Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Inference for circular distributions and processes.
AU - Coles, Stuart
PY - 1998
Y1 - 1998
N2 - One approach to defining models for circular data and processes has been to take a standard Euclidean model and to wrap it around the circle. This generates rich families of circular models but creates difficulties for inference. Using data augmentation ideas which have previously been applied to this problem in the framework of an EM algorithm, we demonstrate the power and flexibility of Markov chain Monte Carlo methods to fit such classes of models to circular data. The precision of the technique is confirmed through simulated examples, and then applications are given to multivariate and time series data of wind directions.
AB - One approach to defining models for circular data and processes has been to take a standard Euclidean model and to wrap it around the circle. This generates rich families of circular models but creates difficulties for inference. Using data augmentation ideas which have previously been applied to this problem in the framework of an EM algorithm, we demonstrate the power and flexibility of Markov chain Monte Carlo methods to fit such classes of models to circular data. The precision of the technique is confirmed through simulated examples, and then applications are given to multivariate and time series data of wind directions.
KW - circle - directional data - Markov chain Monte Carlo - time series - wind directions - wrapped processes
U2 - 10.1023/A:1008930032595
DO - 10.1023/A:1008930032595
M3 - Journal article
VL - 8
SP - 105
EP - 113
JO - Statistics and Computing
JF - Statistics and Computing
IS - 2
ER -