2004 Progress Report: National Research Program on Design-Based/Model-Assisted Survey Methodology for Aquatic Resources

EPA Grant Number: R829096
Center: National Research Program on Design-Based/Model-Assisted Survey Methodology for Aquatic Resources
Center Director: Stevens, Don L.
Title: National Research Program on Design-Based/Model-Assisted Survey Methodology for Aquatic Resources
Investigators: Stevens, Don L. , Herlihy, Alan T. , Hughes, Robert , Lesser, Virginia , Urquhart, N. Scott
Current Investigators: Stevens, Don L. , Herlihy, Alan T. , Lesser, Virginia , Urquhart, N. Scott
Institution: Oregon State University
Current Institution: Oregon State University , Colorado State University
EPA Project Officer: Packard, Benjamin H
Project Period: October 15, 2001 through October 14, 2005 (Extended to October 13, 2006)
Project Period Covered by this Report: October 15, 2003 through October 14, 2004
Project Amount: $2,989,884
RFA: Research Program on Statistical Survey Design and Analysis for Aquatic Resources (2001) RFA Text |  Recipients Lists
Research Category: Aquatic Ecosystems , Ecological Indicators/Assessment/Restoration , Tribal Environmental Health Research , Water and Watersheds , Water , Ecosystems

Objective:

The objective of this research project is to develop and implement design-based/model-assisted statistical methods for aquatic surveys.

Progress Summary:

Design and Models for Aquatic Resource Surveys (DAMARS) began its third year of collaboration with the Oregon Department of Fish and Wildlife (ODFW) and the U.S. Environmental Protection Agency (EPA) Western Ecology Division (WED) on the sampling of coho salmon. Work continues on the description of a spatial pattern and imputation of missing data, but the focus is now shifting to analysis. Particular emphasis will be on incorporation ancillary information in status estimation, trend description and detection, description of a spatial pattern, imputation of missing data, and post facto design modification.

The utility of the Generalized Random Tessellation Stratified (GRTS) design for sampling and monitoring environmental resources is becoming more widely recognized by other federal agencies. Director Don L. Stevens has attended multiple workshops sponsored by the National Park Service, the Bureau of Land Management, the U.S. Department of Agriculture (USDA) Forest Service, the National Oceanic and Atmospheric Administration (NOAA) Fisheries, and other federal agencies where the GRTS design has been adopted or is being considered.

A new collaborative effort with another STAR program, the Great Lakes Environmental Indicators Program (GLEI), was initiated following a visit to Corvallis by GLEI Director Gerald Neimi. The goal of the research is to develop a multiscale habitat association model, possibly incorporating some approaches from Bayesian Belief Networks.

Eight papers have appeared in professional journals or proceedings this year, six more have been submitted and are currently in review, and another seven are in preparation. DAMARS staff have made over a dozen presentations at professional meetings. Presentations were made at the North American Benthological Society Annual Meeting, The Graybill Conference 2004, and the joint meeting of TIES 2004: The Fifteenth Annual Conference of The International Environmetrics Society and ACCURACY 2004: The Sixth International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental Sciences.

Project 1: Direction and Administration

The Director monitored the progress of Projects 2-5, including oversight of their budgets, staffing and coordination; monitored subcontracts to Colorado State University (CSU), Washington State University, and Iowa State University; assembled and submitted quarterly and annual reports; coordinated various matters with Space-Time Aquatic Resources Modeling and Analysis Program (STARMAP), the Colorado State University Program, and with the Program’s EPA Project Officer.

Project 2: Integration and Extramural Outreach Project

Program Directors Stevens and Urquhart have continued their frequent contact to coordinate the Oregon State University (OSU) and CSU programs, and each has made external contacts on the part of both the DAMARS and STARMAP programs. Highlights include:

  • CSU graduate student Gerald Scarzella completed his masters report on the development of browser-based learning materials , completed degree requirements, and took a position teaching in Alaska. His report has been posted to the STARMAP Web Site. His work was directly involved in the outreach materials for states and tribes. Development of browser-based learning materials has continued with the implementation of the “site” by the CSU Office of Instructional Services. The dictionary lookup feature has been implemented. Another masters student is starting work on the browser-based learning materials.
  • Director Stevens has attended a number of workshops with a theme of design for aquatic monitoring programs in the Pacific Northwest. The workshops have been sponsored by various federal and state agencies, and nongovernmental research organizations. These workshops have been an important and effective means to facilitate the forging of collaborative relationships between program statisticians, EPA/ORD scientists, and state and Tribal personnel, demonstrating current and new statistical approaches using aquatic monitoring data, and expanding the pool of personnel in the states and tribes who have both an understanding of, and experience in, using the statistical tools. Workshop attendees who have been exposed to some of these statistical tools have included representatives from NOAA-Fisheries, U.S. Geological Survey, USDA Forest Service, U.S. Fish and Wildlife Service (USFWS), five state fish agencies (WA, OR, ID, AK, and MT), the Fish Passage Center, the Columbia River Inter-Tribal Fish Commission (CRITFC; Nez Perce, Yakima, Umatilla, and Warm Springs Tribes), Confederated Tribes of the Siletz Indians, and the Colville Tribes, the Northwest Power and Conservation Council (NPCC), Fisheries and Oceans Canada, Hokkaido Institute of Environmental Sciences, Hokkaido Fish Hatchery, Khabarovsk TINRO, and Kamchata NIRO. These workshops have increased the awareness of the need for rigorous statistical basis for monitoring, and the likelihood that a coherent monitoring strategy based on some Environmental Monitoring and Assessment Program (EMAP) concepts will be adopted by numerous agencies engaged in aquatic monitoring in the Northwest.

Project 3: Survey Design Methodology for Aquatic Resources Project

This project continued the investigation of both design issues and modeling of survey data. On the design side, active projects were looking at incorporating ancillary information in survey design, optimal allocation for two-stage designs, variance estimation for spatially balanced designs, and comparison of model-based and design-based sample selection techniques. Modeling efforts, which include a collaborative research project with GLEI that was initiated to develop statistical models for multiscale environmental data and the continued spatial-temporal modeling of ODFW coastal coho data continued, with elaboration of the mean structure model, and extension to include a temporal component. Specific activities include:

  • One issue that arises frequently in environmental sampling is that agencies have a long history of sampling at nonprobability sites. Director Stevens has extended the GRTS sample selection algorithm to select a spatially balanced sample conditional on the existence of some fixed sites. The results of the selection process is a spatially balanced composite sample (fixed + probability sites). He also has been investigating ways to use data from fixed sites in conjunction with data from probability sites. A natural outcome of the process of selecting a spatially balanced composite sample is that it is possible to assign a “pseudo inclusion probability” to the fixed sites.
  • The sample point pattern resulting from a GRTS sample also was compared to a point pattern that was optimized for spatial regularity via simulated annealing. Several traditional spatial regularity criteria were investigated, plus one that was developed by Director Stevens called the Side-Vertex-Boundary (SVB) criterion. The SVB is defined by:

In practice, the SVB is approximated by the minimum separation distance from a sample point to Sides, Vertices, and Boundaries relative to a nominal value. As expected, the GRTS sample showed more spatial regularity than simple random sample, but less than an optimized point pattern. Similar behavior was observed for the variance of a mean value for patchy response surfaces.

  • Several efforts have been looking at variance estimators for spatial sampling designs. In one, Ph.D. candidate Cynthia Cooper has developed a proposed model-assisted sampling-process variance estimator for design-based estimation and model-based prediction. The approach and simulated results for a grid-stratified sample were presented at the OSU Statistics Department Seminar and later at the TIES-ACCURACY 2004 Conference. The sampling-process variance estimation uses a fitted covariance structure to model the variance of any randomly sampled element within a stratum. Graduate student Susan Hornsby has been studying the behavior of several variance estimators that have been proposed for systematic designs and comparing them to the behavior of the neighborhood estimator developed by Stevens and Olsen for the GRTS design. The neighborhood estimator compared favorably to the other estimators even for strictly systematic designs when the response showed some spatial covariance.
  • Director Stevens has been working with Ron Regal, a statistician at the University of Minnesota–Duluth, on optimizing efficiency of multistage cluster sample designs. The results of the research will be applied to selecting wetland samples for GLEI, another EPA STAR supported project, and presented at the Ft. Collins joint program meeting with STARMAP in September.
  • Doctoral student Leigh Ann Harrod worked with Director Stevens to update and develop the trend analysis methodology for application with the ODFW habitat survey data. The trend estimate draws on the panel structure of the ODFW design by utilizing a design-based difference estimator. Current effort is to develop a variance estimator based on the Stevens-Olsen estimator for spatially balanced designs.
  • Kathryn Georgitis, a Ph.D. candidate, is collaborating with researchers from the Natural Resources Research Institute in Duluth, Minnesota. An important question for understanding bird distributions across landscapes is their relationship with vegetation characteristics at different spatial scales. With the ready availability of remotely sensed data, local vegetation characteristics are increasingly supplemented with vegetation and landuse information at broader spatial scales. Using Geographic Information Systems software, it is possible to create different classification schemes and different scales of measurement, which can be used as explanatory variables. Thus, it is important to understand the influence of landscape characterization on statistical estimates. Georgitis is implementing hierarchical Bayesian models to assess if bird species abundance is associated with local habitat and/or landscape characteristics, and how that association changes with different scales and characterizations. She is using a subset of data from a long-term breeding bird survey. The corresponding landscape characteristics are developed from a land cover map.
  • Georgitis and Alix Gitelman are investigating the use of graphical models to address multiscale questions in ecological studies. The conditional modeling approach allows for specification of correlation between variables at the same and multiple scales. Also, this approach can be used to explore how the presence/absence of a species is related to vegetation characteristics at multiple scales, similar to Bayesian hierarchical models. They presented the poster “ What is a Multi-Scale Analysis? Implications for Modeling Presence/Absence of Bird Species” at the annual meeting of TIES in Portland, Maine, in July, and are currently working on a paper about their findings. A manuscript on this topic is currently in review.
  • Post-doctoral research associate Ruben Smith continued his work on modeling spatial patterns in Coho populations using ODFW survey data. Focus has been to elaborate the mean structure by incorporating explanatory variables, such as habitat metrics, and indicator variables for biological population membership. A manuscript based on this work, titled “Statistical Distribution Maps of Abundance of Returning Adult Coho Salmon ( Oncorhynchus kisutch) for the Oregon Coast”, has been submitted to the Canadian Journal of Fisheries and Aquatic Sciences. Current work is on developing a Space-Time Autoregressive Moving Average Model (STARMA). The approach to the space-time model is to discretize the spatial process by assigning each observation to the nearest location on fine grid. A model of the form:

is then fit to the gridded data. In this model, Z t is a s patio-temporal dynamic process that accounts for the spatial variation of the coho spawners over time, h ti is a spatio-temporal random process that accounts for observational error and small-scale spatio-temporal variation, and the x ti term models the mean structure. The STARMA used for Z is of the form:

where W is an autoregressive process that can vary over space. The model is being fit by Markov Chain Monte Carlo methods. Results from preliminary simulations suggest that the model implementation in MATLAB is running as expected, but the chain has not yet converged.

Project 4: Parametric Model-Assisted Survey Methods for Environmental Surveys Project

Virginia Lesser, Breda Munoz, and graduate student Leigh Ann Harrod are developing a technique for addressing non-ignorable nonresponse based on a Bayesian model. The approach is being developed using the ODFW coho salmon survey, which has substantial nonresponse rates in some of the Monitoring Areas. The nonresponse appears to be related to site ownership, and may be associated with habitat quality and salmon abundance. The paper “Applying Multiple Imputation with Geostatistical Models to Account for Item Nonresponse in Environmental Data” is ready for submission to the Journal of Agricultural, Biological, and Environmental Statistics or the journal Ecological and Environmental Statistics. The manuscript “A Weighting Class Adjustment Estimator for the Total Under a Stratified Sampling Design in a Continuous Domain” is almost ready for submission, pending review of simulation results. The manuscript “Adjustment Procedures to Account for Non-Ignorable Missing Data in Environmental Surveys” is in its second revision. Further simulation work is needed prior to journal submission. The manuscript “Model-Based Approaches for Handling the Non-Ignorable Missing Data Mechanism for Inference in Environmental Surveys” is in its second draft stage. Theoretical development has been completed for the manuscript “Accounting for Missing Data in Spatial CDF Estimation”. The theory has yet to be verified via simulation.

Harrod has continued development of a user manual for environmental scientists who use probability surveys in which missing data are encountered. The user manual contains definitions of types of nonresponse, methods to determine which types of nonresponse may affect the survey data, approaches to deal with the nonresponse, and examples of nonresponse adjustment approaches on sample data sets. Research by Harrod on this topic has included a review of literature addressing nonresponse error, derivation of adjustment estimators for finite population sampling, and applications of these methods to data from the annual ODFW coho salmon spawner surveys as well as examples from questionnaire surveys on nonresponse using data from elk harvest surveys from the New Mexico Department of Game and Fish. This report will illustrate analysis techniques and adjustment methodology for missing-at-random data.

Project 5: Nonparametric Model-Assisted Survey Estimation for Aquatic Resources

Postdoctoral fellow M. Giovanna Ranalli has been working with F. Jay Breidt and Jean Opsomer on semiparametric methods for model-assisted regression estimation: penalized splines in a spatial context have been considered to model ANC data from MAHA. Low-rank thin plate splines and kriging have been implemented with a mixed model representation. Geometric anisotropy and nonstationarity is now being considered. The mixed model representation allows straightforward insertion of a random effect for prediction in small areas. Ranalli has been working with Haonan Wang (CSU - Statistics) on a modification of low-rank thin plate splines to model surfaces with boundaries (e.g., measurements on a lake with islands) and nonfunctional surfaces. Simulations were conducted and a manuscript on this is planned. Ranalli has applied nonparametric model calibration estimation in a model-assisted framework to stream nutrients (total nitrogen and phosphorus) in the MAHA study. Neural networks and local polynomials have been employed. A manuscript utilizing MAHA data has tentatively been accepted for publication in the Journal of the American Statistical Association. Ranalli has continued her work with Wang on a modification of low-rank thin plate splines to model surfaces with boundaries (e.g., measurements on a lake with islands) and nonfunctional surfaces. Simulations have been conducted and a manuscript is nearly ready for submission to Biometrika.

Breidt and Opsomer are continuing work on the use of nonparametric modeling for survey regression estimation, jointly supported by DAMARS and STARMAP. Numerous invited talks have been given and several manuscripts have been submitted. The problems of interest in this context combine landscape-level auxiliary data (such as those from GIS coverages) together with field observations. The inferential problems range from model-assisted descriptive inferences for aquatic populations, to model-based small area estimates. Breidt and Opsomer, together with students and colleagues, extended earlier results on local polynomial survey regression estimation in a number of directions, some of which are described here. The M.S. project of Alicia Johnson on cumulative distribution function estimation was submitted for publication, and the M.S. project of Siobhan Everson-Stewart on two-dimensional kernel estimators was extended by Ranalli to the setting of penalized splines. Ranalli and Breidt also obtained promising preliminary results on the use of low-rank radial basis functions for smoothing data from river networks. Ji-Yeon Kim successfully defended her Ph.D. under the direction of Breidt and Opsomer, and submitted a joint paper on two-stage local polynomial regression estimation. New work was conducted with Gerda Claeskens on nonparametric model-assisted estimation using penalized splines, and was extended to the case of small area estimation. Ph.D. student Mark Delorey is further extending penalized spline estimators to the setting of two-stage sampling.

Future Activities:

Project 2: Integration and Extramural Outreach

Our Science Advisory Committee (SAC) recommended that DAMARS and STARMAP develop a focused integration project, possibly centered on a case study. The concept has been discussed with members of STARMAP and DAMARS, as well as potential collaborators. Currently, the Directors of STARMAP and DAMARS are discussing a special issue of an environmental statistics journal that would consist of a series of papers encompassing all aspects of designing, implementing, and analyzing an aquatic resource monitoring program. It is anticipated that substantial effort will be devoted to developing and coordinating the integration project suggested by the SAC.

Project 3: Survey Design Methodology for Aquatic Resources

Director Stevens will continue active work on developing design-based trend assessment methods for rotating panel designs, methods for combining probability and nonprobability data, and using Bayesian hierarchical models to predict the distribution of indicator values. An additional active research area will be the realignment of rotating panel design to accommodate changing priorities and emphasis regions.

Smith will extend the Bayesian Hierarchical spatial model for counts of juvenile coho salmon in Oregon coastal streams to include a temporal component and ancillary data, such as ocean and watershed conditions. He also will continue to develop tools for data display.

Director Stevens will present an invited paper at the ENAR meetings in March in Austin, Texas, and a contributed paper at the International Statistical Institute (ISI) Meetings in Sydney, Australia, in April of 2005. He also expects to spend some time working with Dr. Bronwyn Harch at the Commonwealth Scientific and Industrial Research Organization in Queensland and to present a short course at the University of Melbourne while in Australia.

Project 4: Parametric Model-Assisted Survey Methods for Environmental Surveys

Breda Munoz, the postdoctoral fellow who was working on Project 4, left DAMARS at the end of October 2004. Because of the shortage of interested and qualified students, the project currently does not have a graduate student assigned. Therefore, progress will likely be limited in the coming year, although Munoz has committed to completing jointly authored manuscripts. It is expected that some of the methodology developed in Project 4 will be applied to the integration project suggested by the SAC.

Lesser will attend the ISI meeting in Sydney in April, and present a paper.

Project 5: Nonparametric Model-Assisted Survey Estimation for Aquatic Resources

Breidt, Opsomer, Delorey, and Ranalli will continue to develop semiparametric methods for small area estimation, focusing on comparing penalize splines methods in a spatial context. These semiparametric procedures will be compared to fully parametric methods. A paper on this work, possibly using ANC data from MAHA, is planned.

Breidt and Opsomer are finalizing a manuscript on semiparametric additive regression estimation, which can accommodate models with multiple auxiliary variables of both continuous and categorical types, and can be a useful estimation procedure for regions with moderate sample sizes.


Journal Articles: 16 Displayed | Download in RIS Format

Other center views: All 142 publications 19 publications in selected types All 16 journal articles
Type Citation Sub Project Document Sources
Journal Article Andrews B, Davis RA, Breidt FJ. Maximum likelihood estimation for all-pass time series models. Journal of Multivariate Analysis 2006;97(7):1638-1659. R829096 (2003)
R829095 (Final)
R829095C002 (2003)
R829095C002 (2004)
  • Full-text: ScienceDirect-Full Text PDF
    Exit
  • Abstract: ScienceDirect-Abstract
    Exit
  • Journal Article Breidt FJ, Hsu N-J. Best mean square prediction for moving averages. Statistica Sinica 2005;15(2):427-446. R829096 (2003)
    R829096 (2005)
    R829095 (Final)
    R829095C002 (2003)
    R829095C002 (2004)
    R829095C002 (2005)
  • Full-text: StatisticaSinica-Full Text PDF
    Exit
  • Abstract: StatisticaSinica-Abstract
    Exit
  • Journal Article Breidt FJ, Hsu N-J, Coar W. A diagnostic test for autocorrelation in increment-averaged data with application to soil sampling. Environmental and Ecological Statistics 2008;15(1):15-25. R829096 (2005)
  • Abstract: SpringerLink Abstract
    Exit
  • Journal Article Buchanan RA, Conquest LL, Courbois J-Y. A cost analysis of ranked set sampling to estimate a population mean. Environmetrics 2005;16(3):235-256. R829096 (2002)
    R829096 (2003)
    R829096 (2004)
    R829096 (2005)
  • Abstract: Wiley Interscience
    Exit
  • Journal Article Cooper C. Sampling and variance estimation on continuous domains. Environmetrics 2006;17(6):539-553. R829096 (2005)
  • Abstract: Wiley Interscience Abstract
    Exit
  • Journal Article Courbois JP, Urquhart NS. Comparison of survey estimates of the finite population variance. Journal of Agricultural, Biological, and Environmental Statistics 2004;9(2):236-251. R829096 (2003)
    R829096 (2004)
    R829096 (2005)
    R829095 (2004)
    R829095 (2005)
    R829095 (Final)
    R829095C003 (2003)
    R829095C003 (2004)
  • Abstract: SpringerLink
    Exit
  • Journal Article Da Silva DN, Opsomer JD. Properties of the weighting cell estimator under a nonparametric response mechanism. Survey Methodology 2004;30(1):45-55. R829096 (2004)
    R829096 (2005)
    R829095 (2003)
    R829095 (2004)
    R829095 (2005)
    R829095 (Final)
    R829095C002 (2004)
    R829095C002 (2005)
  • Full-text: Statistics Canada-Full Text PDF
    Exit
  • Abstract: Statistics Canada-Abstract
    Exit
  • Journal Article Montanari GE, Ranalli MG. Nonparametric model calibration estimation in survey sampling. Journal of the American Statistical Association 2005;100(472):1429-1442. R829096 (2004)
    R829096 (2005)
    R829095 (Final)
    R829095C002 (2004)
    R829095C002 (2005)
  • Abstract: American Statistical Association-Abstract
    Exit
  • Journal Article Munoz B, Lesser VM. Adjustment procedures to account for non-ignorable missing data in environmental surveys. Environmetrics 2006;17(6):653-662. R829096 (2005)
  • Abstract:
    Exit
  • Journal Article Munoz B, Lesser VM, Ramsey FL. Design-based empirical orthogonal function model for environmental monitoring data analysis. Environmetrics 2008;19(8):805-817. R829096 (2003)
    R829096 (2004)
    R829096 (2005)
  • Abstract: Wiley InterScience Abstract
    Exit
  • Journal Article Opsomer JD, Botts C, Kim JY. Small area estimation in a watershed erosion assessment survey. Journal of Agricultural, Biological, and Environmental Statistics 2003;8(2):139-152. R829096 (2004)
    R829096 (2005)
    R829095 (2004)
    R829095 (2005)
    R829095 (Final)
    R829095C002 (2004)
  • Full-text: Research Gate-Abstract and Full Text HMTL
    Exit
  • Abstract: SpringerLink-Abstract
    Exit
  • Journal Article Opsomer JD, Breidt FJ, Moisen GG, Kauermann G. Model-assisted estimation of forest resources with generalized additive models. Journal of the American Statistical Association 2007;102(478):400-409. R829096 (2003)
    R829096 (2004)
    R829096 (2005)
    R829095 (2004)
    R829095 (2005)
    R829095 (Final)
    R829095C002 (2004)
    R829095C002 (2005)
  • Full-text: US Forest Service-Full Text PDF
    Exit
  • Abstract: Journal of the American Statistical Association-Abstract
    Exit
  • Journal Article Opsomer JD, Claeskens G, Ranalli MG, Kauermann G, Breidt FJ. Non-parametric small area estimation using penalized spline regression. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 2008;70(1):265-286. R829096 (2005)
    R829095C002 (2005)
  • Abstract: Wiley
    Exit
  • Other: Prepublication PDF
    Exit
  • Journal Article Stevens Jr. DL, Olsen AR. Variance estimation for spatially balanced samples of environmental resources. Environmetrics 2003;14(6):593-610. R829096 (2003)
    R829096 (2005)
  • Full-text: EPA Full-Text
  • Abstract: Wiley Interscience
    Exit
  • Journal Article Stevens Jr. DL, Olsen AR. Spatially-balanced sampling of natural resources. Journal of the American Statistical Association 2004;99(465):262-278 R829096 (2002)
    R829096 (2004)
    not available
    Journal Article Thomas DL, Johnson D, Griffith B. A Bayesian random effects discrete-choice model for resource selection: population-level selection inference. Journal of Wildlife Management 2006;70(2):404-412. R829096 (2005)
    R829095 (Final)
  • Abstract: Wiley-Abstract
    Exit
  • Supplemental Keywords:

    public policy, decisionmaking, community-based, monitoring, risk assessment, watersheds, streams, rivers, estuaries, economic, social, and behavioral science research program, ecosystem protection/environmental exposure and risk, water, applied math and statistics, aquatic ecosystem, aquatic ecosystems and estuarine research, ecological effects - environmental exposure and risk, ecological risk assessment, economics and decisionmaking, ecosystem protection, ecosystem/assessment/indicators, engineering, chemistry, and physics, environmental monitoring, monitoring/modeling, urban and regional planning, Bayesian approach, EMAP, aquatic, aquatic resources, community-based approach, empirical orthogonal functions, environmental data, environmental decisionmaking, landscapes, model-assisted estimation, model-based analysis, modeling, spatial analysis, statistical methodology, statistical tools, surface water, survey,, RFA, Scientific Discipline, Ecosystem Protection/Environmental Exposure & Risk, Aquatic Ecosystems & Estuarine Research, Aquatic Ecosystem, Environmental Monitoring, EMAP, estuarine research, risk assessment, ecosystem monitoring, statistical survey design, spatial and temporal modeling, aquatic ecosystems, Environmental Monitoring and Assessment Program

    Progress and Final Reports:

    Original Abstract
  • 2002 Progress Report
  • 2003 Progress Report
  • 2005 Progress Report
  • Final