Repeated Measurements Designs, III.

Abstract

Repeated measurements designs (RM designs) are experiments in which an experimental unit is exposed to a sequence of treatments during a number of periods(days). A measurement taken on a unit depends on the treatment administered in the previous period (residual effect), the unit itself (unit effect) and the present period (Period effect). In the first part of the paper, after defining the concept of balanced and connected RM design, we proceed in constructing large families of balanced and connected RM designs when the number of periods is less than the number of treatments. In the last section we discuss the structure and the ranks of the C-matrices for direct and residual effects which arise from these designs, as well as the form of the best linear unbiased estimators of estimable contrasts of residual and direct effects. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 1978
Accession Number
ADA064965

Entities

People

  • A. S. Hedayat
  • C. Magda

Organizations

  • University of Illinois at Chicago

Tags

Communities of Interest

  • Advanced Electronics

DTIC Thesaurus Topics

  • Air Force
  • Coefficients
  • Computations
  • Construction
  • Contrast
  • Estimators
  • Illinois
  • Mathematical Analysis
  • Mathematics
  • Measurement
  • Numbers
  • Observation
  • Polynomials
  • Rational Numbers
  • Residuals
  • Sequences
  • Universities

Fields of Study

  • Mathematics

Readers

  • Graph Algorithms and Convex Optimization.
  • Regression Analysis.
  • Systems Analysis and Design