Geoscience Reference
In-Depth Information
For both policy and scientific reasons, probability sampling is a necessary characteristic of
the sampling design. Within the class of probability sampling designs, we must seek to develop
or identify methods that resolve the conflicts of a design combining stratifying by LC class and
clustering. Protocols incorporating the advantages of two or more of the basic sampling designs
need to be implemented when combining data from different ongoing monitoring programs to
take advantage of existing data, or when augmenting a general sampling design to increase the
sample size for rare classes or small subregions. Sampling methods need to be explored for
assessing accuracy for different spatial aggregations of the data and for nonsite-specific accuracy
assessments. As is often the case for any developing field of application, sampling design for
accuracy assessment may not require developing entirely new methods, but rather learning better
how to use existing methods.
Implementing a scientifically rigorous sampling design provides a secure foundation to any
accuracy assessment. Accuracy assessment data have little or no value to inform us about the map's
utility if the data are not collected via a credible sampling design. Sampling design in accuracy
assessment is still evolving according to a progression common in other fields of application. Early
innovators identified the need for sound sampling practice (Fitzpatrick-Lins, 1981; Card, 1982;
Congalton, 1991). As more familiarity was gained with traditional survey sampling methods, more
complex sampling designs could be introduced and integrated into practice. The challenges con-
fronting sampling design for descriptive objectives of accuracy assessment were recognized as
daunting, but by no means insurmountable. The platitude that we must choose a sampling design
that “balances statistical validity and practical utility” was raised (Congalton, 1991), and specificity
was added to this generic recommendation by stating explicit criteria of both validity and utility
(Stehman, 2001).
The future direction of accuracy assessment sampling design demands new developments.
Practical challenges are a reality. For most, if not all, of these problems, statistical solutions already
exist, or the fundamental concepts and techniques with which to derive the solutions can be found
in the survey sampling literature. The key to implementing better, more cost-effective sampling
procedures in accuracy assessment is to move beyond the parochial, insular traditions characterizing
the early stage of accuracy assessment sampling and to recognize more clearly the broad expanse
of opportunities offered by sampling theory and practice. The topic on sampling design for accuracy
assessment is by no means closed. Sampling design in accuracy assessment may have progressed
to an advanced stage of adolescence, but it has yet to reach a level of consistency in good practice
and sound conceptual fundamentals necessary to be considered a scientifically mature endeavor.
More statistically sophisticated sampling designs not only contribute to the value of map accuracy
assessments, they are the result of our current needs for more information related to map utility.
If our needs were simple and few, the basic sampling designs receiving the bulk of attention in the
1980s and early 1990s would suffice. It is the increasingly demanding questions related to utility
of these maps that compel us to seek better, more cost-effective sampling designs. Identifying these
designs and implementing them in practice is the future of sampling practice in accuracy assessment.
2.8 SUMMARY
As maps delineating LC play an increasingly important role in natural resource science and
policy applications, implementing high-quality, statistically rigorous accuracy assessments becomes
essential. Typically, the primary objective of accuracy assessment is to provide precise estimates
of overall accuracy and class-specific accuracies (e.g., user's or producer's accuracies). An extended
set of objectives exists for most large-area mapping projects because multiple users interested in
different applications will employ the map. Constructing a cost-effective accuracy assessment is a
challenging problem given the multiple objectives the assessment must satisfy. To meet this chal-
lenge, a more integrated sampling approach combining several design elements such as stratifica-
