Stochastic frontier estimation of cost models within the hospital

Assessing the impact of new technologies on health care costs is au importa nt research area. This paper evaluates two technologies used to treat coron ary artery disease. We estimate two separate stochastic frontier model-one for balloon angioplasty patients and one for cardiac bypass surgery patient -using data taken from detailed chart and cost files of a large urban hospi tal. Cost estimates for the two technologies are purged of inefficiency so that forecasts of the cost consequences of technology shift can be based on "best-practice" production techniques. Learning behavior, physician effect s, and patient clinical characteristics are also taken into account. We fin d that there are potential cost savings associated with making angioplasty a more perfect substitute for bypass surgery, as well as current inefficien cy in production.