ARCH test

Description

Computes the Lagrange multiplier test for conditional heteroscedasticity of Engle (1982), as described by Tsay (2005, pp. 101-102).

Usage

ArchTest(x, lags = 12, demean = FALSE)

Arguments

Examples

reg<-nardl(food~inf,fod,ic="aic",maxlag = 4,graph = TRUE,case=3)
x<-reg$selresidu
nlag<-reg$nl
ArchTest(x,lags=nlag)

LM test for serial correlation

Description

LM test for serial correlation

Usage

bp2(object, nlags, fill = NULL, type = c("F", "Chi2"))

Arguments

Examples

reg<-nardl(food~inf,fod,ic="aic",maxlag = 4,graph = TRUE,case=3)
lm2<-bp2(reg$fits,reg$nl,fill=0,type="F")

Function cumsq

Description

Function cumsq

Usage

cumsq(e, k, n)

Arguments

Examples

reg<-nardl(food~inf,fod,ic="aic",maxlag = 4,graph = TRUE,case=3)
e<-reg$rece
k<-reg$k
n<-reg$n
cumsq(e=e,k=k,n=n)

Function cusum

Description

Function cusum

Usage

cusum(e, k, n)

Arguments

Examples

reg<-nardl(food~inf,fod,ic="aic",maxlag = 4,graph = TRUE,case=3)
e<-reg$rece
k<-reg$k
n<-reg$n
cusum(e=e,k=k,n=n)

Indian yearly data of inflation rate and percentage food import to total import

Description

The data frame fod contains the following variables:

• food: percentage food import to total import

• inf: inflation rate

• year: the year

Usage

data(fod)

Format

A data frame with 54 rows and 2 variables

Nonlinear ARDL function

Description

Nonlinear ARDL function

Usage

nardl(formula, data, ic = c("aic", "bic"), maxlag = 4, graph = FALSE, case = 3)

Arguments

Examples

############################################
# Fit the nonlinear cointegrating autoregressive distributed lag model
############################################
# Load data
data(fod)
############################################
# example 1:auto selected lags (maxlags=TRUE)
############################################
reg<-nardl(food~inf,fod,ic="aic",maxlag = 4,graph = FALSE,case=3)
summary(reg)

############################################
# example 2: Cusum and CusumQ plot (graph=TRUE)
############################################
reg<-nardl(food~inf,fod,ic="aic",maxlag = 4,graph = TRUE,case=3)

pssbounds

Description

display the necessary critical values to conduct the Pesaran, Shin and Smith 2001 bounds test for cointegration. See http://andyphilips.github.io/pssbounds/.

Usage

pssbounds(obs, fstat, tstat = NULL, case, k)

Arguments

Details

pssbounds is a module to display the necessary critical values to conduct the Pesaran, Shin and Smith (2001) bounds test for cointegration. Critical values using the F-test are the default; users can also include the critical values of the t-test with the tstat parameter.

As discussed in Philips (2016), the upper and lower bounds of the cointegration test are non-standard, and depend on the number of observations, the number of regressors appearing in levels, and the restrictions (if any) placed on the intercept and trend. Asymptotic critical values are provided by Pesaran, Shin, and Smith (2001), and small-sample critical values by Narayan (2005). The following five cases are possible: I (no intercept, no trend), II (restricted intercept, no trend), III (unrestricted intercept, no trend), IV (unrestricted intercept, restricted trend), V (unrestricted intercept, unrestricted trend). See Pesaran, Shin and Smith (2001) for more details; Case III is the most common.

More details are available at http://andyphilips.github.io/pssbounds/.

Value

None

Author(s)

Soren Jordan, sorenjordanpols@gmail.com

Andrew Q Philips, aphilips@pols.tamu.edu

References

If you use pssbounds, please cite:

Jordan, Soren and Andrew Q. Philips. "pss: Perform bounds test for cointegration and perform dynamic simulations."

and

Philips, Andrew Q. "Have your cake and eat it too? Cointegration and dynamic inference from autoregressive distributed lag models" Working Paper.

Narayan, Paresh Kumar. 2005. "The Saving and Investment Nexus for China: Evidence from Cointegration Tests." Applied Economics 37(17):1979-1990.

Pesaran, M Hashem, Yongcheol Shin and Richard J Smith. 2001. "Bounds testing approaches to the analysis of level relationships." Journal of Applied Econometrics 16(3):289-326.

Examples

reg<-nardl(food~inf,fod,ic="aic",maxlag = 4,graph = TRUE,case=3)
pssbounds(case=reg$case,fstat=reg$fstat,obs=reg$Nobs,k=reg$k)
# F-stat concludes I(1) and cointegrating, t-stat concludes I(0).

Summary of a nardl model

Description

summary method for a nardl model.

Usage

## S3 method for class 'nardl'
summary(object, ...)

Arguments

Value

an object of the S3 class summary.nardl with the following components: