NMath Stats is a .NET statistics library containing classes for data manipulation, statistical computation, and biostatistics. Product features include:
* A data Frame class for holding data of various types (numeric, string, boolean, datetime, and generic), with methods for appending, inserting, removing, sorting, and permuting rows and columns.
* Functions for computing descriptive statistics, such as mean, variance, standard deviation, percentile, median, quartiles, Geometric mean, harmonic mean, RMS, kurtosis, skewness, and many more.
* Special functions, such as Factorial, log factorial, binomial coefficient, log binomial, log gamma, incomplete gamma, beta, and incomplete beta.
* Probability density function (PDF), cumulative distribution function (CDF), inverse CDF, and random variable moments for a variety of probability distributions, including beta, binomial, chi-square, exponential, F, gamma, geometric, logistic, log-normal, negative binomial, normal (Gaussian), Poisson, Student's t, triangular, and Weibull distributions.
* Multiple linear regression.
* Basic hypothesis tests, such as z test, t-test, and F-test, with calculation of p-values, critical values, and confidence intervals.
* One-way and two-way analysis of variance (ANOVA) and analysis of variance with repeated measures (RANOVA).
* Multivariate statistical analyses, including principal component analysis, hierarchical Cluster analysis, and k-means cluster analysis.
* Nonnegative Matrix factorization (NMF), and data clustering using NMF.
* Partial least squares (PLS), including cross validation and the SIMPLS and NIPALS algorithms.
* Data filtering, including a moving average filter and a Savitzky-Golay smoothing filter.