credible intervals for the impulse response functions

[tiantian]

hello
I want to know whether the result in the impulse response functions are significant or not.So ,how could I get the credible intervals for the impulse response functions when using dynare?

Please help me.
Thank you very much in advance for the answers.
Best regards,
Tiantian.

[jpfeifer]

See http://www.dynare.org/phpBB3/viewtopic.php?f=1&t=4647

[tiantian]

Thanks for reply,would you please help again.
Yesterday ,I saw this paper http://www.price.e.u-tokyo.ac.jp/img/researchdata/pdf/p_wp018.pdf,it seems that the author got the credible intervals for the impulse response functions.It says that "In each panel, the solid thick line represents the true response, and the solid thin line and dashed lines are respectively the posterior mean and 90 percent credible interval for the estimated response."Please see page 11.

As a beginner,I can't figure this out.would you please spare a little more time?

Thank you for your time.
best regards,
tiantian.

[tiantian]

Following your advice,I have read the topic"Confidence Interval in IRF". Does it mean that it's not necessary to compute the credible intervals for the impulse response functions since there is not any parameter uncertainty.

Thanks again.
Best wishes.
Tiantian.

[jpfeifer]

The paper you refer to is estimated. Due to parameter uncertainty, the IRFs are also uncertain. If you calibrate your model, there is no uncertainty.

[tiantian]

OK,now I can understand it.

Thank you very much for the reply.

Best regards
Tiantian