Circular data in biology: advice for effectively implementing statistical procedures

Abstract

Circular data are common in biological studies. The most fundamental question that can be asked of a sample of circular data is whether it suggests that the underlying population is uniformly distributed around the circle, or whether it is concentrated around at least one preferred direction (e.g. a migratory goal or activity phase). We compared the statistical power of five commonly used tests (the Rayleigh test, the V-test, Watson’s test, Kuiper’s test and Rao’s spacing test) across a range of different unimodal scenarios. The V-test showed higher power for symmetrical distributions, Rao’s spacing performed worst for all explored unimodal distributions tested and the remaining three tests showed very similar performance. However, the V-test only applies if the hypothesis is restricted to one (pre-specified) direction of interest. In all other unimodal cases, we recommend using the Rayleigh test. Much less explored is the multimodal case with data concentrated around several directions. We performed power simulations for a variety of multimodal situations, testing the performance of the widely used Rayleigh, Rao’s, Watson, and Kuiper’s tests as well as the more recent Bogdan and Hermans-Rasson tests. Our analyses of alternative statistical methods show that the commonly used tests lack statistical power in many of multimodal cases. Transformation of the raw data (e.g. doubling the angles) can overcome some of the issues, but only in the case of perfect f-fold symmetry. However, the Hermans-Rasson method, which is not yet implemented in any software package, outcompetes the alternative tests (often by substantial margins) in most of the multimodal situations explored. We recommend the wider uptake of the powerful but hitherto neglected Hermans-Rasson method. In summary, we provide guidance for biologists helping them to make decisions when testing circular data for single or multiple departures from uniformity.Electronic supplementary materialThe online version of this article (10.1007/s00265-018-2538-y) contains supplementary material, which is available to authorized users.

Taphonomy and chronosequence of the 709 ka Kalinga site formation (Luzon Island, Philippines)

“…Therefore, the mean angle is orthogonal www.nature.com/scientificreports/ to the dominant orientation which problematic for the calculation of the vector of magnitude 39 and for the statistical tests (Supplementary Table 1) based on the mean, especially for the Rayleigh test which is searching for rejection of the unimodality (e.g. isotropy) 51 . Hence, it is not surprising, with bimodal data, that this is the only test where the main orientation is rejected (Table 4) 45 .…”

Nest characteristics of the Eastern Rock Nuthatch (Sitta tephronota) in southwestern Iran

“…The orientation of the nest was assessed using the eight cardinal directions. To examine the frequency of nest entrance directions, the circular statistics method was used (Landler et al 2018). The circular mean direction (mean angle) with a 95% confidence interval was calculated.…”

Magnetic map in nonanadromous Atlantic salmon

“…We computed a mean heading for each individual that was then pooled with the others tested in the same magnetic treatment. We determined the mean heading within each treatment by calculating the mean pooled headings (the average measurement per fish) and used the Rayleigh test to determine the strength of orientation in response to a given magnetic field (42). The Mardia-Watson-Wheeler test (nonparametric) was used to determine whether orientation differed among magnetic fields.…”