Bayesian Analysis

Directional log-spline distributions

José T. A. S. Ferreira, Miguel A. Juárez, and Mark F. J. Steel

Full-text: Open access

Abstract

We introduce a new class of distributions to model directional data, based on hyperspherical log-splines. The class is very flexible and can be used to model data that exhibit features that cannot be accommodated by typical parametric distributions, such as asymmetries and multimodality. The distributions are defined on hyperspheres of any dimension and thus, include the most common circular and spherical cases. Due to the flexibility of hyperspherical log-splines, the distributions can closely approximate observed behaviour and are as smooth as desired. We propose a Bayesian setup for conducting inference with directional log-spline distributions where we pay particular attention to the prior specification and the matching of the priors of the log-splines model and an alternative model constructed through a mixture of von~Mises distributions. We compare both models in the context of three data sets: simulated data on the circle, circular data on the movement of turtles and a spherical application to the arrival direction of cosmic rays.

Article information

Source
Bayesian Anal. Volume 3, Number 2 (2008), 297-316.

Dates
First available in Project Euclid: 22 June 2012

Permanent link to this document
https://projecteuclid.org/euclid.ba/1340370549

Digital Object Identifier
doi:10.1214/08-BA311

Mathematical Reviews number (MathSciNet)
MR2407428

Zentralblatt MATH identifier
1330.62076

Keywords
Directional distributions hyperspherical splines mixture of distributions prior matching von Mises distributions

Citation

Ferreira, José T. A. S.; Juárez, Miguel A.; Steel, Mark F. J. Directional log-spline distributions. Bayesian Anal. 3 (2008), no. 2, 297--316. doi:10.1214/08-BA311. https://projecteuclid.org/euclid.ba/1340370549


Export citation

References

  • Abramowitz, M. and Stegun, I. (eds.) (1972). Handbook of Mathematical Functions with Formulas, Graphs and Mathematical Tables. New York.: Dover.
  • Boulerice, B. and Ducharme, G. R. (1994). "Decentred Directional Data." Annals of the Institute of Statistical Mathematics, 46: 573–586.
  • Denison, D., Holmes, C., Mallick, B., and Smith, A. (2002). Bayesian Methods for Nonlinear Classification and Regression. Chichester: Wiley.
  • Denison, D. G. T., Mallick, B. K., and Smith, A. F. M. (1998). "Automatic Bayesian curve-fitting." Journal of the Royal Statistical Society, B, 60: 330–350.
  • DiMatteo, I., Genovese, C. R., and Kass, R. E. (2001). "Bayesian curve-fitting with free-knot splines." Biometrika, 88: 1055–1071.
  • Fernández-Durán, J. J. (2004). "Circular distributions based on nonnegative trigonometric sums." Biometrics, 60: 499–503.
  • Ferreira, J. T. A. S. and Steel, M. F. J. (2005). "Modelling directional dispersion through hyperspherical log-splines." Journal of the Royal Statistical Society, B, 67: 599–616.
  • Fisher, N. I. (1993). Statistical Analysis of Circular Data. Cambridge: Cambridge University Press.
  • Fisher, N. I., Lewis, T., and Embleton, B. J. J. (1987). Statistical Analysis of Spherical Data. Cambridge: University Press.
  • Ghosh, K., Jammalamadaka, S. R., and Tiwari, R. C. (2003). "Semiparametric Bayesian techniques for problems in circular data." Journal of Applied Statistics, 30: 145–161.
  • Goodall, G. (1999). "Directional Data." Teaching Statistics, 21: 90–92.
  • Grimshaw, S. D., Whiting, D. G., and Morris, T. H. (2001). "Likelihood ratio tests for a mixture of two von Mises distributions." Biometrics, 57: 260–265.
  • Guttorp, P. and Lockhart, R. A. (1988). "Finding the location of a signal: A Bayesian analysis." Journal of the American Statistical Association, 83: 322–329.
  • Hall, P., Watson, G. S., and Cabrera, J. (1987). "Kernel density estimation with spherical data." Biometrika, 74: 751–762.
  • Hansen, M. H. and Kooperberg, C. (2002). "Spline adaptation in extended linear models." Statistical Science, 17: 2–51.
  • Jammalamadaka, S. R. and SenGupta, A. (2001). Topics in Circular Statistics. Singapore: World Scientific.
  • Jones, M. and Pewsey, A. (2005). "A family of symmetric distributions on the circle." Journal of the American Statistical Association, 100: 1422–1428.
  • Kass, R. E. and Raftery, A. E. (1995). "Bayes factors." Journal of the American Statistical Association, 90: 773–795.
  • Kaufman, C. G., Ventura, V., and Kass, R. E. (2005). "Spline-based nonparametric regression for periodic functions and its application to directional tuning of neurons." Statistics in Medicine, 24: 2255–2265.
  • Kendall, M. G. (1961). A course in the Geometry of $n$ Dimensions. Number 8 in Griffin's Statistical Monographs and Courses. London: Charles Griffin.
  • Kent, J. T. (1983). "Identifiability of finite mixtures for directional data." Annals of Statistics, 15: 247–254.
  • Kent, J. T. and Tyler, D. E. (1988). "Maximum likelihood estimation for the wrapped Cauchy distribution." Journal of Applied Statistics, 15: 247–254.
  • Mardia, K. V. and El-Atoum, S. A. M. (1976). "Bayesian inference for the von Mises-Fisher distribution." Biometrika, 63: 403–405.
  • Mardia, K. V. and Jupp, P. E. (2000). Directional Statistics. Chichester: Wiley.
  • Mardia, K. V. and Spurr, B. D. (1973). "Multisample tests for multimodal and axial circular populations." Journal of the Royal Statistical Society, B, 35: 422–436.
  • Mooney, J. A., Helms, P. J., and Jolliffe, I. T. (2003). "Fitting mixtures of von Mises distributions: a case study involving sudden infant death syndrome." Computational Statistics and Data Analysis, 41: 505–513.
  • Newton, M. A. and Raftery, A. E. (1994). "Approximate Bayesian inference with the weighted likelihood bootstrap (with discussion)." Journal of the Royal Statistical Society, B, 56: 3–48.
  • Nuñez-Antonio, G. and Gutiérrez-Peña, E. (2005). "A Bayesian analysis of directional data using the von Mises-Fisher distribution." Communications in Statistics, Simulation and Computation, 34: 1–11.
  • Peel, D., Whiten, W. J., and McLachlan, G. J. (2001). "Finite mixtures of Kent distributions to aid in joint set identification." Journal of the American Statistical Association, 96: 56–63.
  • Ravindran, P. and Ghosh, S. K. (2004). Bayesian analysis of circular data using wrapped distributions. 2564. North Carolina State University: Institute of Statistics Mimeographs.
  • Rheinboldt, W. C. and Rosenfeld, A. (1966). "Computer oriented research in the space related sciences. March 1965 to February 1966." Research grant report NsG-398, NASA.
  • Richardson, S. and Green, P. J. (1997). "On Bayesian analysis of mixtures with an unknown number of components (with discussion)." Journal of the Royal Statistical Society, B, 59: 731–792.
  • Stephens, M. A. (1969). "Techniques for directional data." Technical Report 150, Stanford University.
  • Taijeron, H. J., Gibson, A. G., and Chandler, C. (1994). "Spline interpolation and smoothing in hyperspheres." SIAM Journal on Scientific Computing, 15: 1111–1125.
  • Wahba, G. (1975). "Smoothing noisy data by spline functions." Numerische Mathematik, 24: 383–393.
  • –- (1981). "Spline interpolation and smoothing on the sphere." SIAM Journal on Scientific and Statistical Computing, 2: 5–16.
  • –- (1990). "Spline models for observational data." In CBMS-NSF Regional Conference Series in Applied Mathematics. Philadelphia.
  • Wood, A. T. A. (1982). "A bimodal distribution on the sphere." Journal of the Royal Statistical Society, C, 31: 52–58.