Simpson's paradox: an example from hospital epidemiology.

Simpson's paradox was first recognized at the beginning of the 20th century, but few examples with real data have been presented. In this paper we present an example of this phenomenon from a multicenter study on nosocomial infections, and we try to explain intuitively this type of extreme confounding.

[1]  A. J. Severijnen,et al.  Sentinel System for Nosocomial Infections in the Netherlands A Pilot Study , 1997, Infection Control & Hospital Epidemiology.

[2]  C. I. Neutel,et al.  The potential for Simpson's paradox in drug utilization studies. , 1997, Annals of epidemiology.

[3]  S. Julious,et al.  Confounding and Simpson's paradox , 1994, BMJ.

[4]  T. Hargreave,et al.  European collaborative study of antibiotic prophylaxis for transurethral resection of the prostate. , 1993, European urology.

[5]  H. Verbrugh,et al.  Prophylactic ciprofloxacin for catheter-associated urinary-tract infection , 1992, The Lancet.

[6]  R. Regal,et al.  Conceptus viability, malformation, and suspect mutagens or teratogens in humans. The Yule-Simpson paradox and implications for inferences of causality in studies of mutagenicity or teratogenicity limited to human livebirths. , 1991, Teratology.

[7]  L. Hsu,et al.  Random sampling, randomization, and equivalence of contrasted groups in psychotherapy outcome research. , 1989, Journal of consulting and clinical psychology.

[8]  N. Ciraru‐Vigneron,et al.  [The value of antibiotic prophylaxis using cefotetan in high-risk abdominal hysterectomy. Apropos of a prospective randomized study of 71 patients]. , 1988, Revue francaise de gynecologie et d'obstetrique.

[9]  M. Sharf,et al.  Broad spectrum antibiotics as short term prophylaxis for elective abdominal hysterectomy: Comparison of mezlocillin, cefazolin and placebo , 1986, International journal of gynaecology and obstetrics: the official organ of the International Federation of Gynaecology and Obstetrics.

[10]  J M Robins,et al.  Estimation of a common effect parameter from sparse follow-up data. , 1985, Biometrics.

[11]  Minja K. Paik.  A Graphic Representation of a Three-Way Contingency Table: Simpson's Paradox and Correlation , 1985 .

[12]  P. Madsen,et al.  Antibiotic prophylaxis in transurethral surgery. , 1984, Urology.

[13]  O. Miettinen,et al.  Confounding: essence and detection. , 1981, American journal of epidemiology.

[14]  B. Burtch.  Suicide in Prison: a Commentary , 1979, British Journal of Psychiatry.

[15]  D. Hand.  Psychiatric Examples of Simpson's Paradox , 1979, British Journal of Psychiatry.

[16]  K. Rothman.  A pictorial representation of confounding in epidemiologic studies. , 1975, Journal of chronic diseases.

[17]  E. H. Simpson,et al.  The Interpretation of Interaction in Contingency Tables , 1951 .

[18]  G. Yule.  NOTES ON THE THEORY OF ASSOCIATION OF ATTRIBUTES IN STATISTICS , 1903 .

[19]  G. Yule.  On the Association of Attributes in Statistics: With Illustrations from the Material of the Childhood Society, &c , 1900 .

[20]  G. Yule,et al.  On the association of attributes in statistics, with examples from the material of the childhood society, &c , 1900, Proceedings of the Royal Society of London.