Search found 85 matches

by NicolasR
Wed Aug 13, 2014 2:45 pm
Forum: Add-in Support
Topic: Spectral Analysis*
Replies: 31
Views: 23803

Re: Spectral Analysis*

The Hodrick Prescott filter is a low pass filter, that is, it preserves the low frequency components in the spectrum (long run). Therefore, you can use the estimated spectrum of your series to see if there is any significant peak at the low frequency components, if there is not, the smoothed series ...
by NicolasR
Fri May 16, 2014 10:13 am
Forum: Econometric Discussions
Topic: When to use VAR/VECM
Replies: 2
Views: 3179

Re: When to use VAR/VECM

Hi, You should use VECM if 1) your variables are nonstationary and 2) you find a common trend between the variables (cointegration). If your variables are nonstationary and you transform them to became stationary (diferences or subtracting trends) without doing a cointegration test you might be omit...
by NicolasR
Thu Apr 17, 2014 10:19 am
Forum: Econometric Discussions
Topic: Potential output, the Clark model and State Space Models
Replies: 10
Views: 4691

Re: Potential output, the Clark model and State Space Models

Hi, I belive you should introduce starting values for the state variables, you can do it like this for the Clark model: @signal gdp = trend + cycle @state trend = c(1) + trend(-1) + [var = exp(c(2))] @state cycle = c(3)*cycle(-1) + c(4)*lcycle(-1) + [var = exp(c(5))] @state lcycle = cycle(-1) param ...
by NicolasR
Mon Apr 14, 2014 5:27 pm
Forum: Econometric Discussions
Topic: Impulse Response in Eviews
Replies: 13
Views: 12471

Re: Impulse Response in Eviews

1) In units of the response variable. 2) Cholesky is a matrix decomposition that ensures that your residual covariance matrix could be transformed into a diagonal matrix. The purpose of this Cholesky decomposition is that the impulse to one variable (or their innovations) must be unrelated to the im...
by NicolasR
Wed Apr 09, 2014 7:49 pm
Forum: Econometric Discussions
Topic: Impulse Response in Eviews
Replies: 13
Views: 12471

Re: Impulse Response in Eviews

Hi, When you give an impulse to a system of equations or an equation, you do it through the residuals (also called innovations) which are the non explained part of the depent variable, so they are in units of the impulse variable. Usually the constant of the model is not taken into account in the im...
by NicolasR
Sun Mar 23, 2014 1:55 pm
Forum: Estimation
Topic: near singular matrix
Replies: 1
Views: 1135

Re: near singular matrix

Did you tried different starting values for the coefficients? Maybe the coefficients c(1) to c(5) have a value where the algorithm can not start its iteration.

You can change them in the c vector coeficient.
by NicolasR
Sat Mar 22, 2014 11:16 am
Forum: Estimation
Topic: syntax error
Replies: 4
Views: 2358

Re: syntax error

I did not know of the existence of the formula object, thanks Glenn.
by NicolasR
Sat Mar 22, 2014 6:46 am
Forum: Estimation
Topic: syntax error
Replies: 4
Views: 2358

Re: syntax error

Hi, you miss some brackets or put some more, I estimate it like this: ls log(cs/(cs+ls)) - log(cs(-1)/(cs(-1) + ls(-1)))=c(3)*(c(4) - 1) + (c(4) - 1)/(1-c(2))*(log(cs+ls)/1)- (log(cs(-1)+ls(-1)))/1+ (1- c (4))*(log(pk) - log(pk(-1)))- log(py)+log(py(-1)) I think that a simpler way to estimate the mo...
by NicolasR
Wed Mar 19, 2014 9:47 am
Forum: Programming
Topic: multistep forecast vecm
Replies: 10
Views: 3754

Re: multistep forecast vecm

It uses the 400 past values in the sense that you estimate the model with this data, but the forecast are out of sample dynamic.
by NicolasR
Wed Mar 19, 2014 8:18 am
Forum: Programming
Topic: multistep forecast vecm
Replies: 10
Views: 3754

Re: multistep forecast vecm

No, you don´t have to change the value, you can keep it in seven, I said it in the case you wanted more forecasting ahead steps than five. I have a question,are you sure that the cointegration relationship remains across the time window?
by NicolasR
Tue Mar 18, 2014 7:57 am
Forum: Programming
Topic: multistep forecast vecm
Replies: 10
Views: 3754

Re: multistep forecast vecm

Hi mirror, one easy way to do it is saving the forecasts in a matrix. I do it like this,i think it work, you just have to change the ahead scalar: 'set window size !window=400 'get size of workfile !length=@obsrange 'set step size !step=1 'declare equation for estimation var vecm 'calculate number o...
by NicolasR
Fri Mar 14, 2014 1:40 pm
Forum: Estimation
Topic: How would I input this equation into eViews?
Replies: 5
Views: 1865

Re: How would I input this equation into eViews?

Hi,

You should estimate it with NLS like this:

ls y=c(1)*k^c(2)*l^c(3)*e^c(4)*m^c(5)

By default EViews put the error term. Be careful with the starting values of the parameters, you could introduce them in the c vector-coeficcient.
by NicolasR
Fri Mar 14, 2014 9:39 am
Forum: Programming
Topic: Extracting Trend Using Kalman Filter
Replies: 1
Views: 1170

Re: Extracting Trend Using Kalman Filter

Hi, It depends if you want the smoothed trend or the filtered trend (or the other options that EViews provides) , but you could program it like this for one state variable, you must provide more output names if you have more state variables: sv1.makestate(t=pred) name_1 sv1.makestate(t=predse) name_...
by NicolasR
Sat Feb 22, 2014 1:53 pm
Forum: Add-in Support
Topic: Spectral Analysis*
Replies: 31
Views: 23803

Spectral Analysis*

This thread is about the Spectral Analysis add-in which calculates various spectral analysis tools for time series :series:. It's an improved version of the periodogram add-in, it has new methods to calculate spectal density and a significance test signal that could be used as a white noise test. Re...
by NicolasR
Sun Feb 02, 2014 9:23 pm
Forum: Suggestions and Requests
Topic: asymmetric loss function
Replies: 5
Views: 2734

Re: asymmetric loss function

Section 5 of this document describes the lin-lin,quad-quad and linex functions.

http://www.faculty.ucr.edu/~taelee/pape ... ctions.pdf

Thanks for considering my suggestion. Regards.

Go to advanced search