A Quick and Easy Multiple Use Calibration Curve Procedure
Abstract
The standard multiple use calibration procedure due to Scheffe (1973) states that with probability 1-delta, the proportion of calculated confidence intervals containing the true unknowns is at least 1-alpha in the long run. The probability 1-delta refers to the probability that the calibration experiment results in a 'good' outcome. In Scheffe's formulation a good outcome involves both coverage of the true underlying regression curve and an upper confidence limit for sigma, the scale parameter. Scheffe's procedure is fairly difficult for practitioners to apply because it relies on tables that are not easy to use. A simpler notion of 'goodness' which only requires the calibration experiment to result in coverage of the underlying regression leads to easily calculated confidence intervals for the unknowns. In addition, these intervals are generally shorter than Scheffe's. An application example is given to illustrate the technique.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 1988
- Accession Number
- ADA198227
Entities
People
- C. H. Spiegelman
- J. Sacks
- R. J. Carroll
Organizations
- Texas A&M University