Name
Abstract | ||
|---|---|---|
Given angular data @q"1,...,@q"n@?[0,2@p) a common objective is to estimate the density. In case that a kernel estimator is used, bandwidth selection is crucial to the performance. A ''plug-in rule'' for the bandwidth, which is based on the concentration of a reference density, namely, the von Mises distribution is obtained. It is seen that this is equivalent to the usual Euclidean plug-in rule in the case where the concentration becomes large. In case that the concentration parameter is unknown, alternative methods are explored which are intended to be robust to departures from the reference density. Simulations indicate that ''wrapped estimators'' can perform well in this context. The methods are applied to a real bivariate dataset concerning protein structure. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1016/j.csda.2007.11.003 | Computational Statistics & Data Analysis |
Keywords | Field | DocType |
ramachandran plot,kernel estimator,smoothing parameter selection.,protein structure,bandwidth selection,von mises distri- bution,automatic bandwidth selection,kernel density estimators,angular data,common objective,circular density estimation,angle data,usual euclidean plug-in rule,reference density,concentration parameter,plug-in rule,alternative method,kernel density estimate,density estimation,von mises distribution | Kernel (linear algebra),Density estimation,Econometrics,von Mises distribution,Bandwidth (signal processing),Concentration parameter,Kernel method,Statistics,Mathematics,Estimator,Kernel density estimation | Journal |
Volume | Issue | ISSN |
52 | 7 | Computational Statistics and Data Analysis |
Citations | PageRank | References |
7 | 0.83 | 0 |
Authors | ||
1 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Charles C. Taylor | 1 | 18 | 4.29 |