Optimal Scale in Medical Practice: A Survivor Analysis

The issue of optimal scale in medical practice has received a great deal of attention in the literature.' Researchers have used a variety of methods to determine the relative efficiency of solo versus group practices of various sizes. The empirical results have unfortunately not been consistent. They have run the gamut of weakly favoring solo practice2 to asserting that groups of over 30 physicians are most efficient.3 The purpose of this paper is to point out some of the measurement problems that have plagued these studies (and are likely to hinder similar studies in the future) and to estimate relative efficiency by a method which does not encounter these problems-survivor analysis. The a priori case for economies of scale in medical practice is based upon technical indivisibilities. Larger practices can make use of the services of paramedical personnel to perform many of the simpler