A Nonparametric Geostatistical Method For Estimating Species Importance

Abstract

Parametric statistical methods are not always appropriate for conducting spatial analyses of forest inventory data. Parametric geostatistical methods such as variography and kriging are essentially averaging procedures, and thus can be affected by extreme values. Furthermore, non normal distributions violate the assumptions of analyses in which test statistics are generated and compared to a theoretical distribution, such as analysis of variance or stepwise multiple linear regression. Here, we offer guidelines and an example of the use of the indicator approach for dealing with nonparametric data distributions, using data from a study conducted in northern Vermont and New Hampshire.

Citation

Lister, Andrew J.; Riemann, Rachel; Hoppus, Michael. 2001. A Nonparametric Geostatistical Method For Estimating Species Importance. In: Reams, Gregory A.; McRoberts, Ronald E.; Van Deusen, Paul C., eds. 2001. Proceedings of the second annual Forest Inventory and Analysis symposium; 2000 October 17-18; Salt Lake City, UT. Gen. Tech. Rep. SRS-47. Asheville, NC: U.S. Department of Agriculture, Forest Service, Southern Research Station. pp. 52-59