Estimating Technical Efficiency of Turkish Hospitals using SFAnalysis

Using a newly available dataset provided by the Turkey Ministry of Health, this paper is to investigate technical efficiency of more than 1200 hospitals conducting a stochastic frontier analysis. Public and private hospitals and university hospital’s inputs (doctors, other clinicals, medical devices, policlinic rooms, impatient beds, intensive care unit beds) and output score (derived from outputs like operation, medical device transactions…) will be used for that analys.


The trifecta of rising medical expenditures, low quality, and poor access are of great concern to healthcare administrators and policymakers worldwide. While it is very difficult to address the issues of one area without adversely affecting the others, improving efficiency might make it possible to provide more and better healthcare services with fewer resources.

In 2003, the Government of Turkey initiated a set of major healthcare reforms with an overall goal of increasing improved access to healthcare services and efficiency of healthcare providers. These reforms gave the Ministry of Health (MoH) and its Public Hospitals Institution (PHI) a significant power and centralized authority for determining the goals and principles for health policies, planning and allocating health resources for public and private hospitals, and determination and implementation of healthcare service standards.

Therefore, it becomes essential to develop a better understanding of the healthcare resource utilization and hospital efficiency in the country, which will, subsequently, enable the MoH to develop policies and programs targeted at improving and optimizing healthcare system and delivery in the country. The overall objective of this study is to analyze the technical efficiency of the Turkish hospitals using input and output data of 1,079 public and private hospitals in Turkey.


Cross-sectional data used in this study is obtained from the statistical reports of MoH Health Services General Directorate of Turkey for the year 2011. Our sample consists of 1,079 hospitals with different ownerships (398 private, 56 university, and 625 MoH) and types (98 teaching and 981 general). Dependent variable is a single output score derived as weighted average of several output variables (number of doctor visits, regular and ICU inpatient days, deliveries and number of surgeries which are adjusted based on their risk, time and labor intensity). Weights were average prices of services set by the Turkish Social Insurance Institute. Independent variables control for hospital infrastructure, technology, and human resources.

For this study, we adopt the Stochastic Frontier Analysis (SFA) to estimate hospital inefficiency in Turkish public and private hospitals. SFA measures efficiency in terms of the difference between optimal (best practice) performance and actual performance. Battese and Broca (1997) argue that researchers should test general model specifications against simpler models[a] to examine if the functional form has any impact on the inefficiency estimates. Therefore, our study uses multiple model specifications (e.g. standard Cobb-Douglas, translog, modified Cobb-Douglas) to estimate frontier function for the Turkish hospitals.


The results will provide valuable information to the policymakers and hospital administrators about the efficiencies associated with hospital operations, and hence, guide efforts directed at increasing the effectiveness of resource utilization and healthcare delivery through development of data-driven policies and strategies aimed at improving, regulating, and further optimizing Turkey’s healthcare system.

[a] Rosko MD, Mutter RL. Stochastic frontier analysis of hospital inefficiency: a review of empirical issues and an assessment of robustness. Med Care Res Rev. 2008;65(2): 131–66.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: