Felkner, John
Future possible directions for this research include the following:
A. using a method of logistic regression rather than tree classification for a predictive model — comparison with tree
approach can be evaluated by the resulting accuracy of the predicted maps;
B. sensitivity testing of the parameters used to create the socioeconomic models and then considering the different
predictions resulting from those models for accuracy; :
C. evaluating predictions resulting from inputting different combinations of input models into the prediction
regression model, to see which combinations result in the most accuracy;
D. extension of the modeling to other Thai Provinces (data has been collected for Lop Buri and Buriram Provinces) -
this could allow analysis of relative influences of input models for different regions of a developing tropical
country, perhaps showing that the same factors predict most accurately in each Province, or that different
explanatory factors are different depending on regions with differing conditions;
E. exploration of various methods of spatial representation of the economic inputs under consideration using GIS and
splus statistical software (e.g. kriging methods of spatial representation of inputs);
F. extension of the model to other tropical developing countries.
REFERENCES
Bonham-Carter, G. F. (1994). Geographic Information Systems for Geoscientists: Modeling with GIS. New York,
Pergamon/Elsevier Science Inc.
Jensen, J. R. (1996). Introductory Digital Image Processing. Upper Saddle River, NJ, Prentice-Hall, Inc.
Kaimowitz, D. and A. Angelsen (1998). Economic Models of Tropical Deforestation - A Review. Jakarta, Center for
International Forestry Research.
Laslett, G. M., A. B. McBratney, et al. (1987). “Comparison of Several Spatial Prediction Methods for Soil pH.”
Journal of Soil Science(38): 325-241.
Myer, D. E. (1991). “Interpolation and Estimation with Spatially Located Data.” Chemometrics and Intelligent
Laboratory Systems(11): 209-228.
O'Connor, R., M. T. Jones, et al. (1996). “Spatial Partitioning of Environmental Correlates of Avian Biodiversity in the
Conterminous United States.” Biodiversity Letters(3): 97-110.
Venables, W. N. and B. D. Ripley (1994). Modern Applied Statistics with S-PLUS. New York, Springer-Verlag.
438 International Archives of Photogrammetry and Remote Sensing. Vol. XXXIII, Part B7. Amsterdam 2000.
