desk (version 1.1.2)

qlr.test: Quandt Likelihood Ratio-Test for Structural Breaks in any Parameter with Unknown Break Date

Description

Performs Quandt Likelihood Ratio-test (QLR) for structural breaks with unknown break date. The object returned by this command can be plotted using the plot() function.

Usage

qlr.test(mod, data = list(), from, to, sig.level = 0.05, details = FALSE)

Value

A list object including:

hyp	the null-hypothesis to be tested.
results	data frame of test results.
chi2.stats	chi^2-test statistics calculated between from and to.
f.stats	F-test statistics calculated between from and to.
f.crit	lower and upper critical F-value.
p.value	p-value in the test using approximation method proposed by Hansen (1997).
breakpoint	period at which largest F-value occurs.
periods	the range of periods analyzed.
lf.crit	lower and upper critical F-value including corresponding lambda values.
lambda	the lambda correction value for the critical value.

Arguments

mod

the regular model object (without dummies) estimated by ols() or lm().

data

name of the data frame to be used if mod is only a formula.

from

start period of range to be analyzed for a break.

to

end period of range to be analyzed for a break.

sig.level

significance level. Allowed values are 0.01, 0.05 or 0.10.

details

logical value indicating whether specific details about the test should be returned.

References

Quandt, R.E. (1960): Tests of the Hypothesis That a Linear Regression Obeys Two Separate Regimes. Journal of the American Statistical Association 55, 324–30.

Examples

unemp.est <- ols(unempl ~ gdp, data = data.unempl)
my.qlr <- qlr.test(unemp.est, from = 13, to = 17, details = TRUE)
my.qlr # Print test results

plot(my.qlr) # Plot test results