The RATS Software Forum

Dear Tom

As you know, I've been working on this matter for a while. Now, to bring it to a conclusion, I need your assistance regarding the questions I raised in the previous post.
Furthermore, I haven't received any response despite reaching out to Maheum via email.

Dear Tom, Here is an estimate of the model without removing the outliers. I have some questions and would appreciate, as always, your guidance on them. 1) Why does the sign of b4 in the first mean model differ from the mean equation of the GARCH model? 2) Why are b3 and b4 not statistically insignif...

When I remove outliers the model doesn't converge but when I estimate it without removing the outliers it converges! When I intend to estimate the model by removing outlier data, I use returns data instead of price index data for estimation from the outset. Here is the code: * * Replication file for...

Thanks for your guide. Do you think it is possible to define dummy variables for the days of the week in the proposed model by Chan and Maheu (2002)( "Conditional Jump Dynamics in Stock Market Returns" )?

I shifted the W0 out of the HMEANF as you said and run it again. It still doesn't converge even after removing outliers!

Here is original data and program

I added an extra term for AR(1) [b6]. But it doesn't converge now. * * Replication file for Baillie and Bollerslev, "The Message in Daily * Exchange Rates: A Conditional Variance Tale", JBES 1989, vol 7, pp * 297-305 * open data .xlsx data(format=xlsx,org=columns) 1 3254 sto dow * labels s...

Thank you very much. I edited it, I think we should edit this part compute gstart=%regstart()+1,gend=%regend() to compute gstart=%regstart() +2 ,gend=%regend() too because of Ar(1) component. * * Replication file for Baillie and Bollerslev, "The Message in Daily * Exchange Rates: A Conditional ...

So sorry, I edited it, still have the error: * * Replication file for Baillie and Bollerslev, "The Message in Daily * Exchange Rates: A Conditional Variance Tale", JBES 1989, vol 7, pp * 297-305 * open data tom1.xlsx data(format=xlsx,org=columns) 1 3254 sto dow * labels sto # "Stock&q...

Appreciate your help: * * Replication file for Baillie and Bollerslev, "The Message in Daily * Exchange Rates: A Conditional Variance Tale", JBES 1989, vol 7, pp * 297-305 * open data tom1.xlsx data(format=xlsx,org=columns) 1 3255 sto dow * labels sto # "Stock" log sto * * Unit r...

I still get weird results for Ws. The Error Occurred At Location 141, Line 7 of loop/block ## NL6. NONLIN Parameter B0 Has Not Been Initialized. Trying 0 The Error Occurred At Location 141, Line 7 of loop/block ## NL6. NONLIN Parameter B1 Has Not Been Initialized. Trying 0 The Error Occurred At Loca...

Thank you very much for your valuable guidance. There is only one issue here. When I open the WINRATS software and run the program, I receive an unusual estimation for the Ws. However, if I don't close the software and run the program again, I get a different result that is entirely inconsistent wit...

I did it. It converge now but there are some weird results for Ws and one error too: he Error Occurred At Location 141, Line 7 of loop/block ## NL6. NONLIN Parameter B0 Has Not Been Initialized. Trying 0 The Error Occurred At Location 141, Line 7 of loop/block ## NL6. NONLIN Parameter B1 Has Not Bee...

I really appreciate your kind help and guide. I edited it for one variable and run it. It still does not converge for my data: * * Replication file for Baillie and Bollerslev, "The Message in Daily * Exchange Rates: A Conditional Variance Tale", JBES 1989, vol 7, pp * 297-305 * open data t...

I've even made other changes randomly to the program, but it still doesn't converge.

I did those steps, but it didn’t converge. Here is result: MAXIMIZE - Estimation by BFGS NO CONVERGENCE IN 47 ITERATIONS. FINAL NORMED GRADIENT 0.20463 ESTIMATION POSSIBLY HAS STALLED OR MACHINE ROUNDOFF IS MAKING FURTHER PROGRESS DIFFICULT TRY DIFFERENT SETTING FOR EXACTLINE, DERIVES OR ALPHA ON NL...