Open Collections

Development and examination of sequential approaches for applicability testing of tree volume models

University of British Columbia

In forest inventories, an existing standard volume equation may be considered for appli- cation to a local area (subpopulation), or to the same species in a different geographic region (new population). In order to use a volume model with confidence under these situations, an applicability test must be carried out to determine the actual accuracy of the model. Procedures based on a predetermined, sufficiently large sample of data (fixed sample size procedures) are available. However, since applicability testing is only used to classify a model as either acceptable or unacceptable, it is likely that a testing decision can be made with a smaller sample size, especially when the actual accuracy of the model is far below or above the user’s requirement. This is particularly of concern when data collection for model checking is very expensive, time-consuming or destructive. As an alternative, three sequential accuracy testing plans (SATP) were developed by extending Freese’s (1960) accuracy tests using Wald’s (1947) sequential probability ratio tests (SPRT) in this thesis. Observations are taking sequentially, and at each stage of sampling, a decision of whether to accept or reject the model, or to continue sampling, is made. The SATP procedures are potentially superior to a fixed sample size procedure in terms of lower sample sizes. Approximate Operating Characteristic (OC) and Average Sample Number (ASN) equations were also suggested to assist the potential users of the SATP procedures in choosing appropriate tested parameters for a given problem. The simulation results using normal distribution generators showed that the SATP procedures are reliable for classifying a volume model as either acceptable or unacceptable based on two pre-set limits of the accuracy requirement. Also, on average, the use of the SATP procedures will result in a 40 to 60% of sampling cost-saving compared to an equally reliable conventional fixed sample size procedure. A detailed example is given to illustrate the application of the SATP procedures.

Thesis/Dissertation

application/pdf

2009-06-05

For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.

http://hdl.handle.net/2429/8820

Forestry

University of British Columbia

UBCV

DSpace