"The term experimental design refers to a randomization plan for assigning participants to experimental conditions and the statistical analysis associated with the plan.
The simplest experimental design is the randomization and analysis plan that is used with a t test for independent samples. A t test for dependent samples uses a more complex randomization plan, but the added complexity is usually accompanied by greater power. The next level of design complexity is the randomization and analysis plan that is used with a completely randomized ANOVA design (CR-p design). This design is appropriate for an experiment that has one treatment with p ≥ 2 levels. As you will see, the randomized block design and the completely randomized factorial design described in this chapter utilize features of the designs discussed earlier.
Controlling Nuisance Variables
A large error variance,, can mask or obscure the effects of a treatment. Hence, in designing an experiment, you want to minimize variables that contribute to error variance. Other variables that can contribute to error variance include administering the levels of a treatment under different environmental conditions say; at different times of the day or locations—and having different researchers administer the treatment levels. Variation in the dependent variable that is attributable to such sources is called nuisance variation. Three approaches to controlling or minimizing these undesired sources of variation are as follows:
Hold the nuisance variables constant—for example, use only 19-year-old women participants—and have the same researcher administer the treatment levels at the same time of day and in the same research facility. Assign the participants randomly to the treatment levels so that known and unsuspected sources of variation among the participants are distributed over the entire experiment and thus do not affect just one or a limited number of treatment levels. If the treatment levels must be...
Please join StudyMode to read the full document