Answer to Terrance and Mauree

John would want to use a repeat measures design because he wants to see if the program affects self-esteem.  In order to do this, he would have to test the self-esteem of the participant before they took the program and then again test the self-esteem of the participants after they took the class. Gravett and Wallnau (2010) refer to this, “as a repeated-measure design, or a within subjects design” (p.352), as there are two separate scores for each individual in the sample. This would allow for a t statistic that is based on different scores rather than raw scores.

For this study John would have to find a group of people that have been victims of domestic violence willing to take part in an 8-week program.  He would have to administer some sort of self-esteem test, in order to get a pre-score on the self-esteem levels of his participants before they enter the program.  He should attempt to get at least 25-30 participants in order to gain a sampling for his H1.  Once the program has been completed, John would need to administer the same test he did at the beginning of the program to see if the treatment validates the H1 claiming that the scores on a continuous scale did increase the participants’ self-esteem. John’s goal would be to use the sample of difference score to answer questions about the general population (Gravetter & Wallnau, 2010).

Maureen

Gravetter, F. J., & Wallnau, L. B. (2010). Statistics for the behavioral sciences (9th ed.). Belmont, CA: Wadsworth Cengage Learning. 

{hiddenBy}