Anticipated Patterns of Response
Design sensitivity is used to quantify the effectiveness of devices discussed in Chapter 5. Several of those devices anticipate a particular pattern of results, perhaps coherence among several outcomes, or a dose-response relationship. To what extent do these considerations reduce sensitivity to unmeasured biases?
KeywordsOptimal Weight Statist Assoc Multivariate Normal Distribution Design Sensitivity Verbal Score
Unable to display preview. Download preview PDF.
- Heller, R., Rosenbaum, P.R., Small, D. : Split samples and design sensitivity in observational studies. J Am Statist Assoc 104, to appear (2009)Google Scholar
- Rosenbaum, P.R.: What aspects of the design of an observational study affect its sensitivity to bias from covariates that were not observed? In: Festshrift for Paul W. Holland. Princeton, NJ: ETS (2009)Google Scholar
- Small, D.S., Rosenbaum, P.R.: Error-free milestones in error-prone measurements. Ann App Statist, to appear (2009)Google Scholar