Density function, distribution function, quantile function, random generation,
raw moments and limited moments for the Transformed Beta distribution
with parameters shape1
, shape2
, shape3
and
scale
.
dtrbeta(x, shape1, shape2, shape3, rate = 1, scale = 1/rate,
log = FALSE)
ptrbeta(q, shape1, shape2, shape3, rate = 1, scale = 1/rate,
lower.tail = TRUE, log.p = FALSE)
qtrbeta(p, shape1, shape2, shape3, rate = 1, scale = 1/rate,
lower.tail = TRUE, log.p = FALSE)
rtrbeta(n, shape1, shape2, shape3, rate = 1, scale = 1/rate)
mtrbeta(order, shape1, shape2, shape3, rate = 1, scale = 1/rate)
levtrbeta(limit, shape1, shape2, shape3, rate = 1, scale = 1/rate,
order = 1)
dtrbeta
gives the density,
ptrbeta
gives the distribution function,
qtrbeta
gives the quantile function,
rtrbeta
generates random deviates,
mtrbeta
gives the \(k\)th raw moment, and
levtrbeta
gives the \(k\)th moment of the limited loss
variable.
Invalid arguments will result in return value NaN
, with a warning.
vector of quantiles.
vector of probabilities.
number of observations. If length(n) > 1
, the length is
taken to be the number required.
parameters. Must be strictly positive.
an alternative way to specify the scale.
logical; if TRUE
, probabilities/densities
\(p\) are returned as \(\log(p)\).
logical; if TRUE
(default), probabilities are
\(P[X \le x]\), otherwise, \(P[X > x]\).
order of the moment.
limit of the loss variable.
Vincent Goulet vincent.goulet@act.ulaval.ca and Mathieu Pigeon
The transformed beta distribution with parameters shape1
\(=
\alpha\), shape2
\(= \gamma\), shape3
\(= \tau\) and scale
\(= \theta\), has
density:
$$f(x) = \frac{\Gamma(\alpha + \tau)}{\Gamma(\alpha)\Gamma(\tau)}
\frac{\gamma (x/\theta)^{\gamma \tau}}{%
x [1 + (x/\theta)^\gamma]^{\alpha + \tau}}$$
for \(x > 0\), \(\alpha > 0\), \(\gamma > 0\),
\(\tau > 0\) and \(\theta > 0\).
(Here \(\Gamma(\alpha)\) is the function implemented
by R's gamma()
and defined in its help.)
The transformed beta is the distribution of the random variable $$\theta \left(\frac{X}{1 - X}\right)^{1/\gamma},$$ where \(X\) has a beta distribution with parameters \(\tau\) and \(\alpha\).
The transformed beta distribution defines a family of distributions with the following special cases:
A Burr distribution when shape3 == 1
;
A loglogistic distribution when shape1
== shape3 == 1
;
A paralogistic distribution when
shape3 == 1
and shape2 == shape1
;
A generalized Pareto distribution when
shape2 == 1
;
A Pareto distribution when shape2 ==
shape3 == 1
;
An inverse Burr distribution when
shape1 == 1
;
An inverse Pareto distribution when
shape2 == shape1 == 1
;
An inverse paralogistic distribution
when shape1 == 1
and shape3 == shape2
.
The \(k\)th raw moment of the random variable \(X\) is \(E[X^k]\), \(-\tau\gamma < k < \alpha\gamma\).
The \(k\)th limited moment at some limit \(d\) is \(E[\min(X, d)^k]\), \(k > -\tau\gamma\) and \(\alpha - k/\gamma\) not a negative integer.
Kleiber, C. and Kotz, S. (2003), Statistical Size Distributions in Economics and Actuarial Sciences, Wiley.
Klugman, S. A., Panjer, H. H. and Willmot, G. E. (2012), Loss Models, From Data to Decisions, Fourth Edition, Wiley.
dfpareto
for an equivalent distribution with a location
parameter.
exp(dtrbeta(2, 2, 3, 4, 5, log = TRUE))
p <- (1:10)/10
ptrbeta(qtrbeta(p, 2, 3, 4, 5), 2, 3, 4, 5)
qpearson6(0.3, 2, 3, 4, 5, lower.tail = FALSE)
## variance
mtrbeta(2, 2, 3, 4, 5) - mtrbeta(1, 2, 3, 4, 5)^2
## case with shape1 - order/shape2 > 0
levtrbeta(10, 2, 3, 4, scale = 1, order = 2)
## case with shape1 - order/shape2 < 0
levtrbeta(10, 1/3, 0.75, 4, scale = 0.5, order = 2)
Run the code above in your browser using DataLab