Open AccessUSER 2.1; User Specified Estimation Routine, Techncial Manual 2003.
Author(s) -
James Lady,
Peter Westhagen,
John R. Skalski
Publication year - 2003
Language(s) - English
Resource type - Reports
DOI - 10.2172/962975
Subject(s) - computer science , multinomial distribution , count data , user interface , software , statistical model , estimation , statistical power , interface (matter) , data mining , statistics , systems engineering , machine learning , engineering , programming language , mathematics , poisson distribution , bubble , maximum bubble pressure method , parallel computing
This document is primarily a description of the user interface for USER2.1; it is not a description of the statistical theory and calculations behind USER. This project is funded by the Bonneville Power Administration, U.S. Department of Energy, under Contract No. 004126, Project No. 198910700 as part of the BPA's program to protect, mitigate, and enhance fish and wildlife affected by the development and operation of hydroelectric facilities on the Columbia River and its tributaries. The analysis of fish and wildlife data requires investigators to have the ability to develop statistical models tailored to their study requirements. Hence, a flexible platform to develop statistical likelihood models to estimate demographic parameters is necessary. To this end, Program USER (User Specified Estimation Routine) was developed to provide a convenient platform for investigators to develop statistical models and analyze tagging and count data. The program is capable of developing models and analyzing any count data that can be described by multinomial or product multinomial distributions. Such data include release-recapture studies using PIT-tags, radio-tags, balloon-tags, and acoustic-tags to estimate survival, movement, and demographic data on the age and/or sex structure of wild populations. The user of the program can specify the parameters and model structure at will to tailor the analyses to the specific requirements of the field sampling program, the data, and populations under investigation. All of this is available without the need for the user to know advanced programming languages or numerical analysis techniques, and without involving cumbersome software developed for extraneous purposes. Program USER represents a powerful statistical modeling routine that can be readily used by investigators with a wide range of interests and quantitative skills