A Spatial Econometrics Analysis of The Calls to The Portuguese National Healthline

Orador: Paula Simões, aluna do  Programa Doutoral em Estatística e Gestão do Risco, Faculdade de Ciências e Tecnologia, Universidade Nova de Lisboa.

Data: 20 fevereiro 2017 (2ª feira)

Hora: 14h30

Local: Sala de Seminários - Edifício VII, FCT-UNL

 

Abstract: 

The Portuguese national healthline, LS24, is an initiative of the health ministry to meet citizens  needs in order to improve accessibility and to rationalize the  use of existing resources, by directing users to the most appropriate institutions of the public national health services.

Since for the LS24 data, the location attribute is an important source of information to describe its use, this study analyses the calls received, at the country administrative sub-division ``município'' level, under a spatial econometrics approach, aiming to describe and evaluate the use of LS24. This analysis will allow a future development of decision support indicators, in a hospital context, based on the  economic impact of the good use of LS24.

Considering the discrete nature of data, the number of calls to LS24 in each ``município'' is better modelled by a Poisson model, with some possible covariates: demographic, socio-economic information, characteristics of the health Portuguese system and development indicators. In order to explain model spatial variability, the residual autocorrelation can be explained, in a bayesian setting, through different hierarchical log-Poisson regression models. Alternatively, using an autoregressive methodology, but for count data, a log-Poisson model with a spatial lag autocorrelation component is further considered, better framed under a bayesian paradigm.

With this empirical study different approaches are used and developed to fit this data. We find strong evidencies of a spatial structure in data and obtain similar conclusions with both perspectives of the analysis. This supports that the addition of a spatial structure to the model improves estimation, even after including the relevant covariates.

 Keywords: Bayesian Analysis; Spatial Econometrics; Bayesian Spatial econometric models; Hierarchical models; Autoregressive models; Poisson.

 

 Financiado através do projeto UID/MAT/00297/2013.