Updated 19 Sep 2018
A MATLAB toolbox 'bsspdfest' implementing nonparametric probability function estimation using normalized B-splines was developed. The toolbox implements nonparametric probability function estimation procedures for one or more dimensions using a B-spline series for one-dimensional data and a tensor product B-spline series for multi-dimensional data. The toolbox takes advantage of the direct addressing of MATLAB arrays up to three dimensions and various vectorization approaches to speed up the computations. For data dimensions greater than three indirect addressing is used, converting multi-dimensional indices into linear array addressing, making this function slower.
The toolbox supports the computation of the PDF, CDF, and survivor functions for data of all dimensions as well as the inverse CDF (ICDF) and cumulative hazard functions for one dimensional data. The toolbox also supports the creation and use of gridded interpolants to provide very fast approximate evaluation of the B-spline series or tensor product series for the probability functions. Bounded domains are also now supported for all dimensions.
Version 2.3.1 of the bsspdfest toolbox has just been released! This version now uses reflection for active boundaries on bounded or semi-infinite domains and also supports bounded domains for data of all dimensions. A variety of performance improvements have also been made.
Kevin Gehringer (2020). bsspdfest (https://www.mathworks.com/matlabcentral/fileexchange/49121-bsspdfest), MATLAB Central File Exchange. Retrieved .
Thanks for the comment!
My preferred citation is based on the users manual:
Kevin R. Gehringer, bsspdfest: A MATLAB toolbox for nonparametric probability function estimation using normalized B-splines, 2018, Software Version 2.3.1, Biometrics Northwest LLC, Redmond, WA, USA, https://www.biometricsnw.com/projects/bssest/bssest.htm.
This fits into a BibTex MANUAL with the addition of the HowPublished field for the URL and using the Edition field for the software version.
The "References" section at the end of the user's manual contains the citations for the original work: Gehringer 1990, Gehringer and Redner 1992, Redner 1999, and Redner 2000.
Sorry about providing the information this way. It was not possible to add a custom citation via the "Cite As: section to File Exchange without changing the version number for the software and I did not want to change the version number.
Extremely fast and from I can see very accurate. I was wondering if there is a specific way I can cite this (i.e. in a scientific paper)?
Fixed a typo that was not caught in other testing for some reason. Should
Now uses reflection for active boundaries on bounded or semi-infinite domains and also supports bounded domains for data of all dimensions. A variety of performance improvements have also been made.
Added support for bounded and semi-infinite domains. Fixed several bugs. See the User's Guide or the file changes.txt for details.
Fixed several bugs, consolidated input checking for the PDF estimation functions, removed the 3-d visualization movies to reduce the package size.
Fixed several errors in the User's Guide. Added a new test script that does not depend on the Statistics and Machine Learning Toolbox. The addition of the new test script and supporting functions is why the version number changed.
Fixed a typo in the description
Version 2.0.0 includes significant performance improvements, support for computing PDF, CDF, and survivor functions as well as the inverse CDF and cumulative hazard functions in one dimension.
Fixed an issue with the license file.