The literature on religious activity and health outcomes is fraught with methodological difficulties.1 Regrettably, the article by Harris et al2 on the impact of intercessory prayer in the coronary care unit (CCU) continues this tradition. Evidence for the conclusion that prayer has an impact on clinical course in the CCU and "may be an effective adjunct to standard medical care"2 is weak at best. Although the intercessors were instructed to pray for a speedy recovery, the prayer and control groups did not differ in length of stay in the CCU or in the hospital, nor did they differ on the Byrd scale. They only differed on the unvalidated Mid American Heart Institute–Cardiac Care Unit (MAHI-CCU) scale constructed for the purpose of this study. The lack of construct validity raises serious questions about this finding.