### Re: FAVAR add-in

Posted:

**Wed Jun 07, 2017 8:24 am**Dakila - Thank you for the useful add-in. Is there a way to apply the scaled IRF add-in to the FAVAR add-in?

Page **2** of **7**

Posted: **Wed Jun 07, 2017 8:24 am**

Dakila - Thank you for the useful add-in. Is there a way to apply the scaled IRF add-in to the FAVAR add-in?

Posted: **Wed Jun 07, 2017 4:35 pm**

Good idea. I will try to code it.

Posted: **Fri Jun 09, 2017 7:02 am**

Thank you, Dakila. Is there a possibility of running cumulative IRFs in your add-in?

Posted: **Fri Jun 09, 2017 5:54 pm**

Yes, It actually do the cumulative IRFs when you transform the variable. For example, if you put the transformation code 4 or 5 it will accumulate the IRFs.

Posted: **Fri Jun 09, 2017 8:08 pm**

Ahh, ok. Thanks.

Posted: **Thu Jun 22, 2017 6:09 pm**

Hi,

I tried to get the factors by the usual way of principal components, but I didnĀ“t have the same series. Also I can see that the final factors used in VAR have "rot" in its labels. Does it have any other treatment, or could you please tell me the way to get it? Thanks!

I tried to get the factors by the usual way of principal components, but I didnĀ“t have the same series. Also I can see that the final factors used in VAR have "rot" in its labels. Does it have any other treatment, or could you please tell me the way to get it? Thanks!

Posted: **Fri Jun 23, 2017 2:29 am**

"ROT" means the rotated factors. In order to estimate the factors do the following steps:

1) estimate factors (C) using all variables except FFR (you did this step)

2) estimate slow moving factors (Fs) from the slow moving variables.

3) estimate the regression by OLS : C=b1*Fs + b2*FFR + e

4) estimate the rotated factors : C-b2*FFR

1) estimate factors (C) using all variables except FFR (you did this step)

2) estimate slow moving factors (Fs) from the slow moving variables.

3) estimate the regression by OLS : C=b1*Fs + b2*FFR + e

4) estimate the rotated factors : C-b2*FFR

Posted: **Mon Jun 26, 2017 6:05 pm**

Thank you! I got them but with a very small difference. Maybe that's because I didn't standardize my variables (since all of them were stationaries), do you think thats made the difference?

Posted: **Mon Jun 26, 2017 7:19 pm**

Yes, I think that made the difference.

Posted: **Fri Jun 30, 2017 7:29 am**

Hello, I want to apply FAVAR on eviews but I found difficulties in entering variables on the dialog box, please can you help me?

Thanks a lot.

Thanks a lot.

Posted: **Fri Jun 30, 2017 4:44 pm**

Did you read the instruction which is located in C:\Users\...\Documents\EViews Addins\FAVAR (Favar Package.pdf)?

Posted: **Sat Jul 01, 2017 2:53 pm**

Yes but I still have problems!

Could you explain how to enter variables polease.

Thanks a lot.

Could you explain how to enter variables polease.

Thanks a lot.

Posted: **Sat Jul 01, 2017 4:09 pm**

there is an example program which replicates BBE (2005)

After running this code, fill the boxes. (Please see the attachment)

Code: Select all

`' BBE (2005) replicaton`

' Figure 2

' Table 1

%path = @runpath

cd %path

' open the BBE data that is transformed to induce stationarity

wfopen(type=txt) nsbalpanel.txt delim=space

pagestruct(freq=m,start=1959)

'rename some variables

for !i=1 to 9

rename series0{!i} series{!i}

next

'standardize all variables for principal component analsyis

for !i=1 to 120

series{!i}=(series{!i} - @mean(series{!i}))/@stdevp(series{!i})

next

'Y variables

genr ffr=series77

'All variables (X) except Y variable (FFR)

group xdata

for !i=1 to 120

xdata.add series{!i}

next

xdata.drop series77

' Slow-moving variables

group xslow

for !i=1 to 53

xslow.add series{!i}

next

for !i=103 to 119

xslow.add series{!i}

next

' Selection of key variables for impulse response analysis

group xir

xir.add series16 series108 series78 series81 series96 series93 series74 series102 series17 series49 series50 series51 series26 series48 series118 series54 series62 series71 series120

'Vector of transformation code of Y (ffr) variable + selection of key variables (xir)

'1 for no transformation

'4 for logarithm

'5 for first difference of logarithm

vector tcode =@fill(1, 5, 5, 1, 1, 5, 5, 5, 1, 1, 5, 5, 5, 1, 1, 5, 4, 1, 1, 1)

'Name of Y variables Y(ffr) + selected key variables (xir)

' Please first put a name of Y variable then selected variables

text yx_name

yx_name.append(file) yxirlabel.txt

' or append manually

' yx_name.append FFR

' yx_name.append IP

' yx_name.append CPI

'......

' yx_name.append Consumer Expectation

'favar(factor=3,horizon=48,rep=1000,ci=0.9,vd=1,save=1) 13 xdata xslow xir tcode yx_name @ ffr

After running this code, fill the boxes. (Please see the attachment)

Posted: **Wed Jul 05, 2017 12:06 pm**

Hi,

i have this ERROR message when i run the program : MATRIX SIZE MISMATCH

please can you help me ?

THANK you !!

i have this ERROR message when i run the program : MATRIX SIZE MISMATCH

please can you help me ?

THANK you !!

Posted: **Wed Jul 05, 2017 6:24 pm**

if you have missing value, change the sample size.