Negative Controls: A Tool for Detecting Confounding and Bias in Observational Studies

Noncausal associations between exposures and outcomes are a threat to validity of causal inference in observational studies. Many techniques have been developed for study design and analysis to identify and eliminate such errors. Such problems are not expected to compromise experimental studies, where careful standardization of conditions (for laboratory work) and randomization (for population studies) should, if applied properly, eliminate most such noncausal associations. We argue, however, that a routine precaution taken in the design of biologic laboratory experiments—the use of “negative controls”—is designed to detect both suspected and unsuspected sources of spurious causal inference. In epidemiology, analogous negative controls help to identify and resolve confounding as well as other sources of error, including recall bias or analytic flaws. We distinguish 2 types of negative controls (exposure controls and outcome controls), describe examples of each type from the epidemiologic literature, and identify the conditions for the use of such negative controls to detect confounding. We conclude that negative controls should be more commonly employed in observational studies, and that additional work is needed to specify the conditions under which negative controls will be sensitive detectors of other sources of error in observational studies.

[1]  J. Robins,et al.  Instruments for Causal Inference: An Epidemiologist's Dream? , 2006, Epidemiology.

[2]  M. Lipsitch,et al.  Interleukin-17A Mediates Acquired Immunity to Pneumococcal Colonization , 2008, PLoS pathogens.

[3]  Ping Li,et al.  Potentially unintended discontinuation of long-term medication use after elective surgical procedures. , 2006, Archives of Internal Medicine.

[4]  A. B. Hill The Environment and Disease: Association or Causation? , 1965, Proceedings of the Royal Society of Medicine.

[5]  J. Robins,et al.  A Structural Approach to Selection Bias , 2004, Epidemiology.

[6]  Noel S Weiss,et al.  Can the "specificity" of an association be rehabilitated as a basis for supporting a causal hypothesis? , 2002, Epidemiology.

[7]  Cecile Viboud,et al.  Impact of influenza vaccination on seasonal mortality in the US elderly population. , 2005, Archives of internal medicine.

[8]  Sander Greenland,et al.  Causation and Causal Inference , 2021, International Encyclopedia of Statistical Science.

[9]  T. Cook,et al.  Quasi-experimentation: Design & analysis issues for field settings , 1979 .

[10]  Ann Aschengrau,et al.  Essentials of Epidemiology in Public Health , 2003 .

[11]  M. Lipsitch,et al.  Control-group selection importance in studies of antimicrobial resistance: examples applied to Pseudomonas aeruginosa, Enterococci, and Escherichia coli. , 2002, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[12]  J. I The Design of Experiments , 1936, Nature.

[13]  A. DeMaris Introduction to Regression Modeling , 2005 .

[14]  Wiebe R. Pestman,et al.  Instrumental Variables: Application and Limitations , 2006, Epidemiology.

[15]  Tom Jefferson,et al.  Vaccines for preventing influenza in the elderly. , 2010, The Cochrane database of systematic reviews.

[16]  Cecile Viboud,et al.  Mortality benefits of influenza vaccination in elderly people: an ongoing controversy. , 2007, The Lancet. Infectious diseases.

[17]  S. Suissa,et al.  Bias in observational study of the effectiveness of nasal corticosteroids in asthma. , 2005, The Journal of allergy and clinical immunology.

[18]  M Alan Brookhart,et al.  Evaluating Short-Term Drug Effects Using a Physician-Specific Prescribing Preference as an Instrumental Variable , 2006, Epidemiology.

[19]  Sander Greenland,et al.  Causal Diagrams , 2011, International Encyclopedia of Statistical Science.

[20]  J. Nelson,et al.  Evidence of bias in estimates of influenza vaccine effectiveness in seniors. , 2006, International journal of epidemiology.

[21]  S. van Buuren,et al.  Selective association of multiple sclerosis with infectious mononucleosis , 2008, Multiple sclerosis.

[22]  J. Ledolter,et al.  Introduction to Regression Modeling , 2005 .