FAVAR add-in

[dakila]

Yes, it is right. Use scale (1 or 0) and sn (scale number) command. For example,

Code: Select all

favar(factor=3,horizon=60,rep=1000,ci=0.9,vd=1, scale=1, sn=0.25) 13 xdata xslow xir tcode yx_name @ ffr

[heer0]

Yes, it is right. Use scale (1 or 0) and sn (scale number) command. For example,

Code: Select all

favar(factor=3,horizon=60,rep=1000,ci=0.9,vd=1, scale=1, sn=0.25) 13 xdata xslow xir tcode yx_name @ ffr

That's great thanks so much. Quick follow-up question: in your reply, you set the scaling factor to 0.25, which I suppose changes the magnitude of the one-period shock from one standard deviation of the impulse variable (e.g., ffr) to a 25 bps increase. Would I need to set sn equal to 0.25/std(ffr) if I estimated the FAVAR with non-standardized data?

I would also like to know if the "favar" command allows for the inclusion of a constant and a linear time trend as in the standard EViews command for estimating a VAR, i.e.

Code: Select all

favar(factor=3,horizon=60,rep=1000,ci=0.9,vd=1, scale=1, sn=0.25) 13 xdata xslow xir tcode yx_name c @trend @ ffr

Finally, I would like to know if the inclusion of the transformation codes in the "favar" command automatically backs out impulse responses for the "untransformed" variables. For example, we often tranform GDP by taking logs and then first differences such that GDP enters in growth rates rather than levels. Would the corresponding impulse response function from the "favar" command show the change in the level of GDP in USD in response to a monetary policy shock? Or would the impulse response function just accumulate the changes in the growth rates such that the Y-axis shows the relative change in GDP (i.e., %-change)?

Thanks so much for taking the time to answer all my questions!!

[dakila]

Would I need to set sn equal to 0.25/std(ffr) if I estimated the FAVAR with non-standardized data?

I think you need to set sn equal to 0.25/std(ffr) if you estimated the FAVAR with standardized data.

I would also like to know if the "favar" command allows for the inclusion of a constant and a linear time trend as in the standard EViews command for estimating a VAR, i.e.

No it does not allow a linear time trend. It automatically includes a constant.

Would the corresponding impulse response function from the "favar" command show the change in the level of GDP in USD in response to a monetary policy shock? Or would the impulse response function just accumulate the changes in the growth rates such that the Y-axis shows the relative change in GDP (i.e., %-change)?

% -change

[heer0]

Would I need to set sn equal to 0.25/std(ffr) if I estimated the FAVAR with non-standardized data?

I think you need to set sn equal to 0.25/std(ffr) if you estimated the FAVAR with standardized data.

I would also like to know if the "favar" command allows for the inclusion of a constant and a linear time trend as in the standard EViews command for estimating a VAR, i.e.

No it does not allow a linear time trend. It automatically includes a constant.

Would the corresponding impulse response function from the "favar" command show the change in the level of GDP in USD in response to a monetary policy shock? Or would the impulse response function just accumulate the changes in the growth rates such that the Y-axis shows the relative change in GDP (i.e., %-change)?

% -change

Thank you so much for your detailed response. Much appreciated!

[Fondel]

First of all, thank you for this Add-in, surely made my life easier!

I am new to eviews and considerably new to stats in general.

Few questions for which I couldnt find an answer in this thread:

1. Is it possible to forecast individual series used to build factors? (not just factors themselves)
2. Is it possible to draw factors from multiple datasets? Let's say I have sets X1 and X2 composed of different data series and I would like to use the first principal component of each (X1 and X2) in my FAVAR as factors?

Thanks

[dakila]

1. Is it possible to forecast individual series used to build factors? (not just factors themselves)

Yes . this question is answered before

Is it possible to draw factors from multiple datasets? Let's say I have sets X1 and X2 composed of different data series and I would like to use the first principal component of each (X1 and X2) in my FAVAR as factors?

No.

[dakila]

1. Is it possible to forecast individual series used to build factors? (not just factors themselves)

Yes . this question was answered before

Is it possible to draw factors from multiple datasets? Let's say I have sets X1 and X2 composed of different data series and I would like to use the first principal component of each (X1 and X2) in my FAVAR as factors?

No.

[Fondel]

1. Is it possible to forecast individual series used to build factors? (not just factors themselves)

Yes . this question was answered before

Is it possible to draw factors from multiple datasets? Let's say I have sets X1 and X2 composed of different data series and I would like to use the first principal component of each (X1 and X2) in my FAVAR as factors?

No.

Hello,

Thanks for your answers. I do find a relating question:

Thank you for your comments, dakila. I know we can see the forecasting variables on factors. Moreover, I would like to know the forecasting for the original variables (x variables from which we extract factors). I guess I have to know the details of the program in order to get the forecasting for every variables.

Maybe I am missing something here and we both were and are confused.

after the estimation you should use the following command:

Code: Select all

favar01.forecast(prompt)

then you should regress the forecasting variable on factors and ffr:

Code: Select all

eq01.ls series108 _facrot1 _facrot2 _facrot3 ffr eq01.forecast

Keep in the mind all variables are standardized (zero mean and unit variance).
Therefore you shoud transform your variable back to the non-standardized one.

You must be refering to this.

The command

Code: Select all

favar01.forecast(prompt)

returns "_facrot1_f, _facrot2_f and _facrot3_f"
In the "eq01.ls series108 _facrot1 _facrot2 _facrot3 ffr" am I supposed to replace _facrot1...2 with _facrot1_f.....3_f?
forecasting the least square model without introducing any output from the favar forecast done above seems counter intuitive.. Is it that the above forecast using the favar model is forecasting for the facotrs and below (the ls eq) is forecasting for variables themselves?

After forecasting I will unstandardize my results.

Sorry for my newb. questions!

Thank you.

[heer0]

Hi guys,

I have estimated a favar with the favar add-in in EViews 10 (Univ. ed.). Judging from my output (impulse response functions and variance decomposition) there seem to be a few issues:

1. I would need to incude ten factors according to the decision criteria by Bai and Ng (2002) but as soon as I estimate the favar with more than six factors, there is always an error message (which changes from time to time. Most often, it says there is a singularity problem)

2. Estimating the favar with six factors, my impulse response functions are all over the place and defy economic intuition (see attachment IRF_UNSCALED). Changing the number of factors does not change this problem.

3. When estimating the favar with more than one factor, the variance decomposition only gives me 'NA' values (see attachment VARIANCE_DECOM_UNSCALED and SCALED)

4. When estimating the favar with six factors and scaling the impulse response functions by sn = 0.25/@stdev(policy variable), the impulse response functions only return "NA" values (see attachment IRF_SCALED)

For further reference, I will include my workfile and the program I wrote to generate it.

I would be most grateful for any suggestions on how to solve these issues. Any help will be MUCH appreciated!

[FZLAGH]

Hi,

I'm trying to estimate a FAVAR model using this add-in and i wonder if it is possible to obtain impulse responses of “factors” to their orthogonalized innovations and then translate this response to other variables from which we get the factors.

Thank you

[heer0]

Hi,

I'm trying to estimate a FAVAR model using this add-in and i wonder if it is possible to obtain impulse responses of “factors” to their orthogonalized innovations and then translate this response to other variables from which we get the factors.

Thank you

This is exactly what the add-in is for. If you need an introduction, refer to the example file "favar_ex" that comes with the installation package for the add-in. This example file replicates the findings (e.g., impulse response graphs) of Bernanke, Boivin, and Eliasz (2005).

Hope it helps!

[FZLAGH]

Hi,

I'm trying to estimate a FAVAR model using this add-in and i wonder if it is possible to obtain impulse responses of “factors” to their orthogonalized innovations and then translate this response to other variables from which we get the factors.

Thank you

This is exactly what the add-in is for. If you need an introduction, refer to the example file "favar_ex" that comes with the installation package for the add-in. This example file replicates the findings (e.g., impulse response graphs) of Bernanke, Boivin, and Eliasz (2005).

Hope it helps!

Thanks for your request, but what i meen is that the Bernanke, Boivin, and Eliasz example looks for IRF to a monetary Policy shock. In my case i would like to have IRF to the orthogonnalized innovations of factors (shocks to factors).

[heer0]

Hi,

I'm trying to estimate a FAVAR model using this add-in and i wonder if it is possible to obtain impulse responses of “factors” to their orthogonalized innovations and then translate this response to other variables from which we get the factors.

Thank you

This is exactly what the add-in is for. If you need an introduction, refer to the example file "favar_ex" that comes with the installation package for the add-in. This example file replicates the findings (e.g., impulse response graphs) of Bernanke, Boivin, and Eliasz (2005).

Hope it helps!

Thanks for your request, but what i meen is that the Bernanke, Boivin, and Eliasz example looks for IRF to a monetary Policy shock. In my case i would like to have IRF to the orthogonnalized innovations of factors (shocks to factors).

Once you executed the FAVAR add-in as in the example file, the FAVAR model object will be saved to your workfile. Double click on it and go to "View" and "Impulse responses." This will allow you to derive impulse responses of the factors themselves rather than the time series from which the factors were constructed in the first place.

Alternatively, you may estimate a simple VAR in the factors (after rotation!) without the add-in. All up to you. Hope it helps.

[daisysunf18]

hi, I want to know,For example: In the case where SER01 does not exist in xir, a pulse image of Y to SER01 is made by macro-controlling the X-series variables.it can do in add-in? thanks in advance

[daisysunf18]

Hi，I am confuse the impulse variable (optional）what should I choose , I do not see it in favar.package. thanks in advance.