Chang and Serletis (2015)

If you are seeking RATS code for implementing a particular technique or replicating results from a paper, post your request here. Be sure to include complete citations for any papers or books.
TomDoan
Posts: 7814
Joined: Wed Nov 01, 2006 4:36 pm

Re: Chang and Serletis (2015)

Unread post by TomDoan »

za2015 wrote:Hi Tom,

How can I adjust the code to show the 95% confidence intervals in the series?

Thank you for your time,
Add the option PERCENTILES=||.025,.975|| to the @MCGRAPHIRF call.
TomDoan
Posts: 7814
Joined: Wed Nov 01, 2006 4:36 pm

Re: Chang and Serletis (2015)

Unread post by TomDoan »

za2015 wrote:I have another question, Tom:
Is there a way I can add a square on the graph that shows the significance at the 5% level, as in the attached graph?

Thank you,
What determines what gets a square or not? The standard methods for highlighting an entry are LINES and SHADING options.
za2015
Posts: 14
Joined: Thu Oct 08, 2015 9:05 am

Re: Chang and Serletis (2015)

Unread post by za2015 »

Hi Tom,

Is it correct like this:

Code: Select all

@mcgraphirf(model=basevar,include=||2||,center=median,PERCENTILES=||.025,.975||,$
  shocklabels=||"Positive Oil Shock","Negative Oil Shock"||)
thank you,
za2015
Posts: 14
Joined: Thu Oct 08, 2015 9:05 am

Re: Chang and Serletis (2015)

Unread post by za2015 »

Hi Tom,

It is easier to see the difference between responses to positive and to negative shocks. So, I want to plot the irf for positive and the negative of the irf for a negative shock on one graph. Therefore, if I add the bands as lines the figure will look very crowded.
za2015
Posts: 14
Joined: Thu Oct 08, 2015 9:05 am

Re: Chang and Serletis (2015)

Unread post by za2015 »

Hi Tom,

does the @mcgraphirf by default do the 16, 84%-ile bands. i.e. in the below code if I don't include PERCENTILES=||.025,.975||, it will automatically does the 16- and 84%-ile?

@mcgraphirf(model=basevar,include=||2||,center=median,PERCENTILES=||.025,.975||,$
shocklabels=||"Positive Oil Shock","Negative Oil Shock"||)



thank you,
Post Reply