Abstract
In this paper we develop a system-of-equations two-stage approach to explain the simultaneous effect of a number of contextual variables on technical efficiency and capacity utilization, which were derived using Johansen measure of capacity utilization and DEA. The model is applied to a sample of public hospitals in Greece and provides estimates of capacity utilization and optimal input usage. Our results indicate that the sample hospitals operated with excess capacity and by underutilizing doctors and nursing personnel. We also found some variation in capacity and variable input utilization across urban and non-urban hospitals. The results from the second stage SUR system of equations show that hospital size and location have a positive effect on hospital capacity utilization while the average length of stay a negative one.
Similar content being viewed by others
Notes
Other approaches are the frontier separation approach and the all-in-one approach. For details see Thanassoulis et al. (2008, pp. 340–353).
Prior to the technical inefficiency effect model (see Kumbhakar and Lovell 2000, Chap. 7 and the references therein), where estimation of technical efficiency and its determinants can be carried out simultaneously in one-stage, the two-stage approach was also used in stochastic frontier analysis. It has been criticized however as being an inconsistent and mis-specified formulation (see Wang and Schmidt 2002 for a detail discussion). On the other hand, notice that it is not possible to integrate the two-stage DEA into a one-stage model because it involves deterministic (first stage) and stochastic (second stage) components. We will like to thank an anonymous referee for making this point.
Notice than none of previous studies analyzing capacity utilization in hospitals (e.g., Fare et al. 1989a; Magnussen and Mobley 1999; Valdmanis et al. 2004 and Ferrier et al. 2009) have used the second-stage DEA to explain factors that affect it. All the empirical studies in the subject are from the field of fisheries.
We could have used a log-log specification but since some of the contextual variables are dummy variables the log-linear specification is more plausible.
This reasoning holds for capacity utilization rates, which also represent fractional data within the unit interval.
Simar and Wilson (2002) introduced an alternative test to examine the existence of returns to scale.
The non-parametric rank-sum test statistic that follows approximately the standard normal distribution is defined as (Cooper et al. 2000): \(T=\frac{S-I_{1}(I_{1}+I_{2}+1)/2}{\sqrt{I_{1}I_{2}(I_{1}+I_{2}+1)/12}}\), where S being the sum of rankings corresponding to DEA estimates.
Notice that the White (1980) test detected the presence of heteroscedasticity for all equations.
References
Badin, L., Daraio, C., & Simar, L. (2012). Explaining inefficiency in nonparametric production models: the state of art. Annals of Operations Research. doi:10.1007/S10479-012-1173-7.
Banker, R. D. (1993). Maximum likelihood, consistency and data envelopment analysis: a statistical foundation. Management Science, 39(10), 1265–1273.
Banker, R. D., & Natarajan, R. (2004). Statistical tests based on DEA efficiency scores. In Cooper, Seiford, & Zhu (Eds.), Handbook on data envelopment analysis (Chap. 11, pp. 299–321).
Banker, R. D., & Natarajan, R. (2008). Evaluating contextual variables affecting productivity using Data Envelopment Analysis. Operations Research, 56(1), 48–58.
Banker, R. D., Cao, Z., Menon, N., & Natarajan, R. (2010a). Technological progress and productivity growth in the US mobile telecommunications industry. Annals of Operations Research, 173, 77–87.
Banker, R. D., Lee, S. Y., Potter, G., & Srinivasan, D. (2010b). The impact of supervisory monitoring on high-end retail sales productivity. Annals of Operations Research, 173, 25–37.
Cooper, W. W., Seiford, L. M., & Tone, K. (2000). Data envelopment analysis. Dordrecht: Kluwer Academic.
Duncan, G. M. (1983). Estimation and inference for heteroscedastic systems of equations. International Economic Review, 24, 559–566.
Fare, R., Grosskopf, S., & Valdmanis, V. (1989a). Capacity, competition and efficiency in hospitals: a nonparametric approach. Journal of Productivity Analysis, 1, 123–138.
Fare, R., Grosskopf, S., & Kokkelenberg, E. (1989b). Measuring plant capacity, utilization and technical change: a nonparametric approach. International Economic Review, 30(3), 655–666.
Farell, M. J. (1957). The measurement of productive efficiency. Journal of the Royal Statistical Society. Series A. General, 120(3), 253–281.
Ferrier, G., Leleu, H., & Valdmanis, V. (2009). Hospital capacity in large urban areas: is there enough in times of need? Journal of Productivity Analysis, 32, 103–117.
Greek Ministry of Healt and Social Solidarity (1995). Health yearbook 1993. Athens.
Hoff, A. (2007). Second stage DEA: comparison of approaches for modelling the DEA score. European Journal of Operational Research, 181, 425–435.
Johansen, L. (1968). Production functions and the concept of capacity. Economic Mathematique et Econometrie, 2.
Kmenta, J. (1986). Elements of econometrics. New York: Macmillan Co.
Kumbhakar, S. C., & Lovell, C. A. K. (2000). Stochastic frontier analysis. Cambridge: Cambridge University Press.
Lindebo, E., Hoff, A., & Vestergaard, N. (2007). Review-based capacity utilization measures and decomposition: the case of Danish North Sea trawlers. European Journal of Operational Research, 180, 215–227.
Lovo, S. (2011). Pension transfers and farm household technical efficiency: evidence from South Africa. American Journal of Agricultural Economics, 93, 1391–1405.
Magnussen, J., & Mobley, L. R. (1999). The impact of market environment on excess capacity and the cost of an empty hospital bed. International Journal of the Economics of Business, 6(3), 383–398.
McDonald, J. (2009). Using least squares and tobit in second stage DEA efficiency analysis. European Journal of Operational Research, 197, 792–798.
National Statistical Service of Greece (1998). Population and housing census 1991: Vol. II. Piraeus.
National Statistical Service of Greece (2007). Population and housing census 2001: Vol. II. Piraeus.
Ray, S. (1991). Resource-use efficiency in public schools: a study of Connecticut data. Management Science, 37(12), 1620–1628.
Revankar, N. S. (1974). Some finite sample results in the context of two seemingly unrelated regression equations. Journal of the American Statistical Association, 69, 187–190.
Simar, L., & Wilson, P. W. (2002). Non-parametric tests of returns to scale. European Journal of Operational Research, 139, 115–132.
Simar, L., & Wilson, P. W. (2007). Estimation and inference in two-stage, semi-parametric models of production processes. Journal of Econometrics, 136, 31–64.
Simar, L., & Wilson, P. W. (2011). Two-stage DEA: caveat emptor. Journal of Productivity Analysis, 37(1), 205–218.
Thanassoulis, E., Portela, M. C. S., & Despic, O. (2008). Data Envelopment Analysis: the mathematical programming approach to efficiency analysis. In Fried, Lovell, & Schmidt (Eds.), The measurement of productive efficiency and productivity growth (Chap. 3, pp. 251–420). London: Oxford University Press.
Tingley, D., & Pascoe, S. (2005). Factors affecting capacity utilization in English Channel fisheries. Journal of Agricultural Economics, 56(2), 287–305.
Valdmanis, V., Kumanarayake, L., & Lertiendumrong, J. (2004). Capacity in Thai public hospitals and the production of care for poor and nonpoor patients. Health Services Research, 39(6), 2117–2134.
Van Hoff, L., & de Wilde, J. W. (2005). Capacity assessment of the Dutch beam-trawler fleet using data envelopment analysis (DEA). Marine Resource Economics, 20, 327–345.
Vassiliev, A., Luzzi, G. F., Fluckiger, Y., & Ramirez, J. V. (2006). Unemployment and employment offices’ efficiency: what can be done? Socio-Economic Planning Sciences, 49, 169–186.
Vestergaard, N., Squires, D., & Kirkley, J. (2003). Measuring capacity and capacity utilization in fisheries: the case of the Danish gill-net fleet. Fisheries Research, 60, 357–368.
Wang, H. J., & Schmidt, P. (2002). One-step and two-step estimation of the effects of exogenous variables on technical efficiency levels. Journal of Productivity Analysis, 18, 129–144.
White, H. (1980). A heteroscedastic-consistent covariance matrix estimator and a direct test for heteroscedasticity. Econometrica, 48, 817–838.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Karagiannis, R. A system-of-equations two-stage DEA approach for explaining capacity utilization and technical efficiency. Ann Oper Res 227, 25–43 (2015). https://doi.org/10.1007/s10479-013-1367-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10479-013-1367-7