دانلود رایگان مقاله عملکرد خدمات بیمارستان در انتاریو: DEA با رویکرد رگرسیون مختصر

abstract

In this work, we analyze production performance of hospital services in Ontario (Canada), by investigating its key determinants. Using data for the years 2003 and 2006, we follow the two-stage approach of Simar and Wilson (2007). Specifically, we use Data Envelopment Analysis (DEA) at the first stage to estimate efficiency scores and then use truncated regression estimation with doublebootstrap to test the significance of explanatory variables. We also examine distributions of efficiency across geographic locations, size and teaching status. We find that several organizational factors such as occupancy rate, rate of unit-producing personnel, outpatient-inpatient ratio, case-mix index, geographic locations, size and teaching status are significant determinants of efficiency.

6. Concluding remarks

In this work, we examined production performance of hospital services in Ontario across geographic locations, size and teaching status and other key variables using a non-parametric DEA technique with bootstrapping and truncated regression. As a method, DEA estimates the best-practice frontier through a direct comparison with units that are peers in resource usages and then calculates the distance to this frontier, e.g., via Farrell-type output oriented efficiency measure, as we have done here. We also utilized non-parametric kernel density estimation to visualize distributions of efficiency for different geographic locations, size and teaching status of hospitals.