Geoscience Reference
In-Depth Information
might be chosen so that the mean elevation of the sample pixels matches the mean elevation of all
pixels mapped as that LC class (i.e., the population mean). The method is designed to produce a
sample robust to violations in the model used to support inference. Most nonprobability sampling
designs implemented in accuracy assessment lack the underlying model-based rationale of balanced
sampling and instead are the result of convenience, judgment, or poor design. Schreuder and
Gregoire (2001) discuss other potential uses of nonprobability sampling data.
2.4.1
Policy Aspects of Probability vs. Nonprobability Sampling
Considering implementation of a nonprobability sampling protocol has policy implications in
addition to the scientific issues discussed in the previous section. The policy issues arise because
both scientists and managers using the LC map have a vested interest in the map's accuracy. Federal
sponsorship to create these maps adds an element of governmental responsibility to ensure, or at
least document, their quality. The stakes are consequently high and the accuracy assessment design
will need to be statistically defensible. Most government sampling programs responsible for pro-
viding national and broad regional estimates are conducted using probability sampling protocols.
The Current Population Survey (CPS) (McGuiness, 1994) and National Health and Nutrition
Examination Survey (NHANES) (McDowell et al., 1981) are two such programs designed as
probability samples. Similarly, national environmental sampling programs are typically based on
probability sampling protocols (Olsen et al., 1999).
The expense of LC maps covering large geographic regions combined with the multitude of
applications these maps serve elevates the importance of accuracy assessment to a level commen-
surate with these other national sampling programs. Accordingly, the protocols employed to evaluate
the quality of the LC data must achieve standards of sampling design and statistical credibility
established by other national sampling programs. These standards of accuracy assessment protocol
will exceed those acceptable for more local use, lower-profile maps. The exposure, or perhaps
notoriety, accruing to maps such as the NLCD will elicit intense scrutiny of their quality. Concerns
related to litigation may become more prevalent as use of LC maps affecting government decisions
increases. Map quality may be challenged not only scientifically, but also legally. Because the
sampling design is such a fundamental part of the scientific basis of an accuracy assessment, the
credibility of this component of accuracy assessment must be ensured. To provide this assurance,
the use of scientifically defensible probability sampling protocols should be a matter of policy.
2.5 STATISTICAL COMPUTING
The requirements for statistically rigorous design and analysis will tax the capability of tradi-
tional computing practice in accuracy assessment. Stehman and Czaplewski (1998) noted the
absence of readily accessible, easy-to-use statistical software that could perform the analyses
associated with the more complex sampling designs that will be needed for large-area map assess-
ments. Recent upgrades in computing software have improved this situation. For example, the
Statistical Analysis Software (SAS) analysis software now includes survey sampling estimation
procedures that can be adapted for accuracy assessment applications. Nusser and Klaas (2003)
implemented these procedures to obtain the typical suite of accuracy estimates and accompanying
standard errors for complex sampling designs. The SAS procedure accomplishing these tasks is
PROC SURVEYMEANS.
Survey sampling software will be invaluable if data from ongoing monitoring programs are to
be used for accuracy assessment. For example, suppose NRI data serve as the source of reference
data. Two characteristics of the NRI data, confidentiality and the unequal probability design used,
may be resolved by the capabilities available in SAS. To adhere to the estimation criterion of
consistency, the accuracy estimates must incorporate weights for the sample pixels derived from
