Chapter

Bias

Steve Selvin

in Epidemiologic Analysis

Published in print August 2001 | ISBN: 9780195146189
Published online September 2009 | e-ISBN: 9780199864720 | DOI: http://dx.doi.org/10.1093/acprof:oso/9780195146189.003.0004
Bias

More Like This

Show all results sharing this subject:

  • Public Health and Epidemiology

GO

Show Summary Details

Preview

This chapter presents a two-part study. The first part examines the regression to the mean incurred in measuring and remeasuring systolic blood pressure on the same individual. The second part evaluates an experimental diet thought to decrease the severity of benign breast disease when the results are biased by misclassification of individuals assigned to treatment and control groups. The analysis of the repeated blood pressure measurements shows substantial regression to the mean. Necessarily, an intraclass correlation coefficient indicates the same magnitude of regression to the mean. Specifically, the estimated slope is 0.769 from the regression analysis of the first and second blood pressure measurements, and the estimated intraclass correlation coefficient is 0.816. The clinical trial to evaluate the influence of a methylxanthine-free diet on the signs of benign breast disease produces no strong evidence that the diet is effective. The analysis comparing the intend-to-treat individuals yields an odd ratio of 1.420. This odds ratio, however, is reduced by considerable misclassification bias.

Keywords: systolic blood pressure; regression; Buffalo Blood Pressure Study; blood pressure measurements; breast disease; methylxanthine-free diet

Chapter.  4907 words.  Illustrated.

Subjects: Public Health and Epidemiology

Full text: subscription required

How to subscribe Recommend to my Librarian

Buy this work at Oxford University Press »

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.