07-15-2015 08:33 AM
My data currently look like this:
Time To Maturity Volatility
I am looking to run the following three tests on my data and want to make sure I am doing so correctly.
1.Jonckheere-Terpstra test To examine if the volatility increases as a contract approaches maturity
2.Newy West Heteroskedasticity Consistent Covariance Procedure To regress the daily future realised volatility on a constant and the number of days until the contract matures.
3.GARCH (1, 1) model
I want to make sure I am coding this correctly in order to ascertain that the results are correct. I have managed to get answer on how to run my first test from the SAS Statistical Discussion, any assistance on how to run the 2nd and 3rd test will be appreciated.
07-15-2015 03:25 PM
For Newey-west SE's.
PROC AUTOREG DATA=work.data;
MODEL y = x / GARCH=(q=1,p=1) covest=neweywest;
For #1, look here SAS/STAT(R) 14.1 User's Guide
You'll have to estimate that test statistic outside AUTOREG. (Oh i just saw your note. Oh well, for everyone else and me )
07-16-2015 07:37 AM
Thank you for your responses.
When I attempt the test for Newey West as specified above it brings the following error:
ERROR: Procedure AUTOREG not found.
Do you know how could go about fixing this?
07-16-2015 11:01 AM
It looks like the SAS instance that you are using does not have SAS/ETS installed. In particular, if you are using the University Edition, it does not support SAS/ETS procedures.
07-17-2015 01:04 PM
The short answer is that you do not have SAS/ETS installed. If you are interested in licensing that module, follow this link.
If you are a student or using the product for human capital purposes (non revenue generating) then you can access "cloud SAS" here. SAS® Logon Manager
All you need to do is sign up for an account.
Best of luck-Ken
11-02-2015 09:16 AM
Thanks for all your assistance - it is greatly appreciated. I have managed to run all three tests, but I have a question relating to the confidence interval... How do I know what the confidence interval is that the tests are assuming? Or do I have to specify one? If so where?
Thanks in advance
11-04-2015 07:18 AM
Thanks for the information regarding the Newey-West test. Do you know how I add in another dependent variable into the regression?
As when I try to do it currently it bring up an error.