摘要：Common statistical analyses were applied to the statistics on medical school libraries published in 1964 and 1966 in the Bulletin to assess the potential utility of such survey data. The major conclusions of the study are that these statistics (1) are highly redundant; (2) are essentially descriptive and not amenable to analysis for predictive purposes; (3) are of questionable reliability; (4) are of minimal utility for library investigators and managers, and of doubtful value for establishing standards. The authors believe that, rather than continuing to collect similar statistics in the future, we need a systematic program to define specific requirements of data use and to design survey methods that will produce data meeting these requirements.
