A Statistical Procedure for Combining Different Types of Sampling Units in a Forest Inventory

Author: Wensel Lee C.   John Hugo H.  

Publisher: Society of American Foresters

ISSN: 0015-749X

Source: Forest Science, Vol.15, Iss.3, 1969-09, pp. : 307-317

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

A procedure to permit the simultaneous use of more than one primary sampling unit (psu) to give greater flexibility in a forest inventory is presented. Of primary interest is the case where n1 independent samples of size a1 are selected with probability proportional to frequency (ppf) and n2 independent samples of size a2 are selected with probability proportional to size (pps), where a1 is the plot area in acres and a2 is the average plot area in acres. The resulting estimator Z of the population mean is derived as a function of the sample means for each sampling unit and appropriately chosen weights. The variance of this estimator is examined for various choices of weighting functions.