Skip to main content
SpringerLink
Log in

Sensitivity Analysis and Bias Analysis

  • Reference work entry
Book cover Handbook of Epidemiology

Abstract

Over recent decades recognition has grown that the conventional statistical models used to analyze epidemiological data cannot be reasonably claimed to be correct in the way most textbooks treat them to be. In particular, conventional models for epidemiological data-generating processes cannot be credibly taken to represent targets of primary scientific interest. For example, a logistic model for the regression of an observed disease indicator on covariate measurements would only rarely correspond closely to the causal effects on disease of the risk factors represented by the measurements. The discrepancies between the statistical model parameters and the underlying target effects are often called systematic errors, biases, or bias sources. Large biases undermine the interpretation of both frequentist statistics (such as confidence intervals) and Bayesian statistics (such as posterior intervals).

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 999.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 1,399.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  • Breslow NE, Day NE (1980) Statistical methods in cancer research. Vol I: the analysis of case-control data. IARC, Lyon

    Google Scholar 

  • Bross IDJ (1966) Spurious effects from an extraneous variable. J Chronic Dis 19:637–647

    Article  CAS  PubMed  Google Scholar 

  • Bross IDJ (1967) Pertinency of an extraneous variable. J Chronic Dis 20:487–495

    Article  CAS  PubMed  Google Scholar 

  • Brumback BA, Hernan MA, Haneuse S, Robins JM (2004) Sensitivity analyses for unmeasured confounding assuming a marginal structural model for repeated measures. Stat Med 23: 749–767

    Article  PubMed  Google Scholar 

  • Carroll RJ, Ruppert D, Stefanski LA, Crainiceanu C (2006) Measurement error in nonlinear models, 2nd edn. Chapman and Hall, Boca Raton

    Book  Google Scholar 

  • Cole SR, Chu H, Greenland S (2006) Multiple-imputation for measurement-error correction (with comment). Int J Epidemiol 35:1074–1082

    Article  PubMed  Google Scholar 

  • Copas JB, Li HG (1997) Inference for non-random samples (with discussion). J R Stat Soc Ser B 59:55–77

    Article  Google Scholar 

  • Cornfield J, Haenszel WH, Hammond EC, Lilienfeld AM, Shimkin MB, Wynder EL (1959) Smoking and lung cancer: recent evidence and a discussion of some questions. J Natl Cancer Inst 22:173–203

    CAS  PubMed  Google Scholar 

  • Chu H, Wang Z, Cole SR, Greenland S (2006) Sensitivity analysis of misclassification: a graphical and a Bayesian approach. Ann Epidemiol 16:834–841

    Article  PubMed  Google Scholar 

  • Eddy DM, Hasselblad V, Schachter R (1992) Meta-analysis by the confidence profile method. Academic press, New York

    Google Scholar 

  • Efron B, Tibshirani RJ (1994) An introduction to the bootstrap. Chapman and Hall, New York

    Google Scholar 

  • Flanders WD, Khoury MJ (1990) Indirect assessment of confounding: graphic description and limits on effect of adjusting for covariates. Epidemiology 1:199–246

    Google Scholar 

  • Fox MP, Lash TL, Greenland S (2005) A method to automate probabilistic sensitivity analyses of misclassified binary variables. Int J Epidemiol 34:1370–1376

    Article  PubMed  Google Scholar 

  • Gail MH, Wacholder S, Lubin JH (1988) Indirect corrections for confounding under multiplicative and additive risk models. Am J Ind Med 13:119–130

    Article  CAS  PubMed  Google Scholar 

  • Glymour MM, Greenland S (2008) Causal diagrams. Chapter 12. In: Rothman KJ, Greenland S, Lash TL (eds) Modern epidemiology, 3rd edn. Lippincott-Williams-Wilkins, Philadelphia, pp 183–209

    Google Scholar 

  • Graham P (2000) Bayesian inference for a generalized population attributable fraction. Stat Med 19:937–956

    Article  CAS  PubMed  Google Scholar 

  • Greenland S (1998) The sensitivity of a sensitivity analysis. In: 1997 Proceedings of the biometrics section. American Statistical Association, Alexandria, pp 19–21

    Google Scholar 

  • Greenland S (2001) Sensitivity analysis, Monte-Carlo risk analysis, and Bayesian uncertainty assessment. Risk Anal 21:579–583

    Article  CAS  PubMed  Google Scholar 

  • Greenland S (2003) The impact of prior distributions for uncontrolled confounding and response bias. J Am Stat Assoc 98:47–54

    Article  Google Scholar 

  • Greenland S (2005) Multiple-bias modeling for observational studies (with discussion). J R Stat Soc Ser A 168:267–308

    Article  Google Scholar 

  • Greenland S (2008) Introduction to Bayesian statistics. Chapter 18. In: Rothman KJ, Greenland S, Lash TL (eds) Modern epidemiology, 3rd edn. Lippincott-Williams-Wilkins, Philadelphia, pp 328–344

    Google Scholar 

  • Greenland S (2009a) Bayesian perspectives for epidemiologic research. III. Bias analysis via missing-data methods. Int J Epidemiol 38:1662–1673. corrigendum (2010) Int J Epidemiol 39:1116

    Google Scholar 

  • Greenland S (2009b) Relaxation penalties and priors for plausible modeling of nonidentified bias sources. Stat Sci 24:195–210

    Article  Google Scholar 

  • Greenland S, Lash TL (2008) Bias analysis. Chapter 19. In: Rothman KJ, Greenland S, Lash TL (eds) Modern epidemiology, 3rd edn. Lippincott-Williams-Wilkins, Philadelphia, pp 345–380

    Google Scholar 

  • Greenland S, Maldonado G (1994) The interpretation of multiplicative model parameters as standardized parameters. Stat Med 13:989–999

    Article  CAS  PubMed  Google Scholar 

  • Greenland S, Mickey RM (1988) Closed form and dually consistent methods for inference on strict collapsibility in 2x2xK and 2xJxK tables. Appl Stat 37:335–343

    Article  Google Scholar 

  • Greenland S, Gago-Domiguez M, Castellao JE (2004) The value of risk-factor (“black-box”) epidemiology (with discussion). Epidemiology 15:519–535

    Article  Google Scholar 

  • Gustafson P (2003) Measurement error and misclassification in statistics and epidemiology: impacts and Bayesian adjustments. Chapman and Hall/CRC, Boca Raton

    Book  Google Scholar 

  • Gustafson P (2005) On model expansion, model contraction, identifiability, and prior information (with discussion). Stat Sci 20:111–140

    Article  Google Scholar 

  • Gustafson P, Le ND, Saskin R (2001) Case–control analysis with partial knowledge of exposure misclassification probabilities. Biometrics 57:598– 609

    Article  CAS  PubMed  Google Scholar 

  • Gustafson P, McCandless LC, Levy AR, Richardson SR (2010) Simplified Bayesian sensitivity analysis for mismeasured and unobserved confounders. Biometrics 66:1129–1137

    Article  CAS  PubMed  Google Scholar 

  • Hatch EE, Kleinerman RA, Linet MS, Tarone RE, Kaune WT, Auvinen A, Baris D, Robison LL, Wacholder S (2000) Do confounding or selection factors of residential wire codes and magnetic fields distort findings of electromagnetic fields studies? Epidemiology 11:189–198

    Article  CAS  PubMed  Google Scholar 

  • Joseph L, Gyorkos TW, Coupal L (1995) Bayesian estimation of disease prevalence and the parameters of diagnostic tests in the absence of a gold standard. Am J Epidemiol 141: 263–272

    CAS  PubMed  Google Scholar 

  • Kitagawa EM (1955) Components of a difference between two rates. J Am Stat Assoc 50: 1168–1194

    Google Scholar 

  • Kraus JF, Greenland S, Bulterys MG (1989) Risk factors for sudden infant death syndrome in the U.S. Collaborative Perinatal Project. Int J Epidemiol 18:113–120

    Article  CAS  PubMed  Google Scholar 

  • Lash TL, Fink AK (2003) Semi-automated sensitivity analysis to assess systematic errors in observational epidemiologic data. Epidemiology 14:451–458

    PubMed  Google Scholar 

  • Lash TL, Fox MP, Fink AK (2009) Applying quantitative bias analysis to epidemiologic data. Springer, New York

    Book  Google Scholar 

  • Leamer EE (1974) False models and post-data model construction. J Am Stat Assoc 69:122–131

    Article  Google Scholar 

  • Leamer EE (1978) Specification searches. Wiley, New York

    Google Scholar 

  • Leamer EE (1985) Sensitivity analyses would help. Am Econ Rev 75:308–313

    Google Scholar 

  • Little RJA, Rubin DB (2002) Statistical analysis with missing data, 2nd edn. Wiley, New York

    Google Scholar 

  • Lyles RH (2002) A note on estimating crude odds ratios in case-control studies with differentially misclassified exposure. Biometrics 58:1034–1037

    Article  PubMed  Google Scholar 

  • MacLehose RF, Gustafson P (2012) Is probabilistic bias analysis approximately Bayesian? Epidemiology 23:151–158

    Article  PubMed Central  PubMed  Google Scholar 

  • McCandless LC, Gustafson P, Levy AR (2007) Bayesian sensitivity analysis for unmeasured confounding in observational studies. Stat Med 26:2331–2347

    Article  PubMed  Google Scholar 

  • McCandless LC, Gustafson P, Levy AR, Richardson SR (2012) Hierarchical priors for bias parameters in Bayesian sensitivity analysis for unmeasured confounding. Stat Med 31: 383–396

    Article  PubMed  Google Scholar 

  • Molitor N-T, Best N, Jackson C, Richardson S (2009) Using Bayesian graphical models to model biases in observational studies and to combine multiple sources of data: application to low birth weight and water disinfection by-products. J R Stat Soc Ser A 172:615–638

    Article  Google Scholar 

  • Neath AA, Samaniego FJ (1997) On the efficacy of Bayesian inference for nonidentifiable models. Am Stat 51:225–232

    Google Scholar 

  • Orsini N, Bellocco R, Bottai M, Wolk A, Greenland S (2008) A tool for deterministic and probabilistic sensitivity analysis of epidemiologic studies. Stata J 8:29–48

    Google Scholar 

  • Pearl J (2009) Causality, 2nd edn. Cambridge University Press, New York

    Book  Google Scholar 

  • Pepe MS, Janes H, Longton G, Leisenring W, Newcomb P (2004) Limitations of the odds ratio in gauging the performance of a diagnostic, prognostic, or screening marker. Am J Epidemiol 159:882–890

    Article  PubMed  Google Scholar 

  • Phillips CV (2003) Quantifying and reporting uncertainty from systematic errors. Epidemiology 14:459–466

    PubMed  Google Scholar 

  • Rosenbaum PR (2002) Observational studies, 2nd edn. Springer, New York

    Book  Google Scholar 

  • Saltelli A, Chan K, Scott EM (eds) (2000) Sensitivity analysis. Wiley, New York

    Google Scholar 

  • Scharfstein DO, Daniels MJ, Robins JM (2003) Incorporating prior beliefs about selection bias into the analysis of randomized trials with missing outcomes. Biostatistics 4:495–512

    Article  PubMed Central  PubMed  Google Scholar 

  • Schlesselman JJ (1978) Assessing effects of confounding variables. Am J Epidemiol 108:3–8

    CAS  PubMed  Google Scholar 

  • Schneeweiss S (2006) Sensitivity analysis and external adjustment for unmeasured confounders in epidemiologic database studies of therapeutics. Pharmacoepidemiol Drug Saf 15:291–303

    Article  PubMed  Google Scholar 

  • Steenland K, Greenland S (2004) Monte Carlo sensitivity analysis and Bayesian analysis of smoking as an unmeasured confounder in a study of silica and lung cancer. Am J Epidemiol 160:384–392

    Article  PubMed  Google Scholar 

  • Turner RM, Spiegelhalter DJ, Smith GCS, Thompson SG (2009) Bias modeling in evidence Synthesis. J R Stat Soc Ser A 172:21–47

    Article  Google Scholar 

  • VanderWeele TJ, Arah OA (2011) Bias formulas for sensitivity analysis of unmeasured confounding for general outcomes, treatments and confounders. Epidemiology 22:42–52

    Article  PubMed Central  PubMed  Google Scholar 

  • Vansteelandt S, Goetghebeur E, Kenward MG, Molenberghs G (2006) Ignorance and uncertainty regions as inferential tools in a sensitivity analysis. Stat Sin 16:953–980

    Google Scholar 

  • Welton NJ, Ades AE, Carlin JB, Altman DG, Sterne JAC (2009) Models for potentially biased evidence in meta-analysis using empirically based priors. J R Stat Soc Ser A 172:119–136

    Article  Google Scholar 

  • Yanagawa T (1984) Case-control studies: assessing the effect of a confounding factor. Biometrika 71:191–194

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Epidemiology, School of Public Health, University of California, 90095-1772, Los Angeles, CA, USA

    Sander Greenland

Authors
  1. Sander Greenland
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Epidemiological Methods and Etiologic Research, Leibniz Institute for Prevention Research and Epidemiology – BIPS, Bremen, Germany

    Wolfgang Ahrens

  2. Department of Biometry and Data Management, Leibniz Institute for Prevention Research and Epidemiology – BIPS, Bremen, Germany

    Iris Pigeot

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer Science+Business Media New York

About this entry

Cite this entry

Greenland, S. (2014). Sensitivity Analysis and Bias Analysis. In: Ahrens, W., Pigeot, I. (eds) Handbook of Epidemiology. Springer, New York, NY. https://doi.org/10.1007/978-0-387-09834-0_60

Download citation

  • DOI: https://doi.org/10.1007/978-0-387-09834-0_60

  • Publisher Name: Springer, New York, NY

  • Print ISBN: 978-0-387-09833-3

  • Online ISBN: 978-0-387-09834-0

  • eBook Packages: MedicineReference Module Medicine

Publish with us

Policies and ethics

Search

Navigation