The circular quantile residual

Ana C.C. Andrade, Gustavo H.A. Pereira and Rinaldo Artes ()

Computational Statistics & Data Analysis, 2023, vol. 178, issue C

Abstract: Circular-linear regression is often used to model the relationship between a circular dependent variable and a set of linear predictor variables. It is used in many areas such as meteorology, biology, and medicine. For checking model adequacy, it is desirable to use residuals that are approximately standard normally distributed. Most of the residuals used in circular regression models do not meet this requirement and are used especially for outlier identification. Other residuals are limited to the von Mises regression models. An asymptotically standard normally distributed residual that can be used for any parametric circular-linear regression model is introduced. Monte Carlo simulation studies suggest that the distribution of this residual is well approximated by the standard normal distribution in small samples. To study the behavior of this residual, two regression models are introduced, and two applications are used to show that the proposed residual can detect model misspecification.

Keywords: Circular data; Circular-linear regression models; Diagnostic analysis; Quantile residual (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S016794732200192X
Full text for ScienceDirect subscribers only.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:csdana:v:178:y:2023:i:c:s016794732200192x

DOI: 10.1016/j.csda.2022.107612

Access Statistics for this article

Computational Statistics & Data Analysis is currently edited by S.P. Azen

More articles in Computational Statistics & Data Analysis from Elsevier
Bibliographic data for series maintained by Catherine Liu ().