Publication Details

Post-Modeling Histogram Matching of Maps Produced Using Regression Trees

Publication Toolbox

  • Download PDF (593470)
  • This publication is available only online.

Year Published

2006

Publication

In: Proceedings of the sixth annual forest inventory and analysis symposium; 2004 September 21-24; Denver, CO. Gen. Tech. Rep. WO-70. Washington, DC: U.S. Department of Agriculture Forest Service. 126p.

Abstract

Spatial predictive models often use statistical techniques that in some way rely on averaging of values. Estimates from linear modeling are known to be susceptible to truncation of variance when the independent (predictor) variables are measured with error. A straightforward post-processing technique (histogram matching) for attempting to mitigate this effect is presented, and a comparison with untransformed model estimates is made. Histogram matching enhanced the contrast visible in the final map and produced estimates that mimicked the range of estimates in the original data set but performed worse overall with respect to absolute error of prediction. Examples of cases where histogram matching might be an effective post-processing method are given.

Note: This article is part of a larger document. View the larger document

Citation

Lister, Andrew J.; Lister, Tonya W. 2006. Post-Modeling Histogram Matching of Maps Produced Using Regression Trees. In: Proceedings of the sixth annual forest inventory and analysis symposium; 2004 September 21-24; Denver, CO. Gen. Tech. Rep. WO-70. Washington, DC: U.S. Department of Agriculture Forest Service. 126p.

Last updated on: August 11, 2006