↧
Excel Add-in
↧
Asymmetric dynamic multiplier
↧
↧
estimate fiscal multiplier with time series data.
Hi,
I'm Ruwan who wish to estimate fiscal multiplier for Sri Lanka for my master thesis. I am going to follow BP model with expenditure,revenue and GDP variables. But I have only 1990 - 2017 annual data set. So is it possible to estimate using this data set?
2. Can anybody share work file who use annual time series data estimate fiscal multiplier using Blanchard Perotti (2002)model.
Thank you
I'm Ruwan who wish to estimate fiscal multiplier for Sri Lanka for my master thesis. I am going to follow BP model with expenditure,revenue and GDP variables. But I have only 1990 - 2017 annual data set. So is it possible to estimate using this data set?
2. Can anybody share work file who use annual time series data estimate fiscal multiplier using Blanchard Perotti (2002)model.
Thank you
↧
FAVAR add-in
Hi Dakila,
thank you very much for your response.
What you just described is basically the factor rotation that ensures that the factors are indipendent from R. I agree that this is the situation in the FAVAR modeling where the differentiation between slow- and fast-moving matters. However, this is not directly related to the issue I described in my original question.
Let me describe the topic a little bit more detailed (I follow the BBE2005 scenario where they use three factors next to Y_{t} / R in your description):
After the factor rotation we end up with three (rotated) factors. The rotated factors are F_{t}^{hat} in BBE2005. Next, they estimate their equation (1) (transition equation) with F_{t}^{hat} replacing F_{t}. Calculating the impulse responses of the three factors and the policy rate, we end up with IRFs starting with zeros for the three factors (as expected, as they are ordered before the policy rate in the cholesky ordering) and an IRF for the policy rate that starts above zero. In other words: We have a matrix of IRFs with four columns (shock of policy rate on factor one, two, three and on itself) and rows equal to the IRF horizon (BBE use h=48). The first entries of the first three columns are exactly zero as the factors aren't contemporenously affected by a shock in the policy rate.
Next, we use this 48x4 IRF matrix (with IRF(1,1)=0; IRF(1,2)=0; IRF(1,3)=0; IRF(1,4)<>0) to calculate the IRFs of selected variables in the large dataset (X_{t} in BBE2005). Therefore, we multiply this matrix with the (transposed) respective loadings matrix (Lambda^{f} and Lambda^{y} in BBE2005, 120x4). The loadings matrix is supposed to have zeros in the 4th column for all slow moving variables as there is no contemporaneous effect of the policy rate shock on those variables. Ultimately, we end up with a 48x120 matrix of the impulse responses of all variables in X_{t}. By definition, the first entry in each column is supposed to be zero for the slow-moving variables and different from zero for the slow moving variables. That is what I meant when I referred to the point that - at least from my point of view - irfs of slow moving variables should always start with zero.
The example file generates an irf matrix where the unemployment rate (slow-moving) starts with an initial value of -0.005 (see appended image). How is this possible? Or do you disagree with my argumentation? I would really appreciate some feedback.
Thank you very much in advance and best regards
Markus
thank you very much for your response.
What you just described is basically the factor rotation that ensures that the factors are indipendent from R. I agree that this is the situation in the FAVAR modeling where the differentiation between slow- and fast-moving matters. However, this is not directly related to the issue I described in my original question.
Let me describe the topic a little bit more detailed (I follow the BBE2005 scenario where they use three factors next to Y_{t} / R in your description):
After the factor rotation we end up with three (rotated) factors. The rotated factors are F_{t}^{hat} in BBE2005. Next, they estimate their equation (1) (transition equation) with F_{t}^{hat} replacing F_{t}. Calculating the impulse responses of the three factors and the policy rate, we end up with IRFs starting with zeros for the three factors (as expected, as they are ordered before the policy rate in the cholesky ordering) and an IRF for the policy rate that starts above zero. In other words: We have a matrix of IRFs with four columns (shock of policy rate on factor one, two, three and on itself) and rows equal to the IRF horizon (BBE use h=48). The first entries of the first three columns are exactly zero as the factors aren't contemporenously affected by a shock in the policy rate.
Next, we use this 48x4 IRF matrix (with IRF(1,1)=0; IRF(1,2)=0; IRF(1,3)=0; IRF(1,4)<>0) to calculate the IRFs of selected variables in the large dataset (X_{t} in BBE2005). Therefore, we multiply this matrix with the (transposed) respective loadings matrix (Lambda^{f} and Lambda^{y} in BBE2005, 120x4). The loadings matrix is supposed to have zeros in the 4th column for all slow moving variables as there is no contemporaneous effect of the policy rate shock on those variables. Ultimately, we end up with a 48x120 matrix of the impulse responses of all variables in X_{t}. By definition, the first entry in each column is supposed to be zero for the slow-moving variables and different from zero for the slow moving variables. That is what I meant when I referred to the point that - at least from my point of view - irfs of slow moving variables should always start with zero.
The example file generates an irf matrix where the unemployment rate (slow-moving) starts with an initial value of -0.005 (see appended image). How is this possible? Or do you disagree with my argumentation? I would really appreciate some feedback.
Thank you very much in advance and best regards
Markus
↧
Error 2142 in encrypted program
↧
↧
Panel Error Correction model forecating
Hi,
I estimated a panel ECM with fixed effects, using FMOLS for the long run dynamics, and then using OLS for the short term dynamics. I use eviews 9.5, therefore I estimated the long run relation using the following estimation command: COINTREG(PANMETHOD=GROUPED) LOG_NPL_CONS LOG_LAG_LEV_CONS LOG_PIB.
Then, I went to Proc, and generated a residual series. This residual is the one I use to estimate the EMC equation of the following estimation command:
LS(CX=F) D(LOG_NPL_CONS) C D(LOG_NPL_CONS(-1)) D(LOG_LAG_LEV_CONS) D(LOG_PIB) RESID_FOLS_PRUEBA(-1).
The restricted ECM could be written as:
D(LOG_NPL_CONS) = 0.00197766354072 + 0.269590701578*D(LOG_NPL_CONS(-1)) + 0.539345237869*D(LOG_LAG_LEV_CONS) - 0.975875372066*D(LOG_PIB) - 0.0424886489025*[ LOG_NPL_CONS - (0.537641531923*LOG_LAG_LEV_CONS - 0.652596322867*LOG_PIB )]
Up to here is fine. But now I'd like to do out of sample forecast, say for example 8 periods ahead. Is there any easy ways to build it?
kind regards.
I estimated a panel ECM with fixed effects, using FMOLS for the long run dynamics, and then using OLS for the short term dynamics. I use eviews 9.5, therefore I estimated the long run relation using the following estimation command: COINTREG(PANMETHOD=GROUPED) LOG_NPL_CONS LOG_LAG_LEV_CONS LOG_PIB.
Then, I went to Proc, and generated a residual series. This residual is the one I use to estimate the EMC equation of the following estimation command:
LS(CX=F) D(LOG_NPL_CONS) C D(LOG_NPL_CONS(-1)) D(LOG_LAG_LEV_CONS) D(LOG_PIB) RESID_FOLS_PRUEBA(-1).
The restricted ECM could be written as:
D(LOG_NPL_CONS) = 0.00197766354072 + 0.269590701578*D(LOG_NPL_CONS(-1)) + 0.539345237869*D(LOG_LAG_LEV_CONS) - 0.975875372066*D(LOG_PIB) - 0.0424886489025*[ LOG_NPL_CONS - (0.537641531923*LOG_LAG_LEV_CONS - 0.652596322867*LOG_PIB )]
Up to here is fine. But now I'd like to do out of sample forecast, say for example 8 periods ahead. Is there any easy ways to build it?
kind regards.
↧
Panel Error Correction model forecating
sorry, the correct ECM restricted equation would be:
D(LOG_NPL_CONS) = 0.00197766354072 + 0.269590701578*D(LOG_NPL_CONS(-1)) + 0.539345237869*D(LOG_LAG_LEV_CONS) - 0.975875372066*D(LOG_PIB) - 0.0424886489025*[ LOG_NPL_CONS - (0.537641531923*LOG_LAG_LEV_CONS(-1) - 0.652596322867*LOG_PIB(-1) )] + fixed effect
many thaks in advance.
D(LOG_NPL_CONS) = 0.00197766354072 + 0.269590701578*D(LOG_NPL_CONS(-1)) + 0.539345237869*D(LOG_LAG_LEV_CONS) - 0.975875372066*D(LOG_PIB) - 0.0424886489025*[ LOG_NPL_CONS - (0.537641531923*LOG_LAG_LEV_CONS(-1) - 0.652596322867*LOG_PIB(-1) )] + fixed effect
many thaks in advance.
↧
Fan Chart Actual and FC Data
Hi - I have been using the new fanchart option of EViews 11. In previous versions, I used the Fan Chart Add-in which, while being very helpful, was more time consuming as you needed to get data for skewness, uncertainty, mode etc. One advantage however was that it plotted the historical data along with the fan chart. Is there a way of doing this with the new in build feature?
Npg
Npg
↧
Crash When Store Fan Chart Graph
↧
↧
Syntax error
I'm getting a syntax error when I try to create a moving average in a for loop like this:
the same thing works with other functions like this though:
So I assume it has to do with the 8 option I'm adding to the moving average function. Any ideas on how to resolve this?
thanks
Code:
for !i=1 to mygroupgr.@count
%sn = mygroupgr.@seriesname(!i)
series {%sn}ma = @movav({%sn},8))
next
the same thing works with other functions like this though:
Code:
for !i=1 to mygroup.@count
%sn = mygroup.@seriesname(!i)
series {%sn}gr = @pca({%sn})
next
So I assume it has to do with the 8 option I'm adding to the moving average function. Any ideas on how to resolve this?
thanks
↧
Doing everything in a script on two pages
↧
Syntax error
↧
Fan Chart Actual and FC Data
↧
↧
Crash When Store Fan Chart Graph
↧
Syntax error
↧
Icon in crtl-L
↧
Icon in crtl-L
↧
↧
FAVAR add-in
Hi Markus,
I think that assumption is questionable. The slow and fast moving variables matters for the factor rotation not for the impulse response functions.
The loadings matrix is supposed to have zeros in the 4th column for all slow moving variables as there is no contemporaneous effect of the policy rate shock on those variables.
I think that assumption is questionable. The slow and fast moving variables matters for the factor rotation not for the impulse response functions.
↧
Installation Error -1925
I have faced a similar problem: I cannot reinstall Eviews 11 and cannot delete it. In the first case I receive the message “The setup has detected that no version of Eviews 11 is installed. The specified command-line options require that the application be installed to continue. The setup will now terminate”, in the second case, that the program is already deleted.
The same situation is happened with Eviews 10.
Any manipulation with temp directory or registry didn’t help (by the way, zip file for registry corrections does not exist).
Probably, this happened after the last update of Eviews 11 and 10, but I am not sure.
At the same, time both Eviews 11 and 10 work properly.
Any recommendations?
Eviews 11 and 10 64 bit, Windows 10.
The same situation is happened with Eviews 10.
Any manipulation with temp directory or registry didn’t help (by the way, zip file for registry corrections does not exist).
Probably, this happened after the last update of Eviews 11 and 10, but I am not sure.
At the same, time both Eviews 11 and 10 work properly.
Any recommendations?
Eviews 11 and 10 64 bit, Windows 10.
↧
Installation Error -1925
↧