Determining the factors affecting the technical efficiency scores of public hospitals using different regression methods

Abstract

PurposeThis study aims to identify the efficiency scores of hospitals affiliated to the Ministry of Health in Turkey between the years of 2010–2015 at provincial level and to reveal the factors that affect the efficiency scores.Design/methodology/approachThe two-stage data envelopment analysis (DEA) method was used to achieve the study purpose. In the first stage, DEA method based on input-oriented Charnes–Cooper–Rhodes (CCR) model was performed to calculate the efficiency scores of public hospitals at the provincial level between 2010 and 2015, and in the second stage, Tobit regression and linear regression analyses were used to identify whether the efficiency scores of provinces are affected by the input, output and control variables.FindingsUpon the analysis, the average efficiency scores of 81 provinces by years were found to vary between 0.79 and 0.89. According to both regression analyses, all of the input and output variables were found to have significant effects on the efficiency scores of provinces while only the population of province among the control variables was identified as the factor with an effect on the efficiency scores of provinces (p < 0.05).Practical implicationsThe results of this study are thought to guide health policymakers and managers in terms of both determining efficient and inefficient hospitals at the provincial level and revealing which variables should be taken into account in order to increase efficiency.Originality/valueThe study differs from previous studies on the efficiency of hospitals. First, although previous studies were generally descriptive studies to determine the efficiency level of hospitals, this study is an analytical study that tries also to show the factors affecting the efficiency of hospitals. In addition, while examining the effect of input and output variables on efficiency scores, control variables were also included in the study.

Does managerial ability and auditor report readability affect corporate liquidity and cost of debt?

“…Tobit regression analysis was employed to recognize MA estimates. Prior studies confirm the capability of Tobit regression analysis as a practical mean for exploring the association between variables when the dependent variable is censored or has a range constraint (Şahin et al. , 2021; Shahwan and Habib, 2020, 2021; Mourad et al.…”

Evaluating the decentralization of public hospitals in Turkey in terms of technical efficiency: data envelopment analysis and Malmquist index

“…The percentages of efficient hospitals in Groups B, C, D and E were proportionately lower than those of large-scale hospitals. DEA-based input-oriented models are designed to provide input minimization, inputs (number of hospitals, number of beds, number of nurses + midwives and other health personnel) have a negative effect on the efficiency score of DMUs (Şahin et al ., 2021). As the scale of hospitals decreases according to their roles, in small-scale hospitals, the number of physicians, nurses + midwives and other health personnel increase the efficiency scores of hospitals decrease.…”

“…Input and output variables of this study have been commonly employed in similar studies (Şahin et al ., 2021; İlgün and Konca, 2019; Habib and Shahwan, 2020; Bağci and Konca, 2021). Therefore, the variables of the current study are compatible with the literature.…”

Efficiency Measurement Using Data Envelopment Analysis (DEA) in Public Healthcare: Research Trends from 2017 to 2022

“…Therefore, Tobit regression, or truncated regression, was mostly performed. Besides these, Ordinary Least Squares (OLS) regression [20,29,43], Generalized Linear Mixed Model (GLMM) regression [44], Logistic regression [30], Spatial Durbin Model [45], and multilevel zero-one inflated beta regression [37] were also used to verify the causal relationship between efficiency and independent factors.…”