Model criticism

Absolute and relative fit of detection function models

This practical continues the theme of fitting detection functions to line transect distance sampling data. Follow along with the R code inside the Quarto (.qmd) instructions.

You will proceed to fit a number of key function/adjustment term combinations to the data. You will also experiment with setting truncation distances.

The data you are analysing are simulated, where the true density and the true detection function is known. You will see how well your analyses perform in producing confidence intervals that include the true density. Also examine how much variability there is between different detection functions in their density estimates.

After completing that main task, you also have the opportunity to analyse another line transect data set of capercaillie, a native Scottish bird.

Lecture materials

Lecture discussion

Slides

Video

Exercise materials

Using R package

Video introduction

Instructions

Solution and discussion

Video summary

Using Distance for Windows

Video introduction

Instructions

Solution and discussion

Video summary

Supplemental materials

A detailed look at model selection

The two stages of model selection

References