Nonlinear nonparametric statistics using partial moments. Partial moments are the elements of variance and asymptotically approximate the area of f(x). These robust statistics provide the basis for nonlinear analysis while retaining linear equivalences.
NNS offers:
- Numerical Integration & Numerical Differentiation
- Partitional & Hierarchial Clustering
- Nonlinear Correlation & Dependence
- Causal Analysis
- Nonlinear Regression & Classification
- ANOVA
- Seasonality & Autoregressive Modeling
- Normalization
- Stochastic Dominance
See the following for NNS detailed examples and specific applications:
1.1 Partial Moment Equivalences
1.2 Bayes' Theorem
1.3 CDFs and ANOVA
1.4 Bias and Confidence Intervals
1.5 Correlation and Dependence
1.6 Correlation and Dependence (paper)
1.8 Beyond Correlation: Using the Elements of Variance for Conditional Means and Probabilities
1.9 Normalization
2.1 Overview
2.2 Curve Fitting
2.3 Nonparametric Regression Using Clusters
2.4 Clustering and Curve Fitting By Line Segments
2.6 Logistic Regression Binary Classification
2.7 Boston Housing
3.1 Partitional Estimation Using Partial Moments
3.2 NNS Regression in Machine Learning
3.3 Classification Using NNS Clustering Analysis
3.4 NNS vs. xgboost
3.5 Time-Series Classification
3.6 Time-Series Classification II
3.8 MNIST
4.1 Overview
4.2 NNS vs. KERAS
4.3 NNS vs. prophet
4.4 Tides
4.5 Nile
5.1 Econometrics Critiques and Solutions
5.2 VAR Alternative
5.3 NOWCASTING
5.4 Causal Analysis
5.5 Federal Reserve Causal Analysis
The previous examples are just that...examples. They are not meant to serve as proofs or intended to be exhaustive demonstrations, rather the hands-on application of a robust nonparametetric regression in many different types of common machine learning problems.
See the papers available on SSRN, if you'd like to learn why & how NNS does what it does.