source: trunk/c++_tools/statistics/Pearson.h @ 623

#ifndef _theplu_statistics_pearson_
#define _theplu_statistics_pearson_ 

// $Id: Pearson.h 623 2006-09-05 02:13:12Z peter $

#include <c++_tools/statistics/Score.h>

namespace theplu {
namespace utility {
  class vector;
}
namespace classifier {
  class VectorAbstract;
}
namespace statistics {  

  ///
  /// Class for calculating Pearson correlation.
  ///   
  
  class Pearson : public Score
  {
  
  public:
    ///
    /// Default Constructor.
    ///
    Pearson(bool absolute=true);

    ///
    /// Destructor 
    ///
    virtual ~Pearson(void) {};
         
    
    ///
    /// \f$ \frac{\vert \sum_i(x_i-\bar{x})(y_i-\bar{y})\vert
    /// }{\sqrt{\sum_i (x_i-\bar{x})^2\sum_i (x_i-\bar{x})^2}} \f$.
    /// @return Pearson correlation, if absolute=true absolute value
    /// of Pearson is used.
    ///
    double score(const classifier::Target& target, 
                 const utility::vector& value);

    ///
    /// \f$ \frac{\vert \sum_iw^2_i(x_i-\bar{x})(y_i-\bar{y})\vert }
    /// {\sqrt{\sum_iw^2_i(x_i-\bar{x})^2\sum_iw^2_i(y_i-\bar{y})^2}}
    /// \f$, where \f$ m_x = \frac{\sum w_ix_i}{\sum w_i} \f$ and \f$
    /// m_x = \frac{\sum w_ix_i}{\sum w_i} \f$. This expression is
    /// chosen to get a correlation equal to unity when \a x and \a y
    /// are equal. @return absolute value of weighted version of
    /// Pearson correlation.
    ///
    double score(const classifier::Target& target, 
                 const classifier::DataLookupWeighted1D& value); 

    ///
    /// \f$ \frac{\vert \sum_iw^2_i(x_i-\bar{x})(y_i-\bar{y})\vert }
    /// {\sqrt{\sum_iw^2_i(x_i-\bar{x})^2\sum_iw^2_i(y_i-\bar{y})^2}}
    /// \f$, where \f$ m_x = \frac{\sum w_ix_i}{\sum w_i} \f$ and \f$
    /// m_x = \frac{\sum w_ix_i}{\sum w_i} \f$. This expression is
    /// chosen to get a correlation equal to unity when \a x and \a y
    /// are equal. @return absolute value of weighted version of
    /// Pearson correlation.
    ///
    double score(const classifier::Target& target, 
                 const utility::vector& value,
                 const utility::vector& weight); 

    ///
    /// The p-value is the probability of getting a correlation as
    /// large as the observed value by random chance, when the true
    /// correlation is zero (and the data is Gaussian). Note that this
    /// function can only be used together with the unweighted
    /// score. @return two-sided p-value
    ///
    double p_value() const;
         
  private:
    double r_;
    int nof_samples_;


    //    void centralize(utility::vector&, const utility::vector&);
  };

}} // of namespace statistics and namespace theplu

#endif