Consideration of the natural characteristics of aquatic resources and available frame material has led to the development of new designs for surveying large-scale regions. This paper illustrates survey designs developed to meet the requirements for surveying various aquatic resources, including a finite, discrete population, such as lakes within one or more states; a continuous linear population within a bounded area, such as wadeable streams within one or more states; and a continuous two-dimensional population within a bounded area, such as coastal waters associated with one or more states. We present a unified approach that addresses the differences of the aquatic resources assuming the availability of frame material, such as Geographic Information System (GIS) coverages of the boundary for coastal waters, stream network, and lake locations from U.S. Environmental Protection Agency's River Reach File 3, derived from U.S. Geological Survey digital line graph data from 1:100,000 scale maps. The basic design methodology distributes the sample over the spatial extent of the resource domain, and a panel structure can be used to extend the sample through time. Key features for the approach are (1) utilizing survey theory for continuous populations within a bounded area, (2) explicit control of the spatial dispersion of the sample, (3) variable spatial density, (4) nested subsampling, and (5) incorporating panel structures for sampling over time.

https://www.jstor.org/stable/info/1400499

Spatially restricted surveys over time for aquatic resources

Standard time series methods are applied to the analysis of repeated surveys under the assumption that the population parameters at each time period follow a stochastic model. Both overlapping and nonoverlapping surveys are considered in general terms, and specific results are obtained for the time series models assumed in the work of Patterson [10].

Analysis of repeated surveys using time series methods.

Under a federal-state cooperative program, the U.S. Bureau of Labor Statistics (BLS) publishes monthly unemployment rate estimates for its 50 states and the District of Columbia. The primary source of data for this estimation problem is the Current Population Survey (CPS). However, the CPS state unemployment rate estimates are unreliable, because the survey provides relatively few observations per state. Various federal agencies use state-level unemployment rate estimates for policy making and fund allocation. Thus it is important to improve on the CPS estimates. For this, we propose a hierarchical Bayes (HB) method using a time series generalization of a widely used cross-sectional model in small-area estimation. The proposed method is compared in detail with the corresponding HB method, which uses the HB analog of the well-known Fay-Herriot cross-sectional model. A third model based on a time series approach to repetitive surveys is found to be very hard to implement for these data; the resulti...

Hierarchical Bayes Estimation of Unemployment Rates for the States of the U.S.

During the past decade and a half, environmental monitoring programshave increased in numberand importance. Large scale environmental monitoring programs often present design difficulties because they tend to measure many(sometimes hundreds) of parameters through space and time. Thispaper reviewed and summarized one important component of environmental monitoring programs, the statistical survey design. Survey designsused for long-term monitoring programs lasting multiple (≥3)occasions were reviewed, paying specialattention to those published after 1985. During this review, two key components of the overall survey design were identified. The first key component wasthe membership design. Groups of population units sampled the same occasionwere called panels here, and the membership design specified which units were members of which panels. The second component was the revisit design that specified when panels were to be revisited. Membership designs varied, butsome form of simple random or systematic design was popular.Among revisit designs, four basicpatterns were found in the literature and their relative strengths andweaknesses were summarized. To efficiently discuss revisit designs, anew unified short-hand notation was proposed and adopted.

Review of environmental monitoring methods: survey designs.

I consider estimation and seasonal adjustment of population means based on rotating panel surveys carried out at regular time intervals. The analysis uses a dynamic structural model that assumes a decomposition of the mean into a trend-level component and a seasonal component. The model accounts for the correlations between individual panel estimators and for possible rotation group effects. It can be applied to general rotation patterns using either the individual panel estimates or the aggregate sample estimates, depending on data availability. Empirical results illustrating the important features of the procedure are presented.

Estimation and Seasonal Adjustment of Population Means Using Data From Repeated Surveys

A unified finite population theory is developed for composite estimators of both the current level and change in level between consecutive occasions when a rotation sample design is employed. Explicit variance functions are given under the assumption that exponential and arithmetic correlation patterns hold over time for the characteristics of interest. Optimum values of the weight coefficients in the composite estimators, the optimum number of consecutive visits by a sampling unit, and the gain in efficiency relative to the use of simple estimators are all determined numerically. Moderate gains for level and appreciable gains for change are achieved when the correlation is high.

Jack E. Graham

Papers

Rotation designs for sampling on repeated occasions