Grant: Travel Awards - Institute Community Support

Public spending on health care in Canada has been steadily increasing over the years, and this trend is expected to continue in the future. Decision makers, however, operate under tight constraints when making funding decisions. This brings about questions about the efficiency of health care sectors across Canada. More specifically, what is the most appropriate use of inputs (doctors, nurses, personal support workers, etc.) to achieve desired outcomes (both quality and volume of care) within and across care settings (hospital, long-term care, home care, etc.)? Moreover, what are the drivers of technical efficiency, and how can they be used as policy levers to increase health care efficiency? These questions can be investigated using existing regression-based approaches, the results of which are used to inform funding decisions in Canada. These methods, however, can give different results depending on their inherent assumptions in estimation, thereby resulting in conflicting policy recommendations by the analyst. This paper assesses the performance of various statistical estimators in the context of longitudinal (panel) data, and proposes a new estimator, quantile regression, which is shown to overcome the assumptions/limitations of existing methods. Quantile regression, therefore, may become another tool in efficiency measurement analysis to obtain the best estimates of technical efficiency across health care sectors in Canada, as well as the drivers of technical efficiency itself.