Quantcast
Channel: EViews
Viewing all 24080 articles
Browse latest View live
↧

Initial Parameter Values in Sspace

July 4, 2016, 9:17 pm
$
0
0
Hi all,

I'm trying to estimate a state-space model in which a want to set the initial value of the coefficients. I'm having some problems though because I want the value of the coefficients to be based on the value in a vector.

For instance if I put the following line in the state-space spec:

param c(1) 2

it works fine

However if I try using the value from the vector coeff_x, e.g.

param c(1) coeff_x(1)

I get an error message.
I've also tried putting the vector's value into a scalar and then using the scalar in the param line, but this also led to an error message.
Any help would be greatly appreciated.

↧
Search

LENGHT SELECTION: Estimation sample VAR

July 4, 2016, 11:29 pm
$
0
0
VAR Type:

unrestricted VAR
Vector Errror Correction
Bayesian VAR

Estimation sample :
1 125


Lag intervals for Endogenous:
1 2

Endogenous Variables:

Exogenous Variables:
c

Thank you.

↧
↧

Engle Granger Vs adf test on residuals

July 5, 2016, 12:58 am
$
0
0
Hi everyone, this is my very first post, so in case of any mistake i apologize in advance.
This is my problem: i was making some analysis on a currency pairs in order to develop a pairs trading strategy. I was pretty sure about the fact that the following two procedures were the same:
1)make a two step engle granger test by click ing the eviews test
2) i personally made the ols equation of the two currencies and once saved the residuals, I made the adf test on these.
However my results lead to two opposite directions: the first procedure shows no cointegration while the second show stationarity of residuals. Doesn't it mean they are cointegrated?

↧

Engle Granger Vs adf test on residuals

July 5, 2016, 1:33 am
$
0
0
If you want to use procedure 2 you should use EG critical values. Because of generated residuals, you should different c.v table from ADF test c.v table.

↧

VAR Lag Lenght: estimation sample

July 5, 2016, 4:50 am
$
0
0
Hi,
I am trying to estimate the optimal lag length in a VAR estimation. However, when I open the lag length window I don't understand how is expressed the estimation sample. I would like to input as estimation sample 1985q1 2016q1, the problem is that when I write those dates in the estimation sample box and press ok EViews tells me that this date expression is "illegal". And when I click on lag length this is what comes out in the estimation sample box:

VAR Type:

unrestricted VAR
Vector Errror Correction
Bayesian VAR

Estimation sample :
1 125


Lag intervals for Endogenous:
1 2

Endogenous Variables:

Exogenous Variables:
c

Could you please help me to figure it out what does it mean and how I have to write the estimation period?
Thank you.

↧
↧

VAR Lag Lenght: estimation sample

July 5, 2016, 5:07 am
$
0
0
Have you correctly specified workfile structure?

↧

VAR Lag Lenght: estimation sample

July 5, 2016, 5:34 am
$
0
0
All my data are expressed as it follows 1985 Q1 to 2016 Q1. I've also checked the spreadsheet.

↧

VAR Lag Lenght: estimation sample

July 5, 2016, 5:57 am
$
0
0
I meant the structure of Eviews workfile. In the upper left corner of the workfile, range should display 1985Q1 2016Q1 in your case.

↧
Search

Engle Granger Vs adf test on residuals

July 5, 2016, 6:26 am
$
0
0
Thanks for your reply. To be honest I was suspicious about the very same reason. Now you confirmed it.
I downloaded both ADF and Engle Granger Tables for critical values and in fact I now see significant differencies.
Maybe I was just disappointed for tests not confirming my hopes of cointegration between EurJpY vs ChfJpY......just have to look for another good idea :mrgreen:

Thanks again

↧
↧

LENGHT SELECTION: Estimation sample VAR

July 5, 2016, 8:21 am
$
0
0
Looks like your workfile is not dated. You need to structure your workfile as dated before you can use dates in a sample. From the workfile click on Proc->Reshape/Restructure current page.

↧

code to save fcstavg tables to a spool

July 5, 2016, 9:39 am
$
0
0
Using Eview's 9.5 - having trouble saving output from fcstavg commands to a predefined spool named spool1

here's the code:         
            v1606354.sheet
            v1606354.fcastavg(wgttype=aic) eq1 eq2 eq3 eq4 eq5
     spool1.append vi606354.sheet

tried to freeze the output and save but to no avail - suggestions - thanks

↧

code to save fcstavg tables to a spool

July 5, 2016, 9:45 am
$
0
0
If you want to append to an existing non-empty spool called spool1:
Code:

output(s) spool1
pon
v1606354.fcastavg(wgttype=aic) eq1 eq2 eq3 eq4 eq5
poff


or
Code:

freeze(spool2) v1606354.fcastavg(wgttype=aic) eq1 eq2 eq3 eq4 eq5
spool1.append spool2


↧

code to save fcstavg tables to a spool

July 5, 2016, 9:49 am
↧
↧

DCCGARCH11

July 5, 2016, 10:12 am
$
0
0
Hey,

So right now I am estimating bivariate dcc garch (return in 2 indices such as s&p500 and klse).
Some of the paper that I read,
define the mean equation such: r_t=γ_0 + γ_1 r_(t-1)+ γ_2 r_(t-1)^us + ε_t ( I attached the paper's method and result) , it uses ar(1) process in the mean equation

My question is, every time I put Rus and Rmy in the return series and put 1 in the ar process for mean equation box, the rho that is produced is not series instead it's only give me one number (for the first day) whereas i supposed the rho_12_01 supposed to give series right?


I wonder, if I put only Rus and Rmy ( I got the series of rho_12_01) without including ar(1) and later I modify the estimation that is saved under eq_garch_r2_01 (meaning after the dcc then i go back to the univariate garch estimation and change the command there and include the ar(1))? is this violating the dcc proposed by engle somehow?


THANKS A LOT!!!

↧

Time varying SVAR

July 5, 2016, 10:18 am
$
0
0
Hi,

I am using eviews 8 to estimate the TVC-SVAR model with monthly data 2000m1 to 2015m12. There was an error message: "Sizes do not match in matrix function" during estimation. May I know how can I fix this problem? And what does the "y01" represent?
I find many papers using 40 as a training sample. what does training sample mean? Is there any test to measure it?

Thank you.

↧
Search

Initial Parameter Values in Sspace

July 5, 2016, 10:22 am
$
0
0
Don't use the param statement, just fill the coefficient vector that is referenced in the sspace specification with the value you want to use. So before you estimate just set C(1)=Coeff(1)

↧

converting incremental monthly series to quarterly

July 5, 2016, 10:46 am
$
0
0
Hi,
I've incremental monthly series with value increasing for each month till M12.
Now for converting this series to quarterly, I need to keep Q1 value as it is for M03. Q2 = M6-M3, Q3=M9-M6 and Q4=M12-M09. Don't know how to create such series.
So, please let me know a function that will do this transformation.

Thanks,
Santosh

↧
↧

Run a regression with multiples dummy variables

July 5, 2016, 11:02 am
$
0
0
What do you have to write to run the regression?
independent variable - "Car"
dependent variables - "National", "Top"

Do I have to write "Car c National=1 Top=0"?

Thanks

↧

Run a regression with multiples dummy variables

July 5, 2016, 11:06 am
↧

converting incremental monthly series to quarterly

July 5, 2016, 11:14 am
$
0
0
You'll have to do it in a few steps.
Code:

copy(c=l) monlypage\y quarterlypage\y
smpl if @quarter<>1
y = y-y(-1)
smpl @all


Where Y is the underlying series, and monthlypage and quarterlypage are your pages.

↧
Viewing all 24080 articles
Browse latest View live
Search
<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>