A Spatio-Temporal Analysis of OECD Member Countries’ Health Care Systems : Effects of Imputation and Geographically and Temporally Weighted Regression on Inference

Assessing determinants of health care quality and efficiency is of importance to researchers, policy-makers, and public health officials. Doing so allows for improved human capital and resource allocation as well as long-term fiscal planning. Statistical analysis has been used to understand determinants, however, most research neglects to explicitly discuss how missing data is handled and previous statistical analysis has been limited in inferential capability. The importance of transparency behind the assumptions grounding the treatment of data missingness and imputation in studies analyzing OECD health care data is highlighted. Attention is drawn to the variation in ordinary least squares coefficient estimates and performance resulting from different data imputation methods, and how this variation can undermine statistical inference and weaken resulting policy recommendations. We also suggest that parametric regression models used previously are limited and potentially ill-suited for analysis of OECD data due to the inability to deal with both spatial and temporal autocorrelation. We propose the use of an alternative method in geographically and temporally weighted regression. A spatio-temporal analysis of health care system efficiency along with the quality of care and health outcomes across 20 OECD member countries is performed. Using a forward variable selection procedure, we identify medical imaging units (CT scanners or MRI units) in a country as a key contributing factor to health care system performance across three proxy variables for quality of care and health outcomes. Government and compulsory health insurance expenditure per capita is also identified as a key contributing factor to health care system performance in terms of efficiency through one proxy variable