Detailed Description

A class to perform non-linear least square fitting. It works on a time serie and uses matrix arithmetic to perform an arbitrary fit (see http://mathworld.wolfram.com/NonlinearLeastSquaresFitting.html).

Public Member Functions
	FitLeastSquare ()

void	setData (const std::vector< double > &in_X, const std::vector< double > &in_Y)

bool	fit ()

virtual double	f (const double &x) const =0

Public Member Functions inherited from mio::FitModel
	FitModel ()

virtual	~FitModel ()

void	setGuess (const std::vector< double > &lambda_in)

virtual void	setLapseRate (const double &)

void	getParams (std::vector< double > &o_coefficients) const

std::string	getName () const

std::string	getInfo () const

void	setInfo (const std::string &info)

FitModel &	operator= (const FitModel &source)

std::string	toString () const

Protected Member Functions
virtual void	setDefaultGuess ()

Protected Member Functions inherited from mio::FitModel
virtual bool	checkInputs ()

Additional Inherited Members
Protected Attributes inherited from mio::FitModel
std::vector< double >	Lambda

std::vector< double >	X

std::vector< double >	Y

std::string	infoString

std::string	regname

size_t	nPts

size_t	nParam

size_t	min_nb_pts

bool	fit_ready