fitdistrplus (version 1.0-8)

qmedist: Quantile matching fit of univariate distributions

Description

Fit of univariate distribution by matching quantiles for non censored data.

Usage

qmedist(data, distr, probs, start = NULL, fix.arg = NULL, qtype = 7,  optim.method = "default", lower = -Inf, upper = Inf,  custom.optim = NULL, weights = NULL, silent = TRUE, gradient = NULL, ...)

Arguments

data

A numeric vector for non censored data.

distr

A character string "name" naming a distribution for which the corresponding quantile function qname and the corresponding density distribution dname must be classically defined.

probs

A numeric vector of the probabilities for which the quantile matching is done. The length of this vector must be equal to the number of parameters to estimate.

start

A named list giving the initial values of parameters of the named distribution or a function of data computing initial values and returning a named list. This argument may be omitted (default) for some distributions for which reasonable starting values are computed (see the 'details' section of mledist).

fix.arg

An optional named list giving the values of fixed parameters of the named distribution or a function of data computing (fixed) parameter values and returning a named list. Parameters with fixed value are thus NOT estimated.

qtype

The quantile type used by the R quantile function to compute the empirical quantiles, (default 7 corresponds to the default quantile method in R).

optim.method

"default" or optimization method to pass to optim.

lower

Left bounds on the parameters for the "L-BFGS-B" method (see optim).

upper

Right bounds on the parameters for the "L-BFGS-B" method (see optim).

custom.optim

a function carrying the optimization.

weights

an optional vector of weights to be used in the fitting process. Should be NULL or a numeric vector with strictly positive integers (typically the number of occurences of each observation). If non-NULL, weighted QME is used, otherwise ordinary QME.

silent

A logical to remove or show warnings when bootstraping.

gradient

A function to return the gradient of the squared difference for the "BFGS", "CG" and "L-BFGS-B" methods. If it is NULL, a finite-difference approximation will be used, see details.

...

further arguments passed to the optim, constrOptim or custom.optim function.

Value

qmedist returns a list with following components,

Details

The qmedist function carries out the quantile matching numerically, by minimization of the sum of squared differences between observed and theoretical quantiles. Note that for discrete distribution, the sum of squared differences is a step function and consequently, the optimum is not unique, see the FAQ. The optimization process is the same as mledist, see the 'details' section of that function. Optionally, a vector of weights can be used in the fitting process. By default (when weigths=NULL), ordinary QME is carried out, otherwise the specified weights are used to compute weighted quantiles used in the squared differences. Weigthed quantiles are computed by wtd.quantile from the Hmisc package. It is not yet possible to take into account weighths in functions plotdist, plotdistcens, plot.fitdist, plot.fitdistcens, cdfcomp, cdfcompcens, denscomp, ppcomp, qqcomp, gofstat and descdist (developments planned in the future).

This function is not intended to be called directly but is internally called in fitdist and bootdist.

References

Klugman SA, Panjer HH and Willmot GE (2012), Loss Models: From Data to Decissions, 4th edition. Wiley Series in Statistics for Finance, Business and Economics, p. 253.

Delignette-Muller ML and Dutang C (2015), fitdistrplus: An R Package for Fitting Distributions. Journal of Statistical Software, 64(4), 1-34.

See Also

mmedist, mledist, mgedist, fitdist for other estimation methods and quantile for empirical quantile estimation in R.

Examples

# (1) basic fit of a normal distribution 
#

set.seed(1234)
x1 <- rnorm(n=100)
qmedist(x1, "norm", probs=c(1/3, 2/3))


# (2) defining your own distribution functions, here for the Gumbel 
# distribution for other distributions, see the CRAN task view dedicated 
# to probability distributions

dgumbel <- function(x, a, b) 1/b*exp((a-x)/b)*exp(-exp((a-x)/b))
qgumbel <- function(p, a, b) a - b*log(-log(p))
qmedist(x1, "gumbel", probs=c(1/3, 2/3), start=list(a=10,b=5))

# (3) fit a discrete distribution (Poisson)
#

set.seed(1234)
x2 <- rpois(n=30,lambda = 2)
qmedist(x2, "pois", probs=1/2)

# (4) fit a finite-support distribution (beta)
#

set.seed(1234)
x3 <- rbeta(n=100,shape1=5, shape2=10)
qmedist(x3, "beta", probs=c(1/3, 2/3))

# (5) fit frequency distributions on USArrests dataset.
#

x4 <- USArrests$Assault
qmedist(x4, "pois", probs=1/2)
qmedist(x4, "nbinom", probs=c(1/3, 2/3))