Chapter 12.1, Problem 27E

(a)

To determine

To explain why this was an experiment and not an observational study.

Explanation of Solution

In the question Mr. Starnes designed a study to examine the questions that does the color in which words are printed affect your ability to read them and so the words themselves affect your ability to name the color in which they are printed. Thus, as we know that an experiment deliberately imposes some treatment on individuals in order to observe their responses. And the observational study tries to gather the information without disturbing the scene they are observing. Thus, this was an experiment and not an observational study because each subjects had two treatments and they affect the individuals in the study.

(b)

To determine

To explain did Mr. Starnes use a completely randomized design or a randomized block design and why do you think he chose this experimental design.

Answer to Problem 27E

Mr. Starnes uses a randomized block design.

Explanation of Solution

In the question Mr. Starnes designed a study to examine the questions that does the color in which words are printed affect your ability to read them and so the words themselves affect your ability to name the color in which they are printed. Thus, in this case Mr. Starnes use a randomized block design because each subject received two treatments and thus each subject forms a block. And the other option, completely randomized design, would require that each subject receives one treatment and thus not two.

(c)

To determine

To explain the purpose of the random assignment in the context of the study.

Explanation of Solution

In the question Mr. Starnes designed a study to examine the questions that does the color in which words are printed affect your ability to read them and so the words themselves affect your ability to name the color in which they are printed. Thus, random assignment is used to make different groups of subjects as similar as possible which is required to eliminate possible confounding. And in this case, the order in which the two treatments are given is randomly assigned such that experience does not influence the results. Thus the experience would be a possible confounding variable when no random assignment occurs.