A comparison of methods of scoring the General Health Questionnaire

Abstract

The General Health Questionnaire (GHQ) has been criticized for failing to detect individuals with chronic symptoms due to its focus on recent changes in one's usual state. Using data from a community survey in Edmonton, Canada, in which 3,258 subjects completed the 30-item GHQ and the Diagnostic Interview Schedule (DIS), the traditional method of scoring the GHQ was compared to a revised method proposed by Goodchild and Duncan-Jones. A case was defined to be someone with a history in the preceding month of one or more of the following DIS/DSM-III disorders: major depressive episode, phobia, panic disorder and obsessive-compulsive disorder. A receiver operating characteristic analysis demonstrated no difference in the two methods of scoring the GHQ.