The two-stage method for measurement error characterization

Abstract

A measurement error (ME) is a component of any study involving the use of actual measurements, but is often not recognized or is ignored. The consequences of ME on models can be severe, affecting estimates of tree and stand attributes and model parameters. Although correction methods do exist for countering the effects of ME, the use of these methods requires knowledge of the distribution of the errors. A new method for modeling error distributions, called the two-stage error distribution (TSED) method, is presented here. This method is compared with traditional methods for error modeling through an example using diameter and height ME. Comparisons between the fitted error distribution surfaces and the empirical error surface are based on a dissimilarity measure. The results indicate that the TSED method produces a much more accurate and precise characterization of the ME distribution than do traditional methods when a high percentage of errors is identical. In other cases, the TSED method works as well as the most accurate form of the traditional method. The TSED method is also expected to perform better at characterizing asymmetric distributions. It is therefore more adaptable than traditional methods and is being proposed for error modeling in the future.