normfit {LambertW}R Documentation

Graphical and stastical Gaussianity check

Description

Performs a check whether data is Gaussian or not. Graphical and statistical inference.

Usage

normfit(data, volatility = FALSE, plot.it = TRUE)

Arguments

data data
volatility Should the squared data and its autocorrelation be plotted. Useful for financial data to see if squares exhibit dependence (typically they do for asset returns)
plot.it Should graphical inference be plotted (histogram, densities, qqplot, ...); default TRUE

Value

Three results of normality tests are returned (each of class htest)

ad Anderson Darling
sw Shapiro-Wilk
sf Shapiro-Francia

Author(s)

Georg M. Goerg

References

Goerg, G.M. (2009). “Lambert W Random Variables - A new class of skewed distribution functions”. Unpublished

Thode Jr., H.C. (2002): “Testing for Normality”. Marcel Dekker, New York.

Examples

y=rLambertW(200, theta=c(0.1, 0, 1))
normfit(y)

fit=IGMM(y)
summary(fit)

fitl=MLE_LambertW(y)
plot(fitl)
x.d=get.input(y, fitl$theta)$x

normfit(y)
x11()
normfit(x.d)

[Package LambertW version 0.1.6 Index]