Classification Using NNS Clustering Analysis
22 Pages Posted: 6 Nov 2016 Last revised: 21 Oct 2019
Date Written: August 4, 2019
NNS stands for Nonlinear Nonparametric Statistics, henceforth "NNS". What is NNS clustering analysis? NNS clustering is a method of partitioning the joint distribution into partial moment quadrants (clustering), and assigning identifiers to observations (classification). NNS clustering is very similar to k-means clustering, and we direct the reader to Vinod and Viole  for a proof and comparison between the methods. This article is intended to present working examples of several classification problems using NNS clustering analysis.
We demonstrate how NNS clustering is quite effective, as well as an alternative method NNS employs for classification tasks. We compare predictions of test sets with NNS, k-means using the "cl.predict" routine offered in R to "predict class ids or memberships from R objects representing partitions", K nearest neighbors classification using the "knn" routine in R-package "class", and a naive Bayes classification using the "e1071" package.
The methods and results presented immediately raise suspicions on the pervasive notion of dimension reduction given the consistent performance of the NNS Multivariate Regression.
Keywords: clustering, classification, text classification, k-means, knn, naive Bayes, partial moments
JEL Classification: C3, C38
Suggested Citation: Suggested Citation