Volume 39 · Number 7
JULY 2009
Where Do We Go Wrong in Assessing Risk Factors, Diagnostic and Prognostic Tests? The Problems of Two-by-two Association
By Helena Chmura Kraemer, PhD; Robert D. Gibbons, PhD
A vital issue in medical research is that of assessing the relationship between two binary variables: examining how well the presence/absence of a certain factor (eg, smoking, obesity) predicts a future event (prognostic test); how well a test result (eg, a blood, urine, skin, or imaging test) discriminates between those who do and do not have a disorder (a diagnostic test); and how well a decision rule (based on genes, gender, age, ethnicity, etc.) discriminates between those who will or will not succeed, etc.
ABOUT THE AUTHORS
Helena Chmura Kraemer, PhD, is Professor of Biostatistics in Psychiatry (Emerita), Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, California. Robert D. Gibbons, PhD, is with the Center for Health Statistics, University of Illinois at Chicago.
Address correspondence to: Helena Chmura Kraemer, PhD, Professor of Biostatistics in Psychiatry (Emerita), Department of Psychiatry and Behavioral Sciences, Stanford University, 1116 Forest Avenue, Palo Alto, CA 94301; or e-mail hckhome@pacbell.net.
Dr. Kraemer has disclosed no relevant financial relationships. Dr. Gibbons disclosed the following relevant financial relationships: National Institutes of Mental Health: research grant recipient (R56-MH078580 and R01-MH8012201).
doi: 10.3928/00485713-20090625-05
EDUCATIONAL OBJECTIVES
- Review two-by-two contingency tables.
- Express methods for assessing the strength of association between two binary variables.
- Explain design, sampling, and estimation issues in assessing risk, prognostic, and diagnostic factors.
Design and Analysis of Longitudinal Studies, Part 2
Of the Terrible Doubt of Appearances
Jan Fawcett, MD
Design and Analysis of Longitudinal Studies, Part 2
Robert D. Gibbons, PhD
A 54-year-old Man with History of PTSD
Violeta O. Tan, MD;
Natalie L. Rasgon, PhD
Using Non-experimental Data to Estimate Treatment Effects
Elizabeth A. Stuart, PhD;
Sue M. Marcus, PhD;
Marcela V. Horvitz-Lennon, MD;
Robert D. Gibbons, PhD;
Sharon-Lise T. Normand, PhD;
C. Hendricks Brown, PhD
Statistical Approaches to Modeling Multiple Outcomes in Psychiatric Studies
Armando Teixeira-Pinto, PhD;
Juned Siddique, DrPH;
Robert D. Gibbons, PhD;
Sharon-Lise T. Normand, PhD
Why Does the Randomized Clinical Trial Methodology So Often Mislead Clinical Decision Making? Focus on Moderators and Mediators of Treatment
Helena Chmura Kraemer, PhD;
Robert D. Gibbons, PhD
The Role of ANCOVA in Analyzing Experimental Data
Thomas R. Belin, PhD;
Sharon-Lise T. Normand, PhD
