Affiliation:
1. University of Naples Federico II
Abstract
Geoadditive models represent efficient and flexible tools, useful in modeling realistically complex situations. Mainly they are based on semi-parametric regressions often integrated by Kriging techniques for the spatial interpolation of surfaces. One of the choices to be made for determination of interpolated surfaces regards the specific function to be used to estimate the unknown values. The choice may currently occur between exponential, gaussian, linear, rational or spherical functions. In this working paper a geoadditive model based on penalized spline functions has been proposed, in order to obtain improvements in forecasting of interpolated surfaces respect to usual Kriging techniques. The main aim of this study is the identification of methodology in able to define and delineate the real estate market scenarios for urban areas through analysis of property values and their spatial distribution.
Publisher
Trans Tech Publications, Ltd.
Reference9 articles.
1. Kammann E.E. e Wand M.P., Geoadditive models, Applied Statistics, 52, (2003).
2. Hastie T.J., Pseudosplines, Journal of the Royal Statistic Society, Series B 58, (1996).
3. Ngo L., Wand M.P., Smoothing with Mixed Model Software, Journal of Statistical Software, 9, (2004).
4. Wand M.P., French J.L., Ganguli B. Kammann E.E., Stuadenmayer J., Zanobetti A., SemiPar 1. 0 R package, http: / cran. r-project. org, (2005).
5. Wand M.P., Smoothing and mixed models, Computational Statistics, 18, (2003).
Cited by
19 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献