EViews.com

I am attemtping to run a bivariate DCC- Garch model in order to test correlation between two stock markets during the period 01/06/2005 and 08/27/2009. The program I am using works perfectly until I attempt to estimate the model. Here i am recieveing the error code,

Error in Sample : Range Error in "sample S1 2 243".

I have tried everything to alleviate this problem but nothing seems to be working. Is this a problem with my program or is this a problem with the range I have set or my data??

Any help with this will be greatly appreciated. The program i am using is pasted below.

'set sample range
sample s1 01/06/2005 08/27/2009
scalar pi=3.14159

'defining the return series in terms of y1 and y2
series y1=sp500
series y2=bse

'fitting univariate GARCH(1,1) models to each of the two returns series
equation eq_y1.arch(1,1,m=1000,h) y1 c
equation eq_y2.arch(1,1,m=1000,h) y2 c

'extract the standardized residual series from the GARCH fit
eq_y1.makeresids(s) z1
eq_y2.makeresids(s) z2

'extract garch series from univariate fit
eq_y1.makegarch() garch1
eq_y2.makegarch() garch2

'Caculate sample variance of series z1, z2 and covariance of z1and z2 and correlation between z1 and z2
scalar var_z1=@var(z1)
scalar var_z2=@var(z2)
scalar cov_z1z2=@cov(z1,z2)
scalar corr12=@cor(z1,z2)

'defining the starting values for the var(z1) var(z2) and covariance (z1,z2)
series var_z1t=var_z1
series var_z2t=var_z2
series cov_z1tz2t=cov_z1z2

'declare the coefficient starting values
coef(2) T
T(1)=0.2
T(2)=0.7

' ...........................................................
' LOG LIKELIHOOD for correlation part
' set up the likelihood
' 1) open a new blank likelihood object and name it 'dcc'
' 2) specify the log likelihood model by append
' ...........................................................

logl dcc
dcc.append @logl logl

'specify var_z1t, var_z2t, cov_z1tz2t
dcc.append var_z1t=@nan(1-T(1)-T(2)+T(1)*(z1(-1)^2)+T(2)*var_z1t(-1),1)
dcc.append var_z2t=@nan(1-T(1)-T(2)+T(1)*(z2(-1)^2)+T(2)*var_z2t(-1),1)
dcc.append cov_z1tz2t=@nan((1-T(1)-T(2))*corr12+T(1)*z1(-1)*z2(-1)+T(2)*cov_z1tz2t(-1),1)

dcc.append pen=(var_z1t<0)+(var_z2t<0)

'specify rho12
dcc.append rho12=cov_z1tz2t/@sqrt(@abs(var_z1t*var_z2t))

'defining the determinant of correlation matrix and determinant of Dt
dcc.append detrRt=(1-(rho12^2))
dcc.append detrDt=@sqrt(garch1*garch2)
dcc.append pen=pen+(detrRt<0)
dcc.append detrRt=@abs(detrRt)

'define the log likelihood function
dcc.append logl=(-1/2)*(2*log(2*pi)+log(detrRt)+(z1^2+z2^2-2*rho12*z1*z2)/detrRt)-10*pen

'estimate the model
sample s1 2 253
smpl s1
dcc.ml(showopts, m=500, c=1e-5)
smpl @all

'display output and graphs
show dcc.output
graph corr.line rho12
show corr

What does EViews show for the workfile range at the top of the workfile window?

At a guess, you have a dated workfile, thus you have to use dates to set the samle

The range at the top of the file shows 1/6/2005 9/2/2009 -- 243. I have used weekly data through the period 1/6/2005 8/27/2009.

I have tried changing the workfile range dates and sample dates.

Could this be a problem be allviated by importing all the data as a STATA data file so the date is already attached to the other data?

No, the problem is as I stated above. You have a dated workfile, yet your command: is trying to set the sample without using dates. You must used dates in the sample command if your workfile is dated.

You got it right in your first sample statement:

I have tried this repeatedly but unfortuantely get the same error message.

Did you change your second sample command to use dates?

as in the one used to estimate the model? yes i have changed that to

sample s1 2 1/06/ etc

i have also tried

sample s1 1/06 etc

neither work i still recieve the same error message

Why don't you tell us exactly what you have tried.

I have tried changing the dates in the program code, changing the observations in the program code. Changing the dates/obs in the workfile. I have attached my workfile.

Try changing the line: to be: Then, tell us what happens.

I have managed to sort it out now. I have dropped the date from the workfile and merely used the number of observations. Using sample s1 2 242 now works and i have the results i needed.

Thank you very much for your time.

Philip