[R-pkgs] Versions 0.50-1 of the np and npRmpi packages released - new features and deprecated options…

Jeffrey Racine racinej at mcmaster.ca
Thu Mar 14 20:29:39 CET 2013

Dear useRs,

We are pleased to announce that versions 0.50-1 of the np package and its MPI-aware counterpart, the npRmpi package, are now available on CRAN:


In these versions we add new functionality:

- new methods for multivariate mixed-data bandwidth selection for unconditional and conditional CDF bandwidth selection (`npudistbw' and `npcdistbw') using Li, Lin, and Racine (2013) and Li and Racine (2013)
- a new function for multivariate mixed-data copula and copula density functions (`npcopula') that exploits Li and Racine (2013)


With these new methods we have deprecated the use of `cdf=TRUE' for density and conditional bandwidth objects (i.e. those generated with `npudensbw' and `npcdensbw') and decoupled this functionality into `npudensbw'/`npudistbw' and `npcdensbw'/`npcdistbw' (previously bandwidths optimal for PDFs were used for CDFs given the lack of methods for mixed-data CDF bandwidth selection).

Bug fixes:

In addition we have corrected a number of bugs reported by users (see the CHANGELOG below)



Li, Q. and J. Lin and J.S. Racine (2013), “Optimal Bandwidth Selection for Nonparametric Conditional Distribution and Quantile Functions”, Journal of Business and Economic Statistics, 31, 57-65.

Li, H. and J.S. Racine (2013), “Cross-validated estimation of cumulative distribution functions with categorical and continuous data,” manuscript.

Kindly see my webpage below for further information and the `Gallery of Code' for a variety of illustrative examples.

-- Jeff & Tristen (co-authors of np/npRmpi)

Professor J. S. Racine         Phone:  (905) 525 9140 x 23825
Department of Economics        FAX:    (905) 521-8232
McMaster University            e-mail: racinej at mcmaster.ca
1280 Main St. W.,Hamilton,     URL: www.economics.mcmaster.ca/racine
Ontario, Canada. L8S 4M4

`The generation of random numbers is too important to be left to chance'

More information about the R-packages mailing list