Graduate Thesis Or Dissertation
 

A comparison of some estimators in forest sampling

Öffentlich Deposited

Herunterladbarer Inhalt

PDF Herunterladen
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/f7623f59q

Descriptions

Attribute NameValues
Creator
Abstract
  • The objectives of this study were to ascertain the relative precision and accuracy of certain estimators on several forest populations and to determine if relative performance could be predicted from knowledge of population characteristics. Performance was tested on three populations of trees drawn from stands in northern Ontario. The first population consisted of 479 spruce and fir trees drawn from an uneven aged second growth spruce-fir stand. The second consisted of 309 maple and birch trees from a mature hardwood stand. The third population was composed of 500 red pine drawn from a forty year old plantation. Measurement data obtained for each tree included breast height diameter and total height. For the spruce-fir and hardwood stands, measurements o height and crown area were also obtained from large scale aerial photography. Estimators for total volume, height and crown area were compared for the test populations. Independent or supplementary variables employed were diameter, height and crown area plus several transformations and combinations of these variables. Four sample sizes, n = 4, 12, 24, and 40 were employed for each of 25 dependent-independent variable combinations considered. Simple expansion, ratio, unbiased ratio, regression and unequal probability estimators and stratified sampling with the simple expansion estimator were compared using Monte Carlo techniques. Relative performance was evaluated using estimates of sampling variances, biases and mean square errors obtained from repeated sampling of the test populations. Results indicated linear and parabolic regression and the Horvitz- Thompson pps estimator were usually among the best three estimators for the two largest sample sizes studied. For the smaller sample sizes, linear egression, the Horvitz- Thompson pps and ratio of means estimators were best. For the estimation of volume using diameter- squared as the supplementary variable, linear regression was the best approach. Parabolic regression using diameter and diameter- squared was equal precise for the larger sample sizes. Major factors affecting the relative performance of estimators were: 1) the form of the dependent-independent variable relationship (linear or curvilinear), 2) the correlation between these variables, 3) the position of the intercept of the population regression line, 4) the variance of the dependent variable given the independent variable and 5) sample size.
Resource Type
Date Available
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Academic Affiliation
Non-Academic Affiliation
Subject
Urheberrechts-Erklärung
Publisher
Language
Digitization Specifications
  • Master files scanned at 600 ppi (256 Grayscale) using Capture Perfect 3.0 on a Canon DR-9080C in TIF format. PDF derivative scanned at 300 ppi (256 B+W), using Capture Perfect 3.0, on a Canon DR-9080C. CVista PdfCompressor 4.0 was used for pdf compression and textual OCR.
Replaces

Beziehungen

Parents:

This work has no parents.

In Collection:

Artikel

Miniaturansicht Titel Hochladedatum Sichtbarkeit Aktionen
file details Ek_Alan_R_1969.pdf 2017-08-01 Öffentlich Herunterladen