if further assumptions can be made; otherwise, bounds can be put on the correctly adjusted value, and these bounds are reasonably close together if the exposure has prevalence near 0.5.

[1]  D. Ruppert,et al.  Measurement Error in Nonlinear Models , 1995 .

[2]  W. Willett,et al.  An overview of issues related to the correction of non-differential exposure measurement error in epidemiologic studies. , 1989, Statistics in medicine.

[3]  N. Day,et al.  Misclassification in more than one factor in a case-control study: a combination of Mantel-Haenszel and maximum likelihood approaches. , 1989, Statistics in medicine.

[4]  S Greenland,et al.  When will nondifferential misclassification of an exposure preserve the direction of a trend? , 1994, American journal of epidemiology.

[5]  S. Duffy,et al.  The correction of risk estimates for measurement error. , 1997, Annals of epidemiology.

[6]  S. Duffy,et al.  Repeat measurement of case-control data: corrections for measurement error in a study of ischaemic stroke and haemostatic factors. , 1997, International journal of epidemiology.

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

[8]  B G Armstrong,et al.  The effects of measurement errors on relative risk regressions. , 1990, American journal of epidemiology.

[9]  J Kaldor,et al.  Latent class analysis in chronic disease epidemiology. , 1985, Statistics in medicine.

[10]  R J Carroll,et al.  Quasilikelihood estimation in measurement error models with correlated replicates. , 1996, Biometrics.

[11]  B. Rosner,et al.  Measurement error models for ordinal exposure variables measured with error. , 1996, Statistics in medicine.

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

[13]  S. Duffy,et al.  Repeat measurement of case-control data: correcting risk estimates for misclassification due to regression dilution of lipids in transient ischemic attacks and minor ischemic strokes. , 1991, American journal of epidemiology.

[14]  Eoin O'Brien,et al.  ABC of Hypertension , 1981 .

[15]  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.

[16]  S. Walter,et al.  Estimating the error rates of diagnostic tests. , 1980, Biometrics.

[17]  K. Flegal,et al.  Differential misclassification arising from nondifferential errors in exposure measurement. , 1991, American journal of epidemiology.

[18]  J. N. R. Jeffers,et al.  Graphical Models in Applied Multivariate Statistics. , 1990 .

[19]  S. T. Buckland,et al.  An Introduction to the Bootstrap. , 1994 .

[20]  S Wacholder,et al.  When Measurement Errors Correlate with Truth: Surprising Effects of Nondifferential Misclassification , 1995, Epidemiology.

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

[22]  S. Richardson,et al.  Conditional independence models for epidemiological studies with covariate measurement error. , 1993, Statistics in medicine.

[23]  J Kuha Estimation by data augmentation in regression models with continuous and discrete covariates measured with error. , 1997, Statistics in medicine.

[24]  S Greenland,et al.  The effect of misclassification in the presence of covariates. , 1980, American journal of epidemiology.

[25]  P A Lachenbruch,et al.  Effects of misclassifications on statistical inferences in epidemiology. , 1980, American journal of epidemiology.

[26]  D. Rubin,et al.  Statistical Analysis with Missing Data. , 1989 .

[27]  Alice S. Whittemore,et al.  Errors-in-Variables Regression Using Stein Estimates , 1989 .

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

[29]  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.

[30]  D A Savitz,et al.  Estimating and correcting for confounder misclassification. , 1989, American journal of epidemiology.