Compounds | |
class | RazorBack::Anova1_ |
class | RazorBack::Anova1_::Group_ |
This class implements an observation group. More... | |
class | RazorBack::Distrapprox_ |
class | RazorBack::Distrapprox_::Bin_ |
A Bin_ object represents the i:th histogram bin. More... | |
class | RazorBack::Distrbase_ |
Distrbase_: an abstract base class for univariate continuous distributions. More... | |
class | RazorBack::Distrfunc_ |
Distrfunc_: function object abstract base class that implements a univariate PDF with an arbitrary number of parameters. More... | |
class | RazorBack::Uniform_ |
Uniform_: implements the uniform distribution in a range. More... | |
class | RazorBack::Gaussian_ |
Gaussian_: implements the Normal distribution. More... | |
class | RazorBack::Linls_ |
Linls_: Class for carrying out linear least-squares using the SVD. More... | |
class | RazorBack::Linreg_ |
Class Linreg_: class for linear regression. More... | |
class | RazorBack::Mvn_ |
Mvn_: a class representing multivariate Normal distributions. More... | |
class | RazorBack::Nonlinfunc_ |
Class Nonlinfunc_: this is an abstract base class for function objects that can be used by the Nonlinreg_ class. More... | |
class | RazorBack::Nonlinreg_ |
Class Nonlinreg_: this class implements a general-purpose multivariate weighted nonlinear regression with Marquardt's method. More... | |
class | RazorBack::Orthpoly_ |
This class implements parameter estimation using orthogonal polynomials. More... | |
class | RazorBack::Paramest_ |
Class Paramest_: base class for parameter estimation. More... | |
class | RazorBack::Randombase_ |
Randombase_: random number generator abstract base class. More... | |
class | RazorBack::Randomuni_ |
Randomuni_: generates uniform random numbers. More... | |
class | RazorBack::Randomnorm_ |
Randomnorm_: random number generator class that produces normally distributed random numbers. More... | |
class | RazorBack::Splstorage_ |
Splstorage_: this is a helper class that stores the data needed by the Spl_ class. More... | |
class | RazorBack::Spl_ |
Class Spl_ : implements third-order splines. More... | |
struct | RazorBack::Spl_::Datapoint_ |
class | RazorBack::Stat_ |
Class Stat_: one-variable statistics. More... | |
class | RazorBack::Stat2_ |
Class Stat2_: Two-variable simple statistics class. More... | |
class | RazorBack::Toofewexc_ |
Class Toofewexc_: an exception object that stores an unsigned integer and can be thrown if there was not enough data available. More... | |
class | RazorBack::Sdevexc_ |
Class Sdevexc_: an exception object that stores an invalid standard deviation value (usually <=0.0). More... | |
class | RazorBack::Forgottenexc_ |
class | RazorBack::Statprob_ |
Functions | |
unsigned int | std_data (vector< double > &X, double &Mean, double &Sd) |
std_data(X, Mean, Sd): standardizes the data vector X by calculating the mean and SD, and then subtracting the mean from each entry and divide the centralised value by the SD. More... | |
double | correl_data (const vector< double > &X, const vector< double > &Y) |
correl_data(X, Y): calculates the correlation coefficient between the data vectors X and Y. More... | |
int | calc_loadings (const Symmat_< double > &Correl, Rectmat_< double > &Load, double Tol, double *Qual=NULL) |
calc_loadings(Correl, Load, Tol, Qual): decomposes the correlation matrix Correl so that the loadings will be returned in Load. More... |
|
std_data(X, Mean, Sd): standardizes the data vector X by calculating the mean and SD, and then subtracting the mean from each entry and divide the centralised value by the SD. Returns the original mean in Mean, the SD in Sd. Return value: the no. of entries converted or 0 on error. |
|
correl_data(X, Y): calculates the correlation coefficient between the data vectors X and Y. X and Y are assumed to have been standardised by std_data() before the call. Return value: the correlation coefficient (-1..+1). |
|
calc_loadings(Correl, Load, Tol, Qual): decomposes the correlation matrix Correl so that the loadings will be returned in Load. Return value: the number of factors which belong to eigenvalues higher than Tol times the largest eigenvalue. If Qual!=NULL, then a quality coefficient is returned in *Qual. |