In a study that examines whether client self-reports of satisfaction with counseling differ between male and female therapists, when should a researcher use a two-tailed test of significance?

1. The researcher finds that the two variables (gender and client satisfaction with counseling), which generally are thought of being related, are really not related.
2. The researcher believes that she knows the direction of the relationship between the two variables.
3. The researcher isn't sure whether male or female therapists perform better in therapy.

d. If the client sample is less than 25, the research should use a two-tailed test of

significance.