aciigt {ig}R Documentation

Approximate confidence region for the parameters of the IGTD

Description

The function aciigt() produces a plot of an approximate confidence region and computes approximate confidence intervals (ACI) for the parameters mu and lambda of the IGTD from a sample of observations.

Usage

  aciigt(x, kernel = "normal", confLevel = 95, 
         chart = c(NULL, NULL, NULL, NULL), 
         colourRegion = 1,
         colourEstimates = 2)

Arguments

x Vector of observations.
kernel Kernel of the pdf of the associated symmetrical distribution by means of which the IGTD is obtained. The kernels: "laplace", "logistic", "normal" and "t" are available.
confLevel Confidence level of the region.
chart Vector of limits of the graphs. It is a vector of the type:
c(xmin, xmax, ymin, ymax).
colourRegion Color of an approximate confidence region in the plot.
colourEstimates Color of MLE estimators in the plot.

Details

In order to construct a confidence region for μ and λ, we use the asymptotic normality of the MLEs.

Value

aciigt() shows a plot of an approximate confidence region and computes approximate confidence intervals (ACI) for the parameters of the IGTD considering the established confidence level from a sample of observatons giving results according to the following list:

muEstimate Return the value of the MLE of mu.
muAci Return 95% ACI for mu.
lambdaEstimate Return the value of the MLE of lambda.
lambdaAci Return 95% ACI for lambda.

Author(s)

Víctor Leiva <victor.leiva@uv.cl; victor.leiva@yahoo.com>,
Hugo Hernández <hugo.hernandez.p@gmail.com> and
Antonio Sanhueza <asanhueza@ufro.cl>.

References

Sanhueza, A., Leiva, V., Balakrishnan, N. (2008). A new class of inverse Gaussian type distributions. Metrika (in press).

Examples

## Generates a sample from the IGTD with normal kernel
x <- rigt(300, mu = 1.0, lambda = 1.0, kernel = "normal")

## Estimates the parameters of the IGTD with normal kernel by means of a 
## 95
## region
aciigt(x, kernel = "normal", confLevel = 95, colourRegion = 3)

[Package ig version 1.2 Index]