This is Columbia Basin Research’s Fourth video in a multi-part series on using Program USER, which stands for User-Specified Estimation Routine. USER is a program created by Columbia Basin Research at the University of Washington’s School of Aquatic and Fishery Sciences with funding provided by the Bonneville Power Administration.
Program USER allows investigators to estimate parameters of a study with the following characteristics:
1. All possible outcomes of the study can be characterized in terms of a finite number of discrete categories.
2. The categories are mutually exclusive and exhaustive; i.e., an individual in the study can be classified into one and only one category.
3. The data from the study consist of the number of individuals in the study that fall into each category.
A model within the USER framework consists of a likelihood with zero or more auxiliary likelihoods. Each likelihood consists of two or more categories, and each category consists of:
1. A unique label for identifying the category.
2. The probability for the category, defined as a function of the model parameters.
3. A count indicating the number of observations for the category.
This video examines another Joint Likelihood example. We’ll look at an example in which estimation requires a joint likelihood. A joint likelihood is composed of two or more separate models that together allow parameters to be estimated. In a simplified, hypothetical study to estimate the survival of downstream migrating juvenile salmon in a given river reach, acoustic-tagged salmon are released and detected at a downstream detection site as shown.
The user manual can be found at
If you use Program USER, please consider filling out our User Satisfaction Survey at
If you have any further questions, please email us at web@cbr.washington.edu
0 Comments