The goals of this article are to (a) describe differences between moderator and mediator effects; (b) provide nontechnical descriptions of how to examine each type of effect, including study design, analysis, and interpretation of results; (c) demonstrate how to analyze each type of effect; and (d) provide suggestions for further reading. The authors focus on the use of multiple regression because it is an accessible data-analytic technique contained in major statistical packages. When appropriate, they also note limitations of using regression to detect moderator and mediator effects and describe alternative procedures, particularly structural equation modeling. Finally, to illustrate areas of confusion in counseling psychology research, they review research testing moderation and mediation that was published in the Journal of Counseling Psychology during 2001.

The effects of religious coping, the potential moderation of such effects by religious affiliation (i.e., Catholic, Protestant), and the potential mediation of such effects by various factors (i.e., cognitive restructuring, social support, perceived control) were investigated in patients and significant others coping with the stress of kidney transplant surgery. At 3 and 12 months after transplantation, results showed that the use of religious coping was generally associated with better adjustment both concurrently and over time in both patients and significant others. These effects were moderated by religious affiliation, such that religious coping was more effective in promoting adjustment for Protestants than for Catholics. Religious coping was related to adjustment beyond the effects of the proposed mediators. Implications of these results for future research and practice are discussed.

The present study examined specific aspects of individuals' personal strivings as mediators, and religious tradition as a moderator, of the relationship between intrinsic religiousness and mental health. In a sample of 268 university students, the negative relationship between intrinsic religiousness and hostility was mediated by the degree of sanctification within individuals' strivings. The relationships between intrinsic religiousness and both anxiety and depression were moderated by religious tradition, with Catholics' intrinsic religiousness significantly associated with greater anxiety and depression but Protestants' intrinsic religiousness not significantly associated with either of these mental health variables. Implications of these results for future research on religiousness are discussed.

In two studies of kidney transplant patients and their significant others, the authors examined whether the relations between enacted social support and patient distress were moderated by patients' satisfaction with their relationship with the support provider (i.e., their significant other). In Study 1 (n = 121 couples), unsupportive spousal behaviors were associated with more distress only among patients who were less satisfied with their marital relationship. In Study 2 (n = 112 couples), the relations between unsupportive behaviors and distress again varied as a function of the patient's relationship satisfaction, although the particular pattern of the interaction depended on the specific unsupportive behaviors offered to the patient. In both studies, relationship dissatisfaction was associated with higher levels of patient distress. Supportive behaviors were not related to distress and did not interact with relationship satisfaction. Implications for future research on social support in marriage are discussed.

The goals of this article are to (a) describe differences between moderator and mediator effects; (b) provide nontechnical descriptions of how to examine each type of effect, including study design, analysis, and interpretation of results; (c) demonstrate how to analyze each type of effect; and (d) provide suggestions for further reading. The authors focus on the use of multiple regression because it is an accessible data-analytic technique contained in major statistical packages. When appropriate, they also note limitations of using regression to detect moderator and mediator effects and describe alternative procedures, particularly structural equation modeling. Finally, to illustrate areas of confusion in counseling psychology research, they review research testing moderation and mediation that was published in the Journal of Counseling Psychology during 2001.