In this paper, we describe three methods of the cost-function analysis in a health care: classical econometric analysis, frontier analysis, and survivor analysis. The strength of a classical econometric analysis is a highly developed methodology of hypothesis testing; the weakness is that it is necessary to deal with many problems related to estimation technique, such as multicollinearity, autocorrelation, heteroscedasticity, etc. The strength of the stochastic frontier analysis is that it incorporates the random shocks in efficiency evaluation; on the other hand, the strong assumptions about the distribution of efficiency have to be made. The advantages of survivor analysis are its simplicity and the possibility to include the factors that are otherwise hard to measure; the disadvantages are the application only in the long-term studies, and the provision of no specific information on the character of cost function in the studied industry. The different methods have strengths and weaknesses and the choice of the appropriate method depends on the objective of the study.