On estimating the distribution of data envelopment analysis efficiency scores: an application to nursing homes’ care planning process

ICT as a Key Determinant of Efficiency: A Bootstrap-Censored Quantile Regression (BCQR) Analysis for Vietnamese Banks

There is evidence that ICT developments can improve bank efficiency and performance. Previous studies often employ data envelopment analysis (DEA) to first examine bank performance and then use a second-stage regression to explain the influences of other environmental factors, including ICT, on such efficiency. Since DEA efficiency scores are bounded between the (0, 1] intervals, Tobit and truncated regressions are commonly used in this stage. However, none has accounted for the skewness characteristic of DEA efficiency. This paper applied a bootstrap-censored quantile regression (BCQR) approach to triply account for the issues of a small sample (via bootstrap), bounded intervals (via censored regression), and skewness (via quantile regression) in DEA analysis. We empirically examined the efficiency and performance of 27 Vietnamese commercial banks in the 2007–2019 period. The efficiency scores derived from our first stage revealed that they are skewed and thus, justify the use of the BCQR in the second stage. The BCQR results further confirmed that ICT developments could enhance bank efficiency, which supports the recent policy to restructure the Vietnamese banking sector toward innovation and digitalization. We also examined the impacts of other factors such as bank ownership, credit risk, and bank size on efficiency.

Data Envelopment Analysis in the Presence of Measurement Error: Case Study from the National Database of Nursing Quality Indicators® (NDNQI®)

Data Envelopment Analysis (DEA) is the most commonly used approach for evaluating healthcare efficiency (Hollingsworth, 2008), but a long-standing concern is that DEA assumes that data are measured without error. This is quite unlikely, and DEA and other efficiency analysis techniques may yield biased efficiency estimates if it is not realized (Gajewski, Lee, Bott, Piamjariyakul and Taunton, 2009; Ruggiero, 2004). We propose to address measurement error systematically using a Bayesian method (Bayesian DEA). We will apply Bayesian DEA to data from the National Database of Nursing Quality Indicators® (NDNQI®) to estimate nursing units' efficiency. Several external reliability studies inform the posterior distribution of the measurement error on the DEA variables. We will discuss the case of generalizing the approach to situations where an external reliability study is not feasible.