Presenting the uncertainties of odds ratios using empirical-Bayes prediction intervals.

PloS One
Wan-Yu Lin, Wen-Chung Lee

Abstract

Quantifying exposure-disease associations is a central issue in epidemiology. Researchers of a study often present an odds ratio (or a logarithm of odds ratio, logOR) estimate together with its confidence interval (CI), for each exposure they examined. Here the authors advocate using the empirical-Bayes-based 'prediction intervals' (PIs) to bound the uncertainty of logORs. The PI approach is applicable to a panel of factors believed to be exchangeable (no extra information, other than the data itself, is available to distinguish some logORs from the others). The authors demonstrate its use in a genetic epidemiological study on age-related macular degeneration (AMD). The proposed PIs can enjoy straightforward probabilistic interpretations--a 95% PI has a probability of 0.95 to encompass the true value, and the expected number of true values that are being encompassed is 0.95m for a total of m 95% PIs. The PI approach is theoretically more efficient (producing shorter intervals) than the traditional CI approach. In the AMD data, the average efficiency gain is 51.2%. The PI approach is advocated to present the uncertainties of many logORs in a study, for its straightforward probabilistic interpretations and higher efficiency while...Continue Reading

References

Jan 1, 1983·European Journal of Clinical Pharmacology·V W Steinijans, E Diletti
Jan 1, 1994·Archives of Environmental Health·S Greenland, C Poole
Jul 12, 2002·Genetic Epidemiology·Bradley Efron, Robert Tibshirani
Jul 29, 2003·Proceedings of the National Academy of Sciences of the United States of America·John D Storey, Robert Tibshirani
Jan 13, 2004·Statistics in Medicine·Helena Chmura Kraemer
Sep 25, 2004·Genetic Epidemiology·Dmitri V Zaykin
Oct 27, 2004·Statistics in Medicine·Tamás Rudas, Bergsma Wicher
Jan 8, 2005·Genetic Epidemiology·Alessandro RinaldoKathryn Roeder
Feb 5, 2005·Bioinformatics·Susmita Datta, Somnath Datta
Mar 12, 2005·Science·Robert J KleinJosephine Hoh
May 2, 2006·Statistical Applications in Genetics and Molecular Biology·Yan LinEleanor Feingold
Aug 2, 2007·American Journal of Human Genetics·Gary K Chen, John S Witte
Nov 23, 2007·Occupational and Environmental Medicine·A 't MannetjeN Pearce
Oct 9, 2009·European Journal of Epidemiology·Ulf Strömberg
Mar 25, 2010·Journal of the American Statistical Association·Bradley Efron
Jul 10, 2010·International Journal of Environmental Research and Public Health·Yuejen ZhaoTony Barnes
Oct 5, 2010·Statistical Applications in Genetics and Molecular Biology·J T Gene Hwang, Peng Liu

❮ Previous
Next ❯

Related Concepts

Related Feeds

Blood And Marrow Transplantation

The use of hematopoietic stem cell transplantation or blood and marrow transplantation (bmt) is on the increase worldwide. BMT is used to replace damaged or destroyed bone marrow with healthy bone marrow stem cells. Here is the latest research on bone and marrow transplantation.

B-Cell Lymphoma

B-cell lymphomas include lymphomas that affect B cells. This subtype of cancer accounts for over 80% of non-Hodgkin lymphomas in the US. Here is the latest research.