Effects of new drugs on overall health spending: Frank Lichtenberg responds.

When the model I estimated in 2002 is modified in all of the ways advocated by Yuting Zhang and Stephen Soumerai, it still implies that in general, using newer drugs reduces nondrug costs more than it increases drug costs. Moreover, some of Zhang and Soumerai's modifications might be inappropriate, and they did not make a necessary adjustment that implies that the true cost offset is considerably larger than their estimate. Their description of my methodology is quite inaccurate, and they ignored some previous evidence of large cost offsets based on an entirely different methodology (analysis of longitudinal group-level data) not subject to their critique.