source: trunk/c++_tools/statistics/tScore.h @ 675

#ifndef _theplu_statistics_tscore_
#define _theplu_statistics_tscore_ 

// $Id: tScore.h 675 2006-10-10 12:08:45Z jari $

/*
  Copyright (C) The authors contributing to this file.

  This file is part of the yat library, http://lev.thep.lu.se/trac/yat

  The yat library is free software; you can redistribute it and/or
  modify it under the terms of the GNU General Public License as
  published by the Free Software Foundation; either version 2 of the
  License, or (at your option) any later version.

  The yat library is distributed in the hope that it will be useful,
  but WITHOUT ANY WARRANTY; without even the implied warranty of
  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  General Public License for more details.

  You should have received a copy of the GNU General Public License
  along with this program; if not, write to the Free Software
  Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
  02111-1307, USA.
*/

#include "yat/statistics/Score.h"

#include <gsl/gsl_cdf.h>


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

  ///
  /// Class for Fisher's t-test.
  ///   
  /// See <a href="http://en.wikipedia.org/wiki/Student's_t-test">
  /// http://en.wikipedia.org/wiki/Student's_t-test</a> for more
  /// details on the t-test.
  /// 
  class tScore : public Score
  {
  
  public:
    ///
    /// Default Constructor.
    ///
    tScore(bool absolute=true);

    
    /**
       Calculates the value of t-score, i.e. the ratio between
       difference in mean and standard deviation of this
       difference. \f$ t = \frac{ m_x - m_y }
       {s\sqrt{\frac{1}{n_x}+\frac{1}{n_y}}} \f$ where \f$ m \f$ is the
       mean, \f$ n \f$ is the number of data points and \f$ s^2 =
       \frac{ \sum_i (x_i-m_x)^2 + \sum_i (y_i-m_y)^2 }{ n_x + n_y -
       2 } \f$
       
       @return t-score. If absolute=true absolute value of t-score
       is returned
    */
    double score(const classifier::Target& target, 
                 const utility::vector& value); 

    /**
       Calculates the weighted t-score, i.e. the ratio between
       difference in mean and standard deviation of this
       difference. \f$ t = \frac{ m_x - m_y }{
       s\sqrt{\frac{1}{n_x}+\frac{1}{n_y}}} \f$ where \f$ m \f$ is the
       weighted mean, n is the weighted version of number of data
       points \f$ \frac{\left(\sum w_i\right)^2}{\sum w_i^2} \f$, and
       \f$ s^2 \f$ is an estimation of the variance \f$ s^2 = \frac{
       \sum_i w_i(x_i-m_x)^2 + \sum_i w_i(y_i-m_y)^2 }{ n_x + n_y - 2
       } \f$. See AveragerWeighted for details.
       
       @return t-score. If absolute=true absolute value of t-score
       is returned
    */
    double score(const classifier::Target& target, 
                 const classifier::DataLookupWeighted1D& value); 

    ///
    /// Calculates the weighted t-score, i.e. the ratio between
    /// difference in mean and standard deviation of this
    /// difference. \f$ t = \frac{ m_x - m_y }{
    /// \frac{s2}{n_x}+\frac{s2}{n_y}} \f$ where \f$ m \f$ is the
    /// weighted mean, n is the weighted version of number of data
    /// points and \f$ s2 \f$ is an estimation of the variance \f$ s^2
    /// = \frac{ \sum_i w_i(x_i-m_x)^2 + \sum_i w_i(y_i-m_y)^2 }{ n_x
    /// + n_y - 2 } \f$. See AveragerWeighted for details.
    ///
    /// @return t-score if absolute=true absolute value of t-score
    /// is returned
    ///
    double score(const classifier::Target& target, 
                 const utility::vector& value, 
                 const utility::vector& weight); 

    ///
    /// Calculates the p-value, i.e. the probability of observing a
    /// t-score equally or larger if the null hypothesis is true. If P
    /// is near zero, this casts doubt on this hypothesis. The null
    /// hypothesis is that the means of the two distributions are
    /// equal. Assumtions for this test is that the two distributions
    /// are normal distributions with equal variance. The latter
    /// assumtion is dropped in Welch's t-test. 
    ///
    /// @return the one-sided p-value( if absolute=true is used
    /// the two-sided p-value)
    ///
    double p_value() const;

         
         
  private:
    double t_;
    double dof_;
        
  };

}} // of namespace statistics and namespace theplu

#endif