Skip to content

zmerino/NAP

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

79 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Non-parametric Adaptive Parition (NAP) Density Estimation

The NAP estimator adaptively paritions a sample of univariant data, finds PDF estimates for all of the paritioned samples, and stitches the estiamtes together using a data driven method. The NAP estimator was developed for applications to large datasets with varying distributions in the data, as well as, applications to distributions that are notoriously difficult to estimate.

This method leverages a density estimator previously developed by Jenny Farmer and Donald Jacobs which is often refered to as Non-parametric Maximum Entropy Method Density Esitmation. The C++ code was compiled into MEX and published on Mathworks for applications in MATLAB.

NOTE: The NAP estimator is theoretically capable of using other methods of PDF estimation to find estiamtes for each parition. Kernal Density Estimation was previously shown to be compatible and produce similiar results.

Installation Notes

  • Required packages: Parallel Toolbox, Statistics and Machine Learning Toolbox.
  • place /functions and /cpp_code directories inside desired project folder.

Version

  • version 1.0 - February 2023

Contributors

Affiliations

  • University of North Carolina at Charlotte, NC, USA
  • University of Waterloo, ON, Canada

About

Code for Nonparametric Stitcing Estimator publication

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors