Affiliations: [a] Department of Statistics and Applied Maths “Diego de Castro”, University of Turin, Turin, Italy | [b] Department of Public Health and Microbiology, University of Turin, Turin, Italy | [c] Cardiovascular Department, Azienda Ospedaliero-Universitaria “Ospedali Riuniti”, Trieste, Italy | [d] Institute of Health Economics and Management, University of Lausanne, Lausanne, Switzerland | [e] Unit of Cancer Epidemiology, University of Turin, CERMS and CPO-Piemonte, Turin, Italy | [f] Institute of Social and Preventive Medicine, University of Lausanne, Lausanne, Switzerland
Correspondence:
[*]
Corresponding author: Prof. Dario Gregori, Department of Public Health and Microbiology, Via Santena 5bis, 10126 Torino, Italy. Tel.: +39 0116705813; Fax: +39 0112365813; E-mail: dario.gregori@unito.it.
Abstract: The population-mean cost of patients with certain pathologies is the parameter of interest for allocating health resources. It generally depends upon a number of covariates and the presence of outliers yields difficulties in the estimation procedure. Recent research in parametric robust techniques proposed the use of robust estimating equations via M-estimation for the Gamma model [2] and a class of high efficiency and high breakdown point estimators [14] extended to the case of generalized log-gamma regression [12]. In the present work, we compared results obtained by the two parametric robust procedures with the standard GLM (Generalized Linear Model) Gamma with log link, both in a simulation study and in a cardiovascular trial. The robust procedures outperformed the GLM Gamma in the contaminated simulation scenario and in the real dataset the significance of some covariates changed between the three estimators, with a better ability of the Log Gamma Robust in isolating the outliers driving these changes.
