Using output

How to interpret and use the outputs from a distance sampling analysis

Evaluate your distance sampling models, and improve your density estimates using multi-model inference

Table of contents

Learning objectives

What you will learn in this module

By the end of this module you will be able to do the following

Alternative datasets

Download data on lemurs or petrels

Choose between two new datasets for your final assignment, or use your own data

Summarise evidence

Use the AICcmodavg package to create a summary table

Compare your models using Information Theory

Assess model fit

Use a Goodness of Fit test to check your models’ validity

Find out whether your models are explaining real patterns in your data, or just fitting noise

Re-assess poor models

Use c-hat and QAICc to deal with over-dispersion

Assess whether over-dispersion is a problem, and update your model comparison table

Evaluate covariates

Assess the importance of each covariate

Use Information theory to contrast the effect of a covariate across multiple models

Confidence intervals

Assess the precision of coefficient estimates

Further evidence to determine the importance of covariates

Model selection strategy

The culmination of our work with Information Theory

A multi-stage process to determine which hypotheses are the most informative

Multi-model inference

Draw conclusions from multiple models

What to do when multiple models and covariates have some degree of evidence in their favour

Assignment

Demonstrate your learning and earn a badge!

Submit work that showcases your new skills and a reflection on what you’re learning, plus feedback to others

Summary and reflection

A brief review of this module

Take a minute to reflect on what you’ve just learnt

🚧 Under construction

Further learning materials will be released shortly