Determinantes espaciais e econômicos da demanda residencial por água em Fortaleza, Ceará

• Ano de defesa: 2012
• Autor(a) principal: André, Diego de Maria
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Palavras-chave em Português: Econometria Espacial
• Link de acesso: http://www.repositorio.ufc.br/handle/riufc/5411

This paper aims to estimate a residential water demand function for the city of Fortaleza (Cear´a), considering the potential impact of the spatial effects on water consumption. The analysis is developed from the investigation of presence of spatial autocorrelation in residential water consumption. For this, the tools of exploratory spatial data analysis (ESDA) were utilized. Subsequently, specific tests are performed to determine the sources of spatial autocorrelation, i.e., if the autocorrelation is caused by the spatial distribution of water consumption or by effects not modeled. Identified the sources of spatial autocorrelation, four water demand functions were estimated, which had as explanatory variables the average price, the difference, income, number of residents and the number of rooms, under different specifications. At first, we estimated a model without special effects; in the second, we estimated the specification of the spatial error model (SEM), which incorporates the spatial autocorrelation in the form of autocorrelation in the error terms; in the third, we estimated the spatial autoregressive model (SAR), where the spatial autocorrelation is incorporated through the spatial lag of the dependent variable and finally, we estima ted the spatial model autoregressive moving average (SARMA), which is the union of the two previous models. The results show that spatial autocorrelation exists in two forms (error and lag), indicating that the SARMA model is the most indicated to model the residential water demand in the city of Fortaleza, in contrast to suggested by Chang et al. (2010), House-Peters et al. (2010), Franczyk e Chang (2008), Ramachandran e Johnston (2011), which used the SEM model. It is concluded that it is important to consider the possibility of spatial effects in the estimation of a residential water demand function, once that not incorporate spatial effects in the analysis underestimate the effect of the variables average price and number of residents on residential water demand, while overestimating the effect of the variables income and number of rooms.