The paper “The Psychological Consequences of Money” (Science [2006]: 1154–1156) describes several experiments designed to investigate the way in which money can change behavior. In one experiment, participants completed one of two versions of a task in which they were given lists of five words and were asked to rearrange four of the words to create a sensible phrase. For one group, half of the 30 unscrambled phrases related to money, whereas the other half were phrases that were unrelated to money. For the second group (the control group), none of the 30 unscrambled phrases related to money. Participants were 44 students at Florida State University. Participants received course credit and $2 for their participation. The following description of the experiment is from the paper:

Participants were randomly assigned to one of two conditions, in which they descrambled phrases that primed money or neutral concepts. Then participants completed some filler questionnaires, after which the experimenter told them that the experiment was finished and gave them a false debriefing.

This step was done so that participants would not connect the donation opportunity to the experiment. As the experimenter exited the room, she mentioned that the lab was taking donations for the University Student Fund and that there was a box by the door if the participant wished to donate.

Amount of money donated was the measure of helping. We found that participants primed with money donated significantly less money to the student fund than participants not primed with money [t(38) 2.13, P  0.05].

The paper also gave the following information on amount donated for the two experimental groups.

Group Mean Standard Deviation Money primed $0.77 $0.74 Control $1.34 $1.02

a. Explain why the random assignment of participants to experimental groups is important in this experiment.

b. Use the given information to verify the values of the test statistic and degrees of freedom (38, given in parentheses just after the t in the quote from the paper) and the statement about the P-value. Assume that both sample sizes are 22.

c. Do you think that use of the two-sample t test was appropriate in this situation? Hint: Are the assumptions required for the two-sample t test reasonable?