SkTDist {skewt} | R Documentation |
Density, distribution function, quantile function and random
generation for the skewed t distribution, as introduced by Fernandez and
Steel, with df
degrees of freedom.
dskt(x, df, gamma = 1)
pskt(x, df, gamma = 1)
qskt(p, df, gamma)
rskt(n, df, gamma)
x |
vector of quantiles. |
p |
vector of probabilities. |
n |
number of observations. If |
df |
degrees of freedom ( |
gamma |
skewing parameter, |
The Skewed t
distribution with df
= \nu
degrees of
freedom has the following density, where f(x)
is the density of the
t
distribution, with = \nu
degrees of
freedom :
f(x) = \frac{2}{\gamma + \frac{1}{\gamma}} f(\gamma x) \quad for
\quad x<0
and
f(x) = \frac{2}{\gamma + \frac{1}{\gamma}} f(\frac{x}{\gamma}) \quad
for \quad x \ge 0
dskt
gives the density,
pskt
gives the distribution function,
qskt
gives the quantile function, and
rskt
generates random deviates.
Fernandez, C. and Steel, M. F. J. (1998). On Bayesian modeling of fat tails and skewness, J. Am. Statist. Assoc. 93, 359–371.
Rohr, P. and Hoeschele, I. (2002).
Bayesian QTL mapping using skewed Student-t
distributions,
Genet. Sel. Evol. 34, 1–21.
df
for the F distribution.
dskt(0.5,2)
dskt(0.01,2,2)
pskt(1.25,2,2)
pskt(c(0.5,1.25),3)
qskt(c(0,0.025,0.25,0.5,0.75,0.975,1),2,2)
rskt(100,2,2)
plot(function(x)dskt(x,2,2),-3,3,n=301)