NMath Stats Changelog

------------------------------------------------------------------------------
 Version 3.2.0 
------------------------------------------------------------------------------
- Upgraded to Intel MKL 10.2 Update 5 with resulting performance increases.
- Added classes InputVariableCorrelator and ReducedVarianceInputCorrelator
  to induce a desired rank correlation among a set of random input variables. 
- Added class KruskalWallisTest for performing a Kruskal-Wallis rank sum test. 
- Added class JohnsonDistribution to encapsulate the Johnson system of
  distributions.
- Added classes GoodnessOfFit and GoodnessOfFitParameter for testing the
  goodness of fit of least squares model-fitting classes, such as
  LinearRegression, PolynomialLeastSquares, and OneVariableFunctionFitter.
- Added class BoxCox for computing the Box-Cox power tranformations.
- Added StatsFunction.Median() for float types.
- Fixed issue where StatsFunctions.SumOfSquares() could occasionally return a
  negative value.
- Improved support for missing values in DataFrame.Load().


------------------------------------------------------------------------------
 Version 3.1.0 
------------------------------------------------------------------------------
- Upgraded to Intel MKL 10.2 Update 1.
- Added class KMeansClustering for k-means clustering. The k-means clustering
  method assigns data points into k groups such that the sum of squares from
  points to the computed cluster centers is minimized. 
- Added class MovingWindowFilter for 1D data filtering. Static class methods
  are provided for generating coefficients to implement a moving average
  filter and a Savitzky-Golay smoothing filter. 
- Added method Cronbach() to class StatsFunctions for calculating the
  standardized Cronbach's alpha test for reliability. 
- Added class NMFNonsmoothUpdate, an NMF update algorithm that minimizes a
  cost functional designed to explicitly represent sparseness, in the form
  of non-smoothness.


------------------------------------------------------------------------------
 Version 3.0.0 
------------------------------------------------------------------------------
- Upgraded to Intel MKL 10.1 Update 2.
- Added class NMFClustering for performing data clustering using iterative
  nonnegative matrix factorization (NMF). 
- Added class NMFConsensusMatrix for computing a consensus matrix from among
  multiple NMF clusterings. 
- Added classes ConnectivityMatrix and OrderedConnectivityMatrix for
  representing connectivity matrices.
- Changed abbreviation for nonnegative matrix factorization from NNMF to NMF in
  all class and method names.   
- Added single precision support for principle component analysis. Renamed class
  PrincipleComponentAnalysis to DoublePCA, and added FloatPCA.  
- Fixed bug in LinearRegression where default IRegressionCalculation was not
  thread-safe.
- Prevented duplicate column name in DataFrame. Duplicate names are now
  automatically suffixed with "_1", "_2",...,"_n".
- Added new overloads for StatsFunction.CovarianceMatrix() for FloatMatrix and
  StatsFunction.Covariance() for FloatVector.
- Added custom visualizer for DataFrame.
- Organized classes into solution folders inside Visual Studio.
- Added VS 2008 solutions for all examples and source editions.
- Added Add(System.Object) method to all types which implement IEnumerable.