dcomper_mv {dsfa}

R Documentation

Multivariate Composed-Error distribution

Description

Probablitiy density function, distribution, quantile function and random number generation for the multivariate composed-error distribution

Usage

dcomper_mv(
  x,
  mu = matrix(c(0, 0), ncol = 2),
  sigma_v = matrix(c(1, 1), ncol = 2),
  sigma_u = matrix(c(1, 1), ncol = 2),
  delta = matrix(0, nrow = 1),
  s = c(-1, -1),
  distr = c("normhnorm", "normhnorm", "normal"),
  rot = 0,
  deriv_order = 0,
  tri = NULL,
  log.p = FALSE
)

pcomper_mv(
  q,
  mu = matrix(c(0, 0), ncol = 2),
  sigma_v = matrix(c(1, 1), ncol = 2),
  sigma_u = matrix(c(1, 1), ncol = 2),
  delta = 0,
  s = c(-1, -1),
  distr = c("normhnorm", "normhnorm", "normal"),
  rot = 0,
  deriv_order = 0,
  tri = NULL,
  log.p = FALSE
)

rcomper_mv(
  n,
  mu = matrix(c(0, 0), ncol = 2),
  sigma_v = matrix(c(1, 1), ncol = 2),
  sigma_u = matrix(c(1, 1), ncol = 2),
  delta = matrix(0, nrow = 1),
  s = c(-1, -1),
  distr = c("normhnorm", "normhnorm", "normal"),
  rot = 0
)

Arguments

x	numeric matrix of quantiles. Must have two columns.
mu	numeric matrix of \mu. Must have two columns.
sigma_v	numeric matrix of \sigma_V. Must be positive. Must have two columns.
sigma_u	numeric matrix of \sigma_U. Must be positive. Must have two columns.
delta	numeric vector of copula parameter \delta.
s	integer vector of length two; each element corresponds to one marginal.
distr	string vector of length three; the first two elements determine the distribution of the marginals. Available are: normhnorm, Normal-halfnormal distribution normexp, Normal-exponential distribution The last element determines the distribution of the copula: independent, Independence copula normal, Gaussian copula clayton, Clayton copula gumbel, Gumbel copula frank, Frank copula joe, Joe copula amh, Ali-Mikhail-Haq copula
rot	integer determining the rotation for Archimedian copulas. Can be 90, 180 or 270.
deriv_order	integer; maximum order of derivative. Available are 0,2 and 4.
tri	optional; List of objects generated by trind_generator().
log.p	logical; if TRUE, probabilities p are given as log(p).
q	numeric matrix of probabilities.
n	positive integer; number of observations.

Details

A bivariate random vector (X_1,X_2)=X follows a composed error multivariate distribution f_{X_1,X_2}(x_1,x_2), which can be rewritten using Sklars' theorem via a copula

f_{X_1,X_2}(y_1,y_2)=c(F_{X_1}(x_1),F_{X_2}(x_2),\delta) \cdot f_{X_1}(x_1) f_{X_2}(x_2) \qquad,

where c(\cdot) is a copula function and F_{X_m}(x_m),f_{X_m}(x_m) are the marginal cdf and pdf respectively. delta is the copula parameter.

Value

dcomper_mv gives the density, pcomper_mv give the distribution function, and rcomper_mv generates random numbers, with given parameters. If the derivatives are calculated the output is a deriv_mat object.

Functions

• pcomper_mv(): distribution function for the multivariate composed-error distribution.

• rcomper_mv(): random number generation for the multivariate composed-error distribution.

References

• Aigner D, Lovell CK, Schmidt P (1977). “Formulation and estimation of stochastic frontier production function models.” Journal of econometrics, 6(1), 21–37.

• Kumbhakar SC, Wang H, Horncastle AP (2015). A practitioner's guide to stochastic frontier analysis using Stata. Cambridge University Press.

• Schmidt R, Kneib T (2020). “Analytic expressions for the Cumulative Distribution Function of the Composed Error Term in Stochastic Frontier Analysis with Truncated Normal and Exponential Inefficiencies.” arXiv preprint arXiv:2006.03459.

• Gradshteyn IS, Ryzhik IM (2014). Table of integrals, series, and products. Academic press.

• Azzalini A (2013). The skew-normal and related families, volume 3. Cambridge University Press.

See Also

Other distribution: dcomper(), dnormexp(), dnormhnorm()

Examples

pdf <- dcomper_mv(x=matrix(c(0,10),ncol=2), mu=matrix(c(1,2),ncol=2),
                  sigma_v=matrix(c(3,4),ncol=2), sigma_u=matrix(c(5,6),ncol=2),
                  delta=c(0.5), s=c(-1,-1), distr=c("normhnorm","normhnorm","normal"),
                  deriv=2 ,
                  tri=list(trind_generator(3),trind_generator(3),trind_generator(1),
                  trind_generator(6),trind_generator(7)), 
                  log.p=TRUE)
cdf <- pcomper_mv(q=matrix(c(0,10),ncol=2), mu=matrix(c(1,2),ncol=2),
                  sigma_v=matrix(c(3,4),ncol=2), sigma_u=matrix(c(5,6),ncol=2),
                  delta=c(0.5), s=c(-1,-1), distr=c("normhnorm","normhnorm","normal"))
r <- rcomper_mv(n=10, mu=matrix(c(1,2),ncol=2),
                sigma_v=matrix(c(3,4),ncol=2), sigma_u=matrix(c(5,6),ncol=2),
                delta=c(0.5), s=c(-1,-1), distr=c("normhnorm","normhnorm","normal"))

---