Breakpoint unit root test with unknown break date
Posted: Tue Jun 07, 2016 7:41 am
The Eviews Guide II (page 543) states the following: "If the break date is estimated, the test statistics considered here do not permit a breaking
trend under the null."
But when I ran the test with breaking trend (break selection: minimize Dickey-Fuller t-statistic) I did get the results which state the null as unit root (see below). Are these results incorrect, or is the Guide outdated? Please help. Thanks. :?
Null Hypothesis: LOGX4 has a unit root
Trend Specification: Trend and intercept
Break Specification: Trend only
Break Type: Innovational outlier
Break Date: 717
Break Selection: Minimize Dickey-Fuller t-statistic
Lag Length: 1 (Automatic - based on Schwarz information criterion,
maxlag=10)
t-Statistic Prob.*
Augmented Dickey-Fuller test statistic -4.593005 0.0424
Test critical values: 1% level -5.067425
5% level -4.524826
10% level -4.261048
*Vogelsang (1993) asymptotic one-sided p-values.
trend under the null."
But when I ran the test with breaking trend (break selection: minimize Dickey-Fuller t-statistic) I did get the results which state the null as unit root (see below). Are these results incorrect, or is the Guide outdated? Please help. Thanks. :?
Null Hypothesis: LOGX4 has a unit root
Trend Specification: Trend and intercept
Break Specification: Trend only
Break Type: Innovational outlier
Break Date: 717
Break Selection: Minimize Dickey-Fuller t-statistic
Lag Length: 1 (Automatic - based on Schwarz information criterion,
maxlag=10)
t-Statistic Prob.*
Augmented Dickey-Fuller test statistic -4.593005 0.0424
Test critical values: 1% level -5.067425
5% level -4.524826
10% level -4.261048
*Vogelsang (1993) asymptotic one-sided p-values.