unit roots with structural breaks

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

cindirella
Posts: 1
Joined: Thu Jun 29, 2017 8:01 am

unit roots with structural breaks

Postby cindirella » Thu Jun 29, 2017 9:28 am

HI,
I'm a new user of Eviews, so sorry if I can seem banal in my question.
I have quarterly series and I want to test unit roots in presence of structural breaks.
I've performed the zivov andrews test and now I'd like to check for unit roots with multiple breaks.
I've used these two types of tests t to check the presence of multiple breaks...

1)Multiple breakpoint tests
Bai-Perron tests of 1 to M globally determined breaks
Date: 06/29/17 Time: 18:08
Sample: 3/01/1987 3/01/2017
Included observations: 121
Breaking variables: C
Break test options: Trimming 0.15, Max. breaks 5, Sig. level 0.05
Allow heterogeneous error distributions across breaks

Sequential F-statistic determined breaks: 5
Significant F-statistic largest breaks: 5
UDmax determined breaks: 2
WDmax determined breaks: 5

Scaled Weighted Critical
Breaks F-statistic F-statistic F-statistic Value

1 * 141.9388 141.9388 141.9388 8.58
2 * 309.2700 309.2700 367.5258 7.22
3 * 239.8462 239.8462 345.2820 5.96
4 * 205.1993 205.1993 352.8277 4.99
5 * 194.3048 194.3048 426.3772 3.91

UDMax statistic* 309.2700 UDMax critical value** 8.88
WDMax statistic* 426.3772 WDMax critical value** 9.91

* Significant at the 0.05 level.
** Bai-Perron (Econometric Journal, 2003) critical values.

Estimated break dates:
1: 9/01/1993
2: 12/01/1993, 9/01/2008
3: 12/01/1993, 6/01/2008, 12/01/2012
4: 12/01/1993, 12/01/2003, 6/01/2008, 12/01/2012
5: 9/01/1993, 3/01/1998, 12/01/2003, 6/01/2008, 12/01/2012

2)
Multiple breakpoint tests
Bai-Perron tests of L+1 vs. L sequentially determined breaks
Date: 06/29/17 Time: 18:23
Sample: 3/01/1987 3/01/2017
Included observations: 121
Breaking variables: C
Break test options: Trimming 0.15, Max. breaks 5, Sig. level 0.05
Allow heterogeneous error distributions across breaks

Sequential F-statistic determined breaks: 3

Scaled Critical
Break Test F-statistic F-statistic Value**

0 vs. 1 * 141.9388 141.9388 8.58
1 vs. 2 * 44.69843 44.69843 10.13
2 vs. 3 * 21.16285 21.16285 11.14
3 vs. 4 5.381268 5.381268 11.83

* Significant at the 0.05 level.
** Bai-Perron (Econometric Journal, 2003) critical values.

Break dates:
Sequential Repartition
1 9/01/1993 12/01/1993
2 9/01/2008 12/01/2003
3 12/01/2003 6/01/2008

IF I'm not wrong, clearly it emerges, the presence of stuctural change.. so.. my question is.. IS THERE ANY TEST, IN EVIEWS, WHICH ALLOW ME SAY THAT MY SERIES IS STATIONARY GIVEN THAT THERE ARE STRUCTURAL BREAKS??
THANKS IN ADVANCE

EViews Glenn
EViews Developer
Posts: 2530
Joined: Wed Oct 15, 2008 9:17 am

Re: unit roots with structural breaks

Postby EViews Glenn » Thu Jul 06, 2017 9:48 am

EViews offers breakpoint unit root tests that will perform a variety of tests for unit roots allowing for breaks.


Return to “Econometric Discussions”

Who is online

Users browsing this forum: No registered users and 2 guests