USDA Forest Service
 

RMRS Black and White Graphic ElementForest Inventory & Analysis

 
 

Forest Inventory & Analysis
507 25th Street
Ogden, UT 84401-2450

(801) 625-5407

United States Department of Agriculture Forest Service.

USDA Link Forest Service Link

 

Paul Patterson - Mathematical Statistician


Paul Patterson

Interior West Forest Inventory and Analysis

2150-A Centre Ave, Suite 350
Fort Collins, CO 80526-8121

(970) 295-5966

plpatterson@fs.fed.us

Education
  • Ph.D in Statistics, Colorado State University, 2006
  • Ph.D in Mathematics, Oregon State University, 1987
  • B.S. in Mathematics, University of Oregon, 1981
Current Research

Primary responsibility is to conduct consultations with individuals from IW-FIA. Although most consultations are with individuals in the Techniques and Analysis group, I also consult with individuals from the Information Management and Data Acquisition groups.  The consultations can involve: 1) assisting the clients in stating the problem in a precise form; 2) determining the appropriate techniques to solve the problem; 3) explaining the solution and the techniques involved in terms the clients can understand; 4) if the solution is not published, then develop statistical techniques, derive equations or write computer programs as needed; 5) assisting the clients in executing the solution and if necessary assist in moving experimental solutions into production mode. I also consult with the national FIA program and with outside groups. A general areas of interest are finite and infinite sampling strategies for forest and rangeland inventories; natural resource monitoring. Some of the current projects are: for modeled variables, incorporating modeling error into the estimated variance, with a specific application to biomass estimation from space-based Lidar; deriving the variance and estimated variance for an unbiased estimator in the presence of nonresponse; verifying or establishing the statistical properties of certain endogenous post-stratified estimators; deriving the estimators, variance of the estimators and estimated variance for photo-based estimates of natural resources from large scale photography.

Past Research

With collaborators assessed the impacts of minimum within-strata and total sample sizes for post-stratification and made recommendations for the within-strata and total sample sizes.

With a collaborator explored the information forest inventory data can produce regarding forest types that were not sampled and developed the equations necessary to define upper confidence bounds on not-sampled forest types; this is relevant to creating mid-level vegetation maps by assisting in the development of statistically defensible map units.

Working with a biologist used quantile regression to identify upper confidence bounds on the amount of pinyon-juniper woodlands that provide security cover, thermal cover and suitable amount of big sagebrush forage for mule deer in Utah.

Along with several collaborators coordinated a pilot exploring aspects of combining the National Resource Inventory (NRCS-USDA) and Forest Inventory and Analysis (USFS-USDA) to form a rangeland monitoring program.

In response to a lawsuit, constructed statistically defensible confidence intervals for the proportion of area within the Forestland of the Targhee National Forest that is old growth and the proportion of either late seral or old growth.

Why This Research is Important

The proper use of statistical techniques is essential in order for managers to make informed decisions and the public to believe the conclusions of research.

Most Significant Publications
Selected Technical Reports

 

 

USDA Forest Service - RMRS - Forest Inventory & Analysis
Last Modified: Friday, 26 September 2014 at 08:28:00 CDT


USDA logo which links to the department's national site. Forest Service logo which links to the agency's national site.