source: trunk/src/RegressionNaive.h @ 213

// $Id: RegressionNaive.h 213 2004-11-04 19:58:08Z peter $

#ifndef _theplu_statistics_regression_linear_
#define _theplu_statistics_regression_linear_

// C++ tools include
/////////////////////
#include "Averager.h"
#include "Regression.h"
#include "vector.h"
#include "WeightedAverager.h"
// Standard C++ includes
////////////////////////
#include <gsl/gsl_fit.h>

namespace theplu {
namespace statistics {  
  
  ///
  /// Class for Regression.   
  ///

  
  class RegressionNaive : public Regression 
  {
  
  public:
    ///
    /// Default Constructor.
    ///
    RegressionNaive(void);

    ///
    /// Copy Constructor. (not implemented)
    ///
    RegressionNaive(const RegressionNaive&);

    ///
    /// Destructor 
    ///
    virtual ~RegressionNaive(void) {};
         
    ///
    /// This function computes the best-fit for the naive model \f$
    /// y = m \f$ from vectors \a x and \a y, by minimizing \f$
    /// \sum{(y_i-m)^2} \f$.
    ///
    inline int fit(const gslapi::vector& x, const gslapi::vector& y)
    {
      Averager a;
      for (size_t i=0; i<y.size(); i++)
        a.add(y(i));
      m_=a.mean();
      var_=a.standard_error()*a.standard_error(); 
      return 0;
    }

    ///
    /// This function computes the best-fit for the naive model \f$ y
    /// = m \f$ from vectors \a x and \a y, by minimizing \f$ \sum
    /// w_i(y_i-m)^2 \f$. The weight \f$ w_i \f$ is the inverse of the
    /// variance for \f$ y_i \f$
    ///
    inline int fit_weighted(const gslapi::vector& x,
                            const gslapi::vector& y,
                            const gslapi::vector& w)
    {
      WeightedAverager a;
      for (size_t i=0; i<y.size(); i++)
        a.add(y(i), w(i));
      m_=a.mean();
      var_=a.standard_error()*a.standard_error(); 
      return 0;
    }

         
  private:
    double var_;
    double m_;

  };

}} // of namespace statistics and namespace theplu

#endif