CoChat
Sign Up
Cited by 260Advanced Causal Inference TechniquesStatistical Methods in EpidemiologyMeta-analysis and systematic reviews

The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.

Risk Factors, Confounding, and the Illusion of Statistical Control

Christenfeld, Nicholas J. S., Sloan, Richard P., Carroll, Douglas, Greenland, Sander·2004·Psychosomatic Medicine
DOI 10.1097/01.psy.0000140008.70959.41
Open this paper in CoChat — free account

Abstract

When experimental designs are premature, impractical, or impossible, researchers must rely on statistical methods to adjust for potentially confounding effects. Such procedures, however, are quite fallible. We examine several errors that often follow the use of statistical adjustment. The first is inferring a factor is causal because it predicts an outcome even after "statistical control" for other factors. This inference is fallacious when (as usual) such control involves removing the linear contribution of imperfectly measured variables, or when some confounders remain unmeasured. The converse fallacy is inferring a factor is not causally important because its association with the outcome is attenuated or eliminated by the inclusion of covariates in the adjustment process. This attenuation may only reflect that the covariates treated as confounders are actually mediators (intermediates) and critical to the causal chain from the study factor to the study outcome. Other problems arise due to mismeasurement of the study factor or outcome, or because these study variables are only proxies for underlying constructs. Statistical adjustment serves a useful function, but it cannot transform observational studies into natural experiments, and involves far more subjective judgment than many users realize.

Overview

Integrity signals

Registry

Crossref · 10.1097/01.psy.0000140008.70959.41

Cites

0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Research works printed but not linked: 34

  1. Talcott, 1998, Co-occurrent use of cigarettes, alcohol, and caffeine in a retired military population., Mil Med, 163, 133, 10.1093/milmed/163.3.133 · DOI
  2. Greenland, 2003, Quantifying biases in causal models: classical confounding vs. collider-stratification bias., Epidemiology, 14, 300, 10.1097/01.EDE.0000042804.12056.6C · DOI · Paper page
  3. Cole, 2002, Fallibility is estimating direct effects., Int J Epidemiol, 31, 163, 10.1093/ije/31.1.163 · DOI · Paper page
  4. Greenland, 2002, An overview of relations among causal modelling methods., Int J Epidemiol, 31, 1030, 10.1093/ije/31.5.1030 · DOI · Paper page
  5. Robins, 1992, Identifiability and exchangeability for direct and indirect effects., Epidemiology, 3, 143, 10.1097/00001648-199203000-00013 · DOI · Paper page
  6. Hopkins, 1981, A survey of 246 suggested coronary risk factors., Atherosclerosis, 40, 1, 10.1016/0021-9150(81)90122-2 · DOI
  7. Davey Smith, 1992, Smoking as ‘independent’ risk factor for suicide: illustration of an artifact from observational epidemiology., Lancet, 340, 709, 10.1016/0140-6736(92)92242-8 · DOI · Paper page
  8. Elliott, 1996, Diagonal earlobe creases and prognosis in patients with suspected coronary artery disease., Am J Med, 100, 205, 10.1016/S0002-9343(97)89460-0 · DOI
  9. Gump, 2000, Are vacations good for your health? The 9-year mortality experience after the multiple risk factor intervention trial., Psychosom Med, 62, 608, 10.1097/00006842-200009000-00003 · DOI
  10. Pickering, 1999, Cardiovascular pathways: socioeconomic status and stress effects on hypertension and cardiovascular function., Ann NY Acad Sci, 896, 262, 10.1111/j.1749-6632.1999.tb08121.x · DOI
  11. Tikkanen, 1998, Associations between skeletal muscle properties, physical fitness, physical activity and coronary heart disease risk factors in men., Atherosclerosis, 137, 377, 10.1016/S0021-9150(97)00276-1 · DOI
  12. Greenland, 1980, Control of confounding in the assessment of medical technology., Int J Epidemiol, 9, 361, 10.1093/ije/9.4.361 · DOI
  13. Royston, 2000, A useful monotonic non-linear model with applications in medicine and epidemiology., Stat Med, 19, 2053, 10.1002/1097-0258(20000815)19:15<2053::AID-SIM505>3.0.CO;2-6 · DOI
  14. Hummer, 1999, Religious involvement and U.S. adult mortality., Demography, 36, 273, 10.2307/2648114 · DOI · Paper page
  15. Koenig, 1999, Does religious attendance prolong survival? A six-year follow-up study of 3,968 older adults., J Gerontol A Biol Sci Med Sci, 54, M370, 10.1093/gerona/54.7.M370 · DOI · Paper page
  16. Presser, 1998, Data collection mode and social desirability bias in self-reported religious attendance., Am Sociol Rev, 63, 137, 10.2307/2657486 · DOI
  17. Phillips, 1991, Bias in relative adds estimation owing to imprecise measurement of correlated exposures., Stat Med, 11, 953, 10.1002/sim.4780110712 · DOI · Paper page
  18. Frasure-Smith, 1995, Depression and 18-month prognosis after myocardial infarction., Circulation, 91, 999, 10.1161/01.CIR.91.4.999 · DOI
  19. Carroll, 2002, Depression and mortality following myocardial infarction: the issue of disease severity., Epidemiol Psichiatr Soc, 11, 65, 10.1017/S1121189X00005510 · DOI
  20. Lane, 2001, Mortality and quality of life 12 months after myocardial infarction: effects of depression and anxiety., Psychosom Med, 63, 221, 10.1097/00006842-200103000-00005 · DOI
  21. Lane, 2002, In-hospital symptoms of depression do not predict mortality three-years after myocardial infarction., Int J Epidemiol, 31, 1179, 10.1093/ije/31.6.1179 · DOI
  22. Mayou, 2000, Depression and anxiety as predictors of outcome after myocardial infarction., Psychosom Med, 62, 212, 10.1097/00006842-200003000-00011 · DOI
  23. Berkman, 2003, effects of treating depression and low perceived social support on clinical events after myocardial infarction: the Enhancing Recovery in Coronary Heart Disease (ENRICHD) randomized trial., JAMA, 289, 3106, 10.1001/jama.289.23.3106 · DOI · Paper page
  24. Louis, 2002, Clinical trials update: The Heart Protection Study, IONA, CARISA, ENRICHD, ALIVE, MADIT II and REMATCH., Eur J Heart Fail, 4, 111, 10.1016/S1388-9842(01)00240-9 · DOI
  25. Macleod, 2001, Are the effects of psychosocial exposures attributable to confounding? Evidence from a prospective observational study on psychological stress and mortality., J Epidemiol Commun Health, 55, 878, 10.1136/jech.55.12.878 · DOI
  26. Macleod, 2002, Psychological stress and cardiovascular disease: empirical demonstration of bias in a prospective observational study of Scottish men., Br Med J, 324, 1247, 10.1136/bmj.324.7348.1247 · DOI
  27. Suls, 1989, Effects of sensory and procedural information on coping with stressful medical procedures and pain: A meta-analysis., J Consult Clin Psychol, 57, 372, 10.1037/0022-006X.57.3.372 · DOI
  28. Smith, 1992, Socioeconomic differences in mortality: evidence from Glasgow graveyards., Br Med J, 305, 1554, 10.1136/bmj.305.6868.1554 · DOI
  29. Glynn, 2001, When stress happens matters: effects of earthquakes on stress responsivity in pregnancy., Am J Obstet Gynecol, 184, 637, 10.1067/mob.2001.111066 · DOI · Paper page
  30. Christenfeld, 1999, New York City as a risk factor for heart attack mortality., Psychosom Med, 61, 740, 10.1097/00006842-199911000-00003 · DOI
  31. Kulik, 1996, Social comparison and affiliation under threat: Effects on recovery from major surgery., J Pers Soc Psychol, 71, 967, 10.1037/0022-3514.71.5.967 · DOI
  32. Robins, 1989, Control of confounding by intermediate variables., Stat Med, 8, 679, 10.1002/sim.4780080608 · DOI
  33. Smith, 2003, Parachute use to prevent death and major trauma related to gravitational challenge: systematic review of randomised controlled trials., Br Med J, 327, 1459, 10.1136/bmj.327.7429.1459 · DOI
  34. Lane, 2004, Is depression following acute myocardial infarction an independent risk for mortality?, Am J Cardiol, 93, 1333, 10.1016/j.amjcard.2004.01.001 · DOI

Cited by

Sorted by citations

See all 260

Metadata

Authors
Christenfeld, N. J. S., Sloan, R. P., Carroll, D., & Greenland, S.
Affiliations
  • University of California San Diego (US)
  • University of California, Los Angeles (US)
Corresponding author
Christenfeld, Nicholas J. S.
ORCID
Venue
Psychosomatic Medicine
Publisher
Ovid Technologies (Wolters Kluwer Health)
Published
2004-11
Volume
66
Issue
6
Pages
868-875
ISSN
0033-3174 (ISSN-L)
DOI
10.1097/01.psy.0000140008.70959.41
OpenAlex
W2065056866
Cited by
260
References
0
Citations by year
2026: 6 · 2025: 6 · 2024: 8 · 2023: 5 · 2022: 11 · 2021: 21 · 2020: 15 · 2019: 17 · 2018: 7 · 2017: 4 · 2016: 13 · 2015: 8 · 2014: 14 · 2013: 14 · 2012: 28
FWCI
1.33
Type
journal article
Language
en
Open access
closed
Locations
  • Psychosomatic Medicine (publishedVersion)
  • PubMed (publishedVersion)
  • University of Birmingham Research Portal (University of Birmingham) (submittedVersion)
Topics
  • Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
Keywords
confounding, statistical adjustment, causal inference, risk factors, measurement error, mediators, covariate adjustment, observational studies, natural experiment
MeSH terms
Data Interpretation, Statistical, False Positive Reactions, Humans, Research Design, Risk Factors, Reproducibility of Results, Health Behavior, Bias, Confounding Factors, Epidemiologic, Randomized Controlled Trials as Topic, Outcome Assessment, Health Care, Observation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review