Perpendicular distance models for line transect sampling.

Research output: Contribution to journalArticlepeer-review

84 Citations (Scopus)

Abstract

Perpendicular distance line transect models are examined to assess whether any single model can provide a general procedure for analysing line transect data. Of the two-parameter models considered, the hazard-rate model appears promising, whereas the exponential power series and exponential quadratic models do not. Of the nonparametric models, the Fourier series is the best developed, and is favoured by many researchers as a general model. However, for a given data set, the Fourier series estimate may be highly dependent on the number of terms selected, and so the model is not a clear improvement over the hazard-rate model. A similar variable-term model, using Hermite polynomials, is less dependent on the number of terms selected.-from Author

Original languageEnglish
Pages (from-to)177-195
Number of pages19
JournalBiometrics
Volume41
Issue number1
DOIs
Publication statusPublished - 1 Jan 1985

Fingerprint

Dive into the research topics of 'Perpendicular distance models for line transect sampling.'. Together they form a unique fingerprint.

Cite this