Design-Based Approaches to Horizontal-Point-Sampling
Abstract:Horizontal-point-sampling is formalized under three different unequal probability finite population sample designs and an infinite population formulation. All four approaches result in unbiased estimators for the per-area total and the variance of the total. It is argued that, of the four approaches, the infinite population formulation corresponds more closely to the need for per-area estimation and to the physical process of randomization. It results in components of change estimators that are additive over time as well as compatible with net change, and it is easier to explain. Regardless of the view accepted, it is demonstrated that horizontal-point-sampling can be formally described in a variety of ways. Examples provide insight into horizontal-point-sampling and into design-based sampling and the generality of the Horvitz-Thompson estimator. For. Sci. 41(4):890-907.
Document Type: Journal Article
Affiliations: Associate Professor, Department of Forest Science, Texas A&M University, College Station, TX 77843-2135
Publication date: November 1, 1995
More about this publication?
- Membership Information
- ingentaconnect is not responsible for the content or availability of external websites