International Journal of Statistics and Systems
  • Year: 2008
  • Volume: 3
  • Issue: 2

Factorial change over designs balanced for one factor

  • Author:
  • Lokesh Dwivedi, Cini Varghese, Seema Jaggi
  • Total Page Count: 9
  • Page Number: 137 to 145

Indian Agricultural Statistics Research Institute, New Delhi-110 012, (India).

Abstract

Change over designs (CODs) are an important class of designs that are especially useful when there is a scarcity in homogeneous experimental units. In these designs, each experimental unit receives some or all of the treatments, one at a time, in successive periods. The distinguishing feature of these designs is the presence of residual effects of the treatments that persist to the succeeding periods of treatment application. In many experimental situations, it is often required to measure the effect of response from two factors where one of the factors exhibits residual effects while the other does not. Two classes of uniform strongly balanced CODs with two factors balanced for residual effects of levels of one factor have been obtained in this study to meet such situations. These designs are variance balanced in the sense that the contrasts pertaining to direct effects of treatment combinations consisting of various levels of both the factors are always estimated with a constant variance.

Keywords

circular design, direct effect, factorial change over design, pre-period, residual effect, strongly balanced, uniform, variance balance