Showing papers in "Sankhya in 2017"
TL;DR: In this paper, a likelihood approach was used to predict environmental characteristics based on both circular and linear predictors, and the observed information matrices and normal curvatures were derived, and simulated and real data examples were provided to illustrate their approach and establish the utility of their results.
Abstract: Distributional studies and regression models have played important roles in statistical analysis of circular data. Asymmetric circular-linear multivariate regression models (SenGupta and Ugwuowo Environ. Ecol. Stat.
13(3), 299–309 2006) are motivated by and applied to predict some environmental characteristics based on both circular and linear predictors. In this paper, we consider a likelihood approach (Cook J. R. Stat. Soc. Ser. B Stat Methodol.
48(2), 133–169 1986) to study influence diagnostic analysis for these models, using the maximum likelihood estimation and influence diagnostics methods. The observed information matrices and normal curvatures are derived. Simulated and real data examples are then provided to illustrate our approach and establish the utility of our results.
17 citations
TL;DR: In this paper, the authors show that the operations of mixing and wrapping linear distributions around a unit circle commute can produce a wide variety of circular models, and also point out how this general approach can produce flexible asymmetric circular models.
Abstract: We show that the operations of mixing and wrapping linear distributions around a unit circle commute, and can produce a wide variety of circular models. In particular, we show that many wrapped circular models studied in the literature can be obtained as scale mixtures of just the wrapped Gaussian and the wrapped exponential distributions, and inherit many properties from these two basic models. We also point out how this general approach can produce flexible asymmetric circular models, the need for which has been noted by many authors.
10 citations