A form of two-phase sampling utilizing regression analysis

A two-phase sampling technique was introduced and tested where sawlog heights were measured on intensive (second phase) points and predicted on non-intensive (first phase) points. Regression analysis is used to predict heights on first phase points in order to achieve an estimate of volume for every point. Results indicate an improved estimate of both mean volume per acre and volume per acre by species when compared to traditional double sampling. An unbiased sampling error was also achieved in this process. Datasets consisted of mostly hardwood species from West Virginia and Maryland.