2018
DOI: 10.1111/mms.12548
|View full text |Cite
|
Sign up to set email alerts
|

Long‐finned pilot whale (Globicephala melas, Traill 1809) subspecies in the Atlantic Ocean: Are there differences in their skulls?

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
2
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(2 citation statements)
references
References 52 publications
0
2
0
Order By: Relevance
“…The nature of the data involving multiple species, age classifications, and sexes caused ratios to have inconsistent distributions and variances, and be resilient to data transformations. Traditionally PCA is performed on data with Gaussian distributions, but this assumption is not required when using PCA as a descriptive tool for exploratory analysis (Jolliffe and Cadima 2016), and non-Gaussian ratio data have been successfully analyzed using PCA (e.g., Marina et al 2018). It is also possible that because resultant principal components are linear functions of 14 random variables with large sample sizes (n = 382 for all-animal analysis and n = 225 for adult-only analysis), the central limit theorem (CLT) can be applied to assume approximate normality even though the ratios are not normally distributed (Jolliffe 2002).…”
Section: Statistical Analysis and Visualizationmentioning
confidence: 99%
“…The nature of the data involving multiple species, age classifications, and sexes caused ratios to have inconsistent distributions and variances, and be resilient to data transformations. Traditionally PCA is performed on data with Gaussian distributions, but this assumption is not required when using PCA as a descriptive tool for exploratory analysis (Jolliffe and Cadima 2016), and non-Gaussian ratio data have been successfully analyzed using PCA (e.g., Marina et al 2018). It is also possible that because resultant principal components are linear functions of 14 random variables with large sample sizes (n = 382 for all-animal analysis and n = 225 for adult-only analysis), the central limit theorem (CLT) can be applied to assume approximate normality even though the ratios are not normally distributed (Jolliffe 2002).…”
Section: Statistical Analysis and Visualizationmentioning
confidence: 99%
“…The author also expressed the need of including samples from additional localities, in order to assess the variation of the colour pattern in the subspecies, as also recommended by other authors 18 . A more recent study found differences in skull morphometry of North and South Atlantic specimens 19 , but no studies were found that account for geographic variation within each area. Little genetic evidence exists to support their classification status using mitochondrial DNA.…”
mentioning
confidence: 92%