In reflecting on correspondence and conversations following our recent review of the possible utility of the dexamethasone suppression test (DST) in psychiatry, we wish to make the following remarks and `amplifications. Certain evaluations pooled data from several studies to test for interesting trends by the use of ϰ2 statistics.1 Janicak et al2 recommended the use of a more conservative ϰ2 procedure developed by Mantel and Haenszel.3 We adapted their approach for use with a microcomputer and incorporated Yates' correction for small samples (the program is available from M.H.T.). The method computes a total ϰ2 statistic by accumulating data from contingency tables arising from each study and decomposes this overall value into a ϰ2 statistic of association testing the main effect, as influenced by the consistency of results across studies, as well as a statistic (ϰ2 for homogeneity) testing the consistency
Arana GW, Teicher MH, Baldessarini RJ. The Utility of the Dexamethasone Suppression Test-Reply. Arch Gen Psychiatry. 1987;44(1):95–96. doi:10.1001/archpsyc.1987.01800130107018
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: