ABSTRACT
A treatment is called a random effect when the levels of the treatment are a random sample of levels from a population of possible levels (Milliken and Johnson, 1992). Assume that there is one covariate and that a simple linear model describes the relationship between the mean of the response and the covariate for each treatment. Since the levels of the treatments are randomly selected from a population of possible levels, the mean of the response given the value of the covariate or the model for a selected treatment is also a random variable. More specifically, the coefficients of the model corresponding to the randomly selected treatment are random variables. These models are referred to as random coefficient models. Three examples are used to demonstrate the use of these models.
