Precision and the Probability of Misclassification in Site Index Estimation
Abstract:This work presents an estimate of variance for a site index predictor. The methodology was tested on height/age data for loblolly pine from the Coastal Plain of the southeastern United States. We quantified the effects of stand age, base age, and sample size on the variance of site index. The derived variance was used in the development of a measure of the probability of misclassification. We used this measure to show the effects of site index class interval width, stand age, base age, and sample size on classification performance of this site index predictor. The results show that changing the width of class intervals or the value of stand age has the greatest effect on the classification performance. The methods have practical value as guides to selecting sample sizes that produce uniformly reliable site index predictions. FOREST SCI. 23:493-499.
Document Type: Journal Article
Affiliations: Professor of Forestry and Statistics, North Carolina State University, Raleigh, North Carolina 27607
Publication date: December 1, 1977
More about this publication?
- Membership Information
- ingentaconnect is not responsible for the content or availability of external websites