Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Journal article
Title: Comparison of three statistical classification techniques for maser identification
Author: Manning, E.
Holland, B.
Ellingsen, S.
Breen, S.
Chen, X.
Humphries, M.
Citation: Publications of the Astronomical Society of Australia, 2016; 33:e015-1-e015-30
Publisher: Cambridge University Press (CUP)
Issue Date: 2016
ISSN: 1323-3580
Statement of
Ellen M. Manning, Barbara R. Holland, Simon P. Ellingsen, Shari L. Breen, Xi Chen and Melissa Humphries
Abstract: We applied three statistical classification techniques—linear discriminant analysis (LDA), logistic regression, and random forests—to three astronomical datasets associated with searches for interstellar masers.We compared the performance of these methods in identifying whether specific mid-infrared or millimetre continuum sources are likely to have associated interstellar masers. We also discuss the interpretability of the results of each classification technique. Non-parametric methods have the potential tomake accurate predictions when there are complex relationships between critical parameters. We found that for the small datasets the parametric methods logistic regression and LDA performed best, for the largest dataset the non-parametric method of random forests performed with comparable accuracy to parametric techniques, rather than any significant improvement. This suggests that at least for the specific examples investigated here accuracy of the predictions obtained is not being limited by the use of parametric models.We also found that for LDA, transformation of the data to match a normal distribution led to a significant improvement in accuracy. The different classification techniques had significant overlap in their predictions; further astronomical observations will enable the accuracy of these predictions to be tested.
Keywords: Masers; methods: classification; stars: formation
Rights: © Astronomical Society of Australia 2016; published by Cambridge University Press
RMID: 0030094949
DOI: 10.1017/pasa.2016.13
Grant ID:
Appears in Collections:Mathematical Sciences publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.