Title: Regression and Geostatistical Techniques: Considerations and Observations from Experiences in NE-FIA

Author: Riemann, Rachel; Lister, Andrew

Year: 2005

Publication: In: McRoberts, Ronald E.; Reams, Gregory A.; Van Deusen, Paul C.; McWilliams, William H.; Cieszewski, Chris J., eds. Proceedings of the fourth annual forest inventory and analysis symposium; Gen. Tech. Rep. NC-252. St. Paul, MN: U.S. Department of Agriculture, Forest Service, North Central Research Station. 231-239

Abstract: Maps of forest variables improve our understanding of the forest resource by allowing us to view and analyze it spatially. The USDA Forest Service's Northeastern Forest Inventory and Analysis unit (NE-FIA) has used geostatistical techniques, particularly stochastic simulation, to produce maps and spatial data sets of FIA variables. That work underscores the importance of generating uncertainty information along with the modeled estimates, the value of incorporating additional satellite and other data into the modeling, and the need to understand the characteristics of the output data set. In our study, we investigated three questions: Does spatial structure matter when satellite-derived and ancillary spatial data sets are incorporated into the modeling of forest attributes? If we use a modeling technique such as multiple linear regression, how do we calculate or estimate the uncertainty? And what are the characteristics of the output data set with respect to the original sample data and the ancillary data used?