Skip to Main Content
Systematic sampling of discrete and continuous populations: sample selection and the choice of estimatorAuthor(s): Harry T. Valentine; David L. R. Affleck; Timothy G. Gregoire
Source: Canadian Journal of Forest Research. 39: 1061-1068.
Publication Series: Scientific Journal (JRNL)
Station: Northern Research Station
PDF: View PDF (838.96 KB)
DescriptionSystematic sampling is easy, efficient, and widely used, though it is not generally recognized that a systematic sample may be drawn from the population of interest with or without restrictions on randomization. The restrictions or the lack of them determine which estimators are unbiased, when using the sampling design as the basis for inference. We describe the selection of a systematic sample, with and without restriction, from populations of discrete elements and from linear and areal continuums (continuous populations). We also provide unbiased estimators for both restricted and unrestricted selection. When the population size is known at the outset, systematic sampling with unrestricted selection is most likely the best choice. Restricted selection affords estimation of attribute totals for a population when the population size - for example, the area of an areal continuum - is unknown. Ratio estimation, however, is most likely a more precise option when the selection is restricted and the population size becomes known at the end of the sampling. There is no difference between restricted and unrestricted selection if the sampling interval or grid tessellates the frame in such a way that all samples contain an equal number of measurements. Moreover, all the estimators are unbiased and identical in this situation.
- Check the Northern Research Station web site to request a printed copy of this publication.
- Our on-line publications are scanned and captured using Adobe Acrobat.
- During the capture process some typographical errors may occur.
- Please contact Sharon Hobrla, email@example.com if you notice any errors which make this publication unusable.
- We recommend that you also print this page and attach it to the printout of the article, to retain the full citation information.
- This article was written and prepared by U.S. Government employees on official time, and is therefore in the public domain.
CitationValentine, Harry T.; Affleck, David L. R.; Gregoire, Timothy G. 2009. Systematic sampling of discrete and continuous populations: sample selection and the choice of estimator. Canadian Journal of Forest Research. 39: 1061-1068.
- Line intersect sampling: Ell-shaped transects and multiple intersections
- Generalized and synthetic regression estimators for randomized branch sampling
- Design unbiased estimation in line intersect sampling using segmented transects
XML: View XML