Specification testing for Markov switching model

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

fr4014
Posts: 8
Joined: Fri Apr 29, 2022 1:50 pm

Specification testing for Markov switching model

Postby fr4014 » Mon Jan 16, 2023 4:46 pm

Ideally, one would like to test the null hypothesis that m 5m and s 5 s . The implication of finding this would be that the Markov switching model had been unable to separate out the data into two distinct regimes; in other words, that it is possible to restrict the data to be
as drawn from only one regime. Unfortunately, as Engel and Hamilton (1990) point out, the derivative of the likelihood function with respect to mu 1 and mu 2 is zero, and the information matrix is singular under the null so that the usual regularity conditions for the asymptotic validity of the hypothesis tests do not hold. Engel and Hamilton (1990) suggest testing this hypothesis indirectly by considering the following two slightly more general hypotheses

rest of the description is attached in the image 1

Test results reported by author is attached in image 2 and his interpretation is reported in image 3.

I would like to know how to find the W1 and W2 values that he reported in table after the estimation of markov switching model.
Attachments
ev3.PNG
Interpretation of specification test
ev3.PNG (36.54 KiB) Viewed 6784 times
eviews2.PNG
Test result by author
eviews2.PNG (47.08 KiB) Viewed 6784 times
eviews1.PNG
Description about the test
eviews1.PNG (77.17 KiB) Viewed 6784 times

Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 12 guests