R Graphical Manual

Browse All

Last data update: 2014.03.03

R: LM test of no Remaining ACD (Meitz and Terasvirta, 2006)

testRmACD

R Documentation

LM test of no Remaining ACD (Meitz and Terasvirta, 2006)

Description

Tests if there is any remaining ACD structure in the residuals

Usage

testRmACD(fitModel, pStar = 2, robust = TRUE)

Arguments

`fitModel`	a fitted ACD model, i.e. an object of class "acdFit".
`pStar`
`robust`	if `TRUE` the LM statistic will be calculated using the "robust" version, making its asymptotic behavior unaffected by possible misspecification of the error term distribution (Meitz and Terasvirta, 2006).

Details

For the model

the function tests the null hypothesis

Value

a list of:

`chi2`	the value of the LM statistic.
`pv`	the pvalue of the test statistic.

Author(s)

Markus Belfrage

References

Meitz, M. and Terasvirta, T. (2006). Evaluating models of autoregressive conditional duration. Journal of Business and Economic Statistics 24: 104-124.

Examples

fitModel3000obs <- acdFit(adjDurData[1:3000,])
testRmACD(fitModel3000obs, pStar = 2, robust = TRUE)

Results


R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> library(ACDm)
> png(filename="/home/ddbj/snapshot/RGM3/R_CC/result/ACDm/testRmACD.Rd_%03d_medium.png", width=480, height=480)
> ### Name: testRmACD
> ### Title: LM test of no Remaining ACD (Meitz and Terasvirta, 2006)
> ### Aliases: testRmACD
> 
> ### ** Examples
> 
> fitModel3000obs <- acdFit(adjDurData[1:3000,])

ACD model estimation by (Quasi) Maximum Likelihood 

Call:
  acdFit(durations = adjDurData[1:3000, ]) 

Model:
  ACD(1, 1)

Distribution:
  exponential

N: 3000

Parameter estimate:
         Coef     SE PV robustSE
omega  0.0533 0.0146  0   0.0150
alpha1 0.0763 0.0125  0   0.0120
beta1  0.8683 0.0247  0   0.0245


The fixed/unfree mean distribution parameter: 
 lambda: 1

QML robust correlations:
        omega alpha1  beta1
omega   1.000  0.558 -0.918
alpha1  0.558  1.000 -0.827
beta1  -0.918 -0.827  1.000


Goodness of fit:
                     value
LogLikelihood -2781.723131
AIC            5569.446263
BIC            5587.465365
MSE               1.355675

Convergence: 0 

Number of log-likelihood function evaluations: 212 

Estimation time: 0.0905 secs 

Description: Estimated at 2016-07-04 14:06:32 by user ddbj

> testRmACD(fitModel3000obs, pStar = 2, robust = TRUE)

M&T (2006) test of no remaining ACD in residuals (robust version): 
                           
LM-stat:             7.2931
Degrees of freedom:  2.0000
P-value:             0.0261
> 
> 
> 
> 
> 
> dev.off()
null device 
          1 
>