fractalBlock: Class constructor for block-dependent estimators for...

Description Usage Arguments S3 METHODS See Also Examples

Description

Class constructor for fractalBlock.

Usage

1
2
3
fractalBlock(domain,estimator, exponent, exponent.name,
    scale, stat, stat.name, detrend, overlap,
    data.name, sum.order, series, logfit, sdf=NULL)

Arguments

domain

character string defining the domain in which the calculations took place, e.g., in the time or frequency domain.

estimator

character string briefly describing the estimator.

exponent

numerical value representing the scaling exponent.

exponent.name

character string defining the name of the scaling exponent.

scale

numeric vector containing the scales used in the analysis.

stat

numeric vector containing the statistic calculated in the analysis.

stat.name

character vector describing the name for the calculated statistic.

detrend

character string describing any series detrending used as a preprocessive measure. NULL values are allowed and signify no detrending.

overlap

numeric value on [0,1] defining the fraction of overlap used in adjacent blocks of data during the aggregation process.

data.name

character string defining the name of the input series.

sum.order

integer representing the sum order.

series

a numeric vector containing the input series.

logfit

a linear regression model (such as that output by lm, lmsreg, or ltsreg) containing the regression model of the log(scale) versus log(stat) data.

sdf

spectral density function. Default: NULL.

S3 METHODS

eda.plot

extended data analyis plot of the data. Available options are:

cex

character expansion ala par. Default: 1.

col

line color index ala par. Default: 2.

plot

plots a summary of the results. Available options are:

pch

plot character ala par. Default: 18.

col

color index ala par for a plot of the data. the first two elements are used to color the data and the regression line, respectively. Default: c(1,8).

lty

line types (ala par) for the data and regression line plot, respectively. Default: c(1,1).

grid

list of grid objects whose default values are grid=list(lty=2, col=16, density=3), key=TRUE, add=FALSE, cex=1, ...).

...

Additional plot arguments (set internally by the par function).

print

prints the object. Available options are:

justify

text justification ala prettPrintList. Default: "left".

sep

header separator ala prettyPrintList. Default: ":".

n.digits

number of digits ala prettyPrintList. Default: 5.

...

Additional print arguments sent directly to the prettyPrintList function).

See Also

hurstBlock, DFA.

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
## construct a fractalBlock object 
xvar <- 2^(1:10)
yvar <- 0.3^(1:10)
z <- fractalBlock(domain="time", estimator="estimator", exponent=pi, exponent.name="PI",
    scale=xvar, stat=yvar, stat.name="My Stat",
    detrend=NULL, overlap=0.2, data.name="My Series",
    sum.order=-1, series=rnorm(2^10),
    logfit=lm(y ~ x, data=data.frame(x=log(xvar), y=log(yvar))))

## print the result 
print(z)

## plot the result 
plot(z)

Example output

Loading required package: splus2R
Loading required package: ifultools
Estimator for My Series
-----------------------
PI estimate            : 3.141593 
Domain                 : Time 
Statistic              : My Stat 
Length of series       : 1024 
Block overlap fraction : 0.2 
Scale ratio            : 2 
Preprocessing          : 1st order difference 
                                                                               
Scale   2.0 4.00 8.000 16.0000 32.00000 6.40e+01 1.280e+02 2.560e+02 5.1200e+02
My Stat 0.3 0.09 0.027  0.0081  0.00243 7.29e-04 2.187e-04 6.561e-05 1.9683e-05
                  
Scale   1.0240e+03
My Stat 5.9049e-06

fractal documentation built on May 1, 2019, 8:04 p.m.