Replicating psychiatric ratings through multiple regression analysis: The Midtown Manhattan Restudy.

This paper examines three related questions: First, can psychiatrists' judgments be successfully predicted by multiple regression techniques? Second, assuming that they can, are such ratings a valid measure of mental health for the same sample at a later point in time? Third, what is the relation between mental health ratings made in 1954 and such subsequently reported behavioral outcomes as nervous breakdown, mental hospitalization, or seeking professional help for emotional problems? The evidence presented warrants two conclusion. (1) The computer-derived mental health ratings are an adequate substitute for the original ratings. The regression equation accounts for 69 percent of the variance in those ratings; and the computer-derived ratings behave in the same way as the psychiatrists' ratings in relation to other variables. (2) However, neither the psychiatrists' ratings nor the computer-derived ratings are very accurate in predicting subsequent self-reported behavior indicative of mental impairment.