Bayesian Variable Selection in Spatial Regression Models

An important task in building regression models is to decide which regressors should be included in the final model. In a Bayesian approach, variable selection can be performed using mixture priors with a spike and a slab component for the effects subject to selection. As the spike is concentrated at zero, variable selection is based on the probability of assigning the corresponding regression effect to the slab component. These posterior inclusion probabilities can be determined by MCMC sampling. In this paper we compare the MCMC implementations for several spike and slab priors with regard to posterior inclusion probabilities and their sampling efficiency for simulated data. Further, we investigate posterior inclusion probabilities analytically for different slabs in two simple settings. Application of variable selection with spike and slab priors is illustrated on a data set of psychiatric patients where the goal is to identify covariates affecting metabolism.

Download Full-text

Irrigation Water Valuation Using Spatial Hedonic Models in GIS Environment

Societal Impacts on Information Systems Development and Applications ◽

10.4018/978-1-4666-0927-3.ch020 ◽

2012 ◽

pp. 308-320

Author(s):

Zisis Mallios

Keyword(s):

Irrigation Water ◽

Regression Models ◽

Spatial Regression ◽

Hedonic Pricing ◽

Spatial Lag Model ◽

Hedonic Pricing Method ◽

Spatial Weights Matrix ◽

Spatial Regression Models ◽

Gis Environment ◽

Value Of Irrigation Water

Hedonic pricing is an indirect valuation method that applies to heterogeneous goods investigating the relationship between the prices of tradable goods and their attributes. It can be used to measure the value of irrigation water through the estimation of the model that describes the relation between the market value of the land parcels and its characteristics. Because many of the land parcels included in a hedonic pricing model are spatial in nature, the conventional regression analysis fails to incorporate all the available information. Spatial regression models can achieve more efficient estimates because they are designed to deal with the spatial dependence of the data. In this paper, the authors present the results of an application of the hedonic pricing method on irrigation water valuation obtained using a software tool that is developed for the ArcGIS environment. This tool incorporates, in the GIS application, the estimation of two different spatial regression models, the spatial lag model and the spatial error model. It also has the option for different specifications of the spatial weights matrix, giving the researcher the opportunity to examine how it affects the overall performance of the model.

Download Full-text

Irrigation Water Valuation Using Spatial Hedonic Models in GIS Environment

International Journal of Information Systems and Social Change ◽

10.4018/jissc.2010100101 ◽

2010 ◽

Vol 1 (4) ◽

pp. 1-13 ◽

Cited By ~ 2

Author(s):

Zisis Mallios

Keyword(s):

Irrigation Water ◽

Regression Models ◽

Spatial Regression ◽

Software Tool ◽

Hedonic Pricing ◽

Spatial Error ◽

Spatial Lag Model ◽

Spatial Weights Matrix ◽

Lag Model ◽

Spatial Regression Models

Hedonic pricing is an indirect valuation method that applies to heterogeneous goods investigating the relationship between the prices of tradable goods and their attributes. It can be used to measure the value of irrigation water through the estimation of the model that describes the relation between the market value of the land parcels and its characteristics. Because many of the land parcels included in a hedonic pricing model are spatial in nature, the conventional regression analysis fails to incorporate all the available information. Spatial regression models can achieve more efficient estimates because they are designed to deal with the spatial dependence of the data. In this paper, the authors present the results of an application of the hedonic pricing method on irrigation water valuation obtained using a software tool that is developed for the ArcGIS environment. This tool incorporates, in the GIS application, the estimation of two different spatial regression models, the spatial lag model and the spatial error model. It also has the option for different specifications of the spatial weights matrix, giving the researcher the opportunity to examine how it affects the overall performance of the model.

Download Full-text