|
factor |
factor performs a Factor Analysis for x (principal
component, principal axes). For each method you can
interactively between two different criteria for the
factors. At the end you get a draftman plot of the
the chosen factors.
|
|
factorial |
Computes the factorial for all values
in an array.
|
|
FARcov |
Procedure for the calculation of the covariance function
of a fractional ARIMA(0,d,0) model, uses the Fast Fourier
Transform
|
|
FARgk |
Calculation of the gk for Simulation of fractional
ARIMA(0,d,0) with FARx
|
|
FARx |
Simulation of a series of fractional ARIMA(0,d,0) by a
method proposed by Davies and Harte
|
|
fastint |
fastint estimates the additive components and their
derivatives of an additive model using a modification
of the integration estimator plus a one step backfit,
see Kim, Linton and Hengartner (1997) and Linton (1996)
|
|
FBMx |
Calculation of a series of fractional Brownian motion,
after a method proposed by Davies and Harte
|
|
fft |
fft computes the Fast Fourier Transformation of a complex vector.
|
|
fgenci |
auxiliary quantlet for cointegration
|
|
FGNchol |
Simulation of a series standard fractional Brownian
Motion by the exact cholesky decomposition
|
|
FGNcov |
Calculation of the aotocovariance function of fractional
Gaussian noise
|
|
FGNgk |
Calculation of a series gk for the calculation of
fractional Gaussian noise by a method proposed by Davies
and Harte
|
|
FGNx |
Simulation of a series of fractional Gaussian noise (not
standard fractional Gaussian noise) by a method proposed
by Davies and Harte
|
|
filltime |
generates vector of time points starting from t with length n and
granulation gran (default month). The difference between two timepoints
is given by step.
|
|
final |
Supporting Quantlet for cartsplit
|
|
finalshow |
shows the final visualization of the network
|
|
financemain |
loads the libraries needed for the macros in finance
|
|
financetest |
self test of extreme value module
|
|
fittail |
transforms location and scale parameter of GP
distribution from fit to exceedances to tail fit.
|
|
fivenum |
computes the five number summary consisting of the
minimum and maximum, the quartiles and the median.
|
|
flipaxes |
adds a menubutton th change the axes of a display
|
|
floatinf |
provides information about real numbers
within the interval [.5,0) in the form of
x=a*10^b, b is bounded by -20
|
|
floor |
floor gives the next smaller integer value of the elements of an array.
|
|
fncovci |
auxiliary quantlet for cointegration
|
|
fnrici |
auxiliary quantlet for cointegration
|
|
fnyzci |
auxiliary quantlet for cointegration
|
|
fnzzci |
auxiliary quantlet for cointegration
|
|
forec2 |
Forecasting in VAR Models with undifferencing
|
|
forecast |
Forecasting in VAR Models
|
|
fracbrown |
the result*normal(2*p*nu+1) gives a fractional brownian motion
with respect to alpha=2*H ( H = Hurst coefficent)
|
|
free |
free removes global objects. It is convenient to delete big objects which consume a lot of memory. If free is invoked without arguments all objects are deleted.
|
|
freecolor |
freecolor deallocates the colors that were allocated by user or by system.
|
|
frequencies |
provides frequency tables for the selected variables of
the data set
|
|
frequency |
provides frequency tables for all columns of a
matrix. An additional vector of name strings can
be given to identify columns by names.
|
|
func |
func loads files and executes them. If necessary the suffix xpl is appended.
|
|
fwt |
fwt computes the Fast Wavelet Transformation of a vector.
|
|
fwt2 |
The algorithm fwt2 is designed for 2 dimensional
wavelet transformation. It mainly corresponds to dwt
for the one dimensional case. If wished it works with the
tensor product of one dimensional wavelet transforms.
|
|
fwtin |
fwtin computes the Fast Wavelet Transformation of all circular
shifts of the vector x.
|
|
fwtinshift |
fwtinshift retrieves the wavelet coefficients for a given shift
of the Fast Wavelet Transformation of all circular shifts (fwtin)
of a vector.
|
|
fwttin |
Generates the translation invariant estimate of x with
automatic hardthresholding.
It is well-known that nonlinear wavelet estimators are not
translation-invariant: if we shift the underlying data set
by a small amount, apply nonlinear thresholding and shift
the estimator back, then we usually obtain an estimator
different from the estimator without the shifting and
backshifting operation.
To get rid of this, we average over several estimators
obtained by shifting, nonlinear thresholding and
backshifting.
|