What is a species? A new universal method to measure differentiation and assess the taxonomic rank of allopatric populations, using continuous variables

Abstract

Existing models for assigning species, subspecies, or no taxonomic rank to populations which are geographically separated from one another were analyzed. This was done by subjecting over 3,000 pairwise comparisons of vocal or biometric data based on birds to a variety of statistical tests that have been proposed as measures of differentiation. One current model which aims to test diagnosability (Isler et al. 1998) is highly conservative, applying a hard cut-off, which excludes from consideration differentiation below diagnosis. It also includes non-overlap as a requirement, a measure which penalizes increases to sample size. The “species scoring” model of Tobias et al. (2010) involves less drastic cut-offs, but unlike Isler et al. (1998), does not control adequately for sample size and attributes scores in many cases to differentiation which is not statistically significant. Four different models of assessing effect sizes were analyzed: using both pooled and unpooled standard deviations and controlling for sample size using t-distributions or omitting to do so. Pooled standard deviations produced more conservative effect sizes when uncontrolled for sample size but less conservative effect sizes when so controlled. Pooled models require assumptions to be made that are typically elusive or unsupported for taxonomic studies. Modifications to improving these frameworks are proposed, including: (i) introducing statistical significance as a gateway to attributing any weighting to findings of differentiation; (ii) abandoning non-overlap as a test; (iii) recalibrating Tobias et al. (2010) scores based on effect sizes controlled for sample size using t-distributions. A new universal method is proposed for measuring differentiation in taxonomy using continuous variables and a formula is proposed for ranking allopatric populations. This is based first on calculating effect sizes using unpooled standard deviations, controlled for sample size using t-distributions, for a series of different variables. All non-significant results are excluded by scoring them as zero. Distance between any two populations is calculated using Euclidian summation of non-zeroed effect size scores. If the score of an allopatric pair exceeds that of a related sympatric pair, then the allopatric population can be ranked as species and, if not, then at most subspecies rank should be assigned. A spreadsheet has been programmed and is being made available which allows this and other tests of differentiation and rank studied in this paper to be rapidly analyzed.

Taxonomic revision, occurrence, and identification of Intermediate Egret Ardea intermedia in North Queensland, Australia

“…For each ratio variable, we compared the two taxa using Welch's t-test as a preliminary procedure recommended by Patten & Unitt (2002) and Donegan (2018). Variables that were not significantly different at α = 0.05 were omitted from further analysis.…”

“…A SIMPER (similarity percentage: Clarke 1993) analysis was conducted to identify which variables contributed most to any difference between the identified groups (Clarke 1993;Hammer et al 2001). The most significant variables were further examined using Cohen's d effect size (Cohen 1988), which has become the preferred method for testing differences between avian biometrics (Tobias et al 2010;Collar et al 2015;Lenhard & Lenhard 2016;Donegan 2018;Ho et al 2019;Sangster et al 2021). Finally, we included an analysis of the five suspect egrets from Cairns that instigated this study, and attempted to assign them to a specific taxon using the universal effect size (UES) diagnosability test provided by Donegan (2018) and canonical discriminant analysis (CDA, also known as canonical variate analysis).…”

“…The Tobias et al (2010) criteria have been criticised by several authors (e.g. Remsen 2015;Donegan 2018;Rheindt & Ng 2021), though many of the taxonomic splits published in Tobias et al (2010) and del Hoyo et al (2014,2016) have slowly been adopted by other national and global taxonomies such as Donegan et al (2016), IOC (Gill et al 2021), Clements (Clements et al 2021) and eBird (eBird 2021); see also discussion in Collar et al (2016). Tobias et al (2021) have also shown that the methodology has been adopted by many publications and globally adopted species splits (see also IOC 2021a,b).…”

Measuring evolutionary independence: A pragmatic approach to species classification

“…Finally, recognised species would arguably be more comparable because major sources of incomparability, such as the use of only one indicator of evolutionary independence, are eliminated. It should also be mentioned that the method's ability to reduce disorder can be expected to increase over time, as the transparency of the method facilitates further improvements and tweaking of the measure (Burfield et al 2017;Donegan 2018).…”

“…Most importantly, the Tobias criterion bypasses genetic data completely, thus ignoring much of the progress made in species delimitation over the past decade. In addition, the criterion has been criticised for the way it scores hybrid zones, its use of hard cut-offs for mostly continuous criteria, and the subjective evaluation of plumage pattern it requires (Remsen 2015(Remsen , 2016Donegan 2018). Finally, the system is obviously only applicable to birds, and thus resolves only a small part of taxonomic disorder.…”