14.4 An investigator is interested in the extent to which children are attentive to violent acts on television. An experiment is run with 120 subjects: half boys and half girls (sex, X) at each of three age levels (Age, A). Each child views six scenes differing with respect to the level of violence (V, 3 levels), and the type of character; half the scenes involve animal cartoon characters and the other involve human characters (C, 2 levels). The dependent variable is a measure of attention during presentation of the scene.

(a) State the SV, df, and error terms for this design.

(b) In an alternative design, each child might view only three scenes involving only one type of character; C would be a between-subjects variable. Present the SV, df, and EMS for this design. What tests will be affected by this change in design? In what way? EXERCISES 14.1 Consider the following data set: thing at A2 and check the sum of the two terms against SSSB/A calculated in part (a). Confirm that MSSB/A is the average of the two S×B mean squares.

(c) Suppose the children are available for only short periods of time, but the investigator has access to large numbers of subjects. What are the advantages and disadvantages of the original design [part (a)] as opposed to using a design in which each subject is tested only once in some combination of V and C?