OpenLB
Open Library of Bioscience
Advanced Search
Statistics in medicine
02 20, 2023;42 (4): 517-535.

Consistent inverse probability of treatment weighted estimation of the average treatment effect with mismeasured time-dependent confounders.

Ying Yan, Mingchen Ren
Author Information
  1. Ying Yan: School of Mathematics, Sun Yat-sen University, Guangzhou, China. ORCID
  2. Mingchen Ren: Department of Mathematics and Statistics, University of Calgary, Calgary, Alberta, Canada.
PMID: 36513267 DOI: 10.1002/sim.9629

Abstract

In longitudinal studies, the inverse probability of treatment weighted (IPTW) method is commonly employed to estimate the effect of time-dependent treatments on an outcome of interest. However, it has been documented that when the confounders are subject to measurement error, the naive IPTW method which simply ignores measurement error leads to biased treatment effect estimation. In the existing literature, there is a lack of measurement error correction methods that fully remove measurement error effect and produce consistent treatment effect estimation. In this article, we develop a novel consistent IPTW estimation procedure for longitudinal studies. The key step of the proposed method is to use the observed data to construct a corrected function that is unbiased of the unknown IPTW function. Simulation studies reveal that the proposed method outperforms the existing consistent and approximate measurement error correction methods for IPTW estimation of the average treatment effect. Finally, we apply the proposed method to analyze a real dataset.

Keywords

causal inference conditional score marginal structural model measurement error sensitivity analysis

References

  1. Robins JM, Hernán MA, Brumback B. Marginal structural models and causal inference in epidemiology. Epidemiology. 2000;11(5):550-560.
  2. Hernán MA, Robins JM. Causal Inference: What If. Boca Raton: Chapman and Hall/CRC Press; 2020.
  3. Regier MD, Moodie EEM, Platt RW. The effect of error-in-confounders on the estimation of the causal parameter when using marginal structural models and inverse probability-of-treatment weights: a simulation study. Int J Biostat. 2014;10(1):1-15.
  4. Imai K, Yamamoto T. Causal inference with differential measurement error: nonparametric identification and sensitivity analysis. Am J Polit Sci. 2010;54(2):543-560.
  5. Le Cessie S, Debeij J, Rosendaal FR, Cannegieter SC, Vandenbroucke JP. Quantification of bias in direct effects estimates due to different types of measurement error in the mediator. Epidemiology. 2012;23(4):551-560.
  6. Vanderweele TJ, Valeri L, Ogburn EL. The role of measurement error and misclassification in mediation analysis: mediation and measurement error. Epidemiology. 2012;23(4):561-564.
  7. Valeri L, Lin X, VanderWeele TJ. Mediation analysis when a continuous mediator is measured with error and the outcome follows a generalized linear model. Stat Med. 2014;33(28):4875-4890.
  8. Zhao S, Prentice RL. Covariate measurement error correction methods in mediation analysis with failure time data. Biometrics. 2014;70(4):835-844.
  9. Ogburn EL, VanderWeele TJ. Bias attenuation results for nondifferentially mismeasured ordinal and coarsened confounders. Biometrika. 2013;100(1):241-248.
  10. Kuroki M, Pearl J. Measurement bias and effect restoration in causal inference. Biometrika. 2014;101(2):423-437.
  11. Schomaker M, Hogger S, Johnson LF, Hoffmann CJ, Bärnighausen T, Heumann C. Simultaneous treatment of missing data and measurement error in HIV research using multiple overimputation. Epidemiology. 2015;26(5):628-636.
  12. Shu D, Yi GY. Estimation of causal effect measures in the presence of measurement error in confounders. Stat Biosci. 2018;10(1):233-254.
  13. Shu D, Yi GY. Weighted causal inference methods with mismeasured covariates and misclassified outcomes. Stat Med. 2019;38(10):1835-1854.
  14. Shu D, Yi GY. Causal inference with measurement error in outcomes: bias analysis and estimation methods. Stat Methods Med Res. 2019;28(7):2049-2068.
  15. Liu J, Li W. A semiparametric method for evaluating causal effects in the presence of error-prone covariates. Biom J. 2021;63(6):1202-1222.
  16. McCaffrey DF, Lockwood JR, Setodji CM. Inverse probability weighting with error-prone covariates. Biometrika. 2013;100(3):671-680.
  17. Lockwood JR, McCaffrey DF. Matching and weighting with functions of error-prone covariates for causal inference. J Am Stat Assoc. 2016;111(516):1831-1839.
  18. Cole SR, Jacobson LP, Tien PC, Kingsley L, Chmiel JS, Anastos K. Using marginal structural measurement-error models to estimate the long-term effect of antiretroviral therapy on incident AIDS or death. Am J Epidemiol. 2010;171(1):113-122.
  19. Edwards JK, Cole SR, Westreich DJ, et al. Multiple imputation to account for measurement error in marginal structural models. Epidemiology. 2015;26(5):645-652.
  20. Cook JR, Stefanski LA. Simulation-extrapolation estimation in parametric measurement error models. J Am Stat Assoc. 1994;89(428):1314-1328.
  21. Kyle RP, Moodie EEM, Klein MB, Abrahamowicz M. Correcting for measurement error in time-varying covariates in marginal structural models. Am J Epidemiol. 2016;184(3):249-258.
  22. Shu D, Yi GY. Inverse-probability-of-treatment weighted estimation of causal parameters in the presence of error-contaminated and time-dependent confounders. Biom J. 2019;61(6):1507-1525.
  23. Tsiatis AA, Degruttola V, Wulfsohn MS. Modeling the relationship of survival to longitudinal data measured with error: applications to survival and CD4 counts in patients with AIDS. J Am Stat Assoc. 1995;90(429):27-37.
  24. Cole SR, Hernán MA, Margolick JB, Cohen MH, Robins JM. Marginal structural models for estimating the effect of highly active antiretroviral therapy initiation on CD4 cell count. Am J Epidemiol. 2005;162(5):471-478.
  25. Arellano-Valle RB, Ozan S, Bolfarine H, Lachos VH. Skew normal measurement error models. J Multivar Anal. 2005;96:265-281.
  26. Stefanski LA, Carroll RJ. Conditional scores and optimal scores for generalized linear measurement-error models. Biometrika. 1987;74(4):703-716.
  27. Huang Y, Wang CY. Consistent functional methods for logistic regression with errors in covariates. J Am Stat Assoc. 2001;96(456):1469-1482.
  28. Carroll RJ, Ruppert D, Stefanski LA, Crainiceanu CM. Measurement Error in Nonlinear Models: A Modern Perspective. 2nd ed. Boca Raton: Chapman and Hall/CRC Press; 2006.
  29. Yi GY. Statistical Analysis with Measurement Error or Misclassification. New York: Springer-Verlag; 2017.
  30. Arellano-Valle RB, Azzalini A, Ferreira CS, Santoro K. A two-piece normal measurement error model. Comput Stat Data Anal. 2020;144:106863.
  31. Azzalini A. A class of distributions which includes the normal ones. Scand J Stat. 1985;12:171-178.
  32. Azzalini A, Dalla-Valle A. The multivariate skew-normal distribution. Biometrika. 1996;83:715-726.
  33. Yi GY, Yan Y. Estimation and hypothesis testing with error-contaminated survival data under possibly misspecified measurement error models. Can J Stat. 2021;49(3):853-874.
  34. Yan Y, Yi GY. A corrected profile likelihood method for survival data with covariate measurement error under the Cox model. Can J Stat. 2015;43(3):454-480.
  35. Yan Y, Yi GY. A class of functional methods for error-contaminated survival data under additive hazards models with replicate measurements. J Am Stat Assoc. 2016;111(514):684-695.
  36. Yan Y, Yi GY. Analysis of error-prone survival data under additive hazards models: measurement error effects and adjustments. Lifetime Data Anal. 2016;22:321-342.

MeSH Term

Humans
Probability
Computer Simulation
Time Factors
Longitudinal Studies
Journal Article Research Support, Non-U.S. Gov't
Article has an altmetric score of 1

Word Cloud

Created with Highcharts 10.0.0treatmenteffectmeasurementerrorIPTWmethodestimationstudiesconsistentproposedlongitudinalinverseprobabilityweightedtime-dependentconfoundersexistingcorrectionmethodsfunctionaveragecommonlyemployedestimatetreatmentsoutcomeinterestHoweverdocumentedsubjectnaivesimplyignoresleadsbiasedliteraturelackfullyremoveproducearticledevelopnovelprocedurekeystepuseobserveddataconstructcorrectedunbiasedunknownSimulationrevealoutperformsapproximateFinallyapplyanalyzerealdatasetConsistentmismeasuredcausalinferenceconditionalscoremarginalstructuralmodelsensitivityanalysis

Similar Articles

Cited By

No available data.