This article is only available in the PDF format. Download the PDF to view the article, as well as its associated figures and tables.
In Reply.—Drs Pascoe and Davis have raised several issues that also concerned us in the preparation of this article. First, we were as concerned as they were regarding selection of the subjects involved in this study. It was precisely this concern that led us to include all of those subjects, and only those subjects, on whom data concerning all of the variables were available. No other criteria were used for selection. In reviewing subjects on whom all of the data were not available, the selection that we made did not seem to be biased since the incomplete data were randomly distributed with regard to the missing variables. Furthermore, had we included subjects on whom incomplete data were available, we would have been presenting an incomplete and confusing picture of the population studied.
Second, the correspondents are correct in their comments concerning the possibility of expectation bias with respect to
GOLDSON E. Child Abuse-Reply. Am J Dis Child. 1979;133(4):448–449. doi:10.1001/archpedi.1979.02130040102031
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: