Incomplete Block Designs for Comparing Treatments with a Control. II. Optimal Designs for p = 2(1)6, k = 2 and p = 3, k =3.
Abstract
In this paper we continue the study of balanced treatment incomplete block (BTIB) designs. These designs are appropriate for comparing simultaneously p > or = 2 test treatments with a control treatment--the so-called multiple comparisons with a control (MCC) problem. In the present paper we obtain optimal designs within this class for selected (p,k,b) where k < p+1 is the number of plots per block, and b is the total number of blocks available. Specifically, optimal designs are obtained for p = 2 (1) 6, k = 2 and for p = 3, k = 3. Tables of exact (discrete) optimal designs are given for these (p,k)-values for a range of b-values which would ordinarily be of practical interest. Tables of approximate (continuous) optimal designs are given for situations in which very large b-values are required. The theory underlying these approximate designs is developed, and the goodness of the approximation is studied.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 1979
- Accession Number
- ADA077919
Entities
People
- Ajit C. Tamhane
- Robert E. Bechhofer
Organizations
- Cornell University College of Engineering