They scale the regressors by the L1 and L2 norms of the data, respectively, prior to estimation. So the penalties on parameters will be on coefficients that are for scaled data. The coefficients are transformed back to original scale for reporting.
Hope that this answers your question.
Search found 2673 matches
- Wed Apr 10, 2024 10:44 am
- Forum: Estimation
- Topic: Ridge Estimation
- Replies: 3
- Views: 240
- Wed Feb 07, 2024 12:54 pm
- Forum: Estimation
- Topic: IRFs with MS-VAR
- Replies: 2
- Views: 530
Re: IRFs with MS-VAR
Are your lag coefficients regime-specific? If they are not, then the impulse-responses are not regime-specific. If they are, then you will see a spool with the IRs for each regime.
- Wed Jan 24, 2024 2:22 pm
- Forum: Estimation
- Topic: Estimating state space model for GARCH(1,1)
- Replies: 17
- Views: 28721
Re: Estimating state space model for GARCH(1,1)
I am sorry, but no.
- Wed Oct 04, 2023 10:01 am
- Forum: Estimation
- Topic: STAR output issues
- Replies: 28
- Views: 27367
Re: STAR output issues
Sorry, just saw this. Yes. Please provide, along with as much information as possible. Thanks.
- Wed Sep 20, 2023 7:27 pm
- Forum: Estimation
- Topic: STAR output issues
- Replies: 28
- Views: 27367
Re: STAR output issues
It's up. Take a look.
- Tue Sep 12, 2023 6:01 am
- Forum: Estimation
- Topic: STAR output issues
- Replies: 28
- Views: 27367
Re: STAR output issues
Very sorry about the delay. I wanted to make sure that we sorted everything out correctly. We've put a fix into the code and testing looks good. It will appear in the next patch (probably early next week). Thanks for your patience, and I greatly apologize for the inconvenience. Let me know if you ha...
- Thu Aug 31, 2023 2:17 pm
- Forum: Estimation
- Topic: State space model on Eviews
- Replies: 3
- Views: 25659
Re: State space model on Eviews
We normally don't debug state-space specifications unless there is a bug, because we don't want to be in the position of offering other than cursory econometric or economic advice. I was however, in the midst of a quick browse of the forum, saw this question, and thought I'd take a quick look. I thi...
- Wed Aug 30, 2023 1:37 pm
- Forum: Estimation
- Topic: STAR output issues
- Replies: 28
- Views: 27367
Re: STAR output issues
On the original wonky test output... we've identified an issue with the scaling of some collinearity diagnostics. We are testing a fix and hope to have something soon.
Many apologies, and thanks for your patience.
Many apologies, and thanks for your patience.
- Wed Aug 16, 2023 3:52 pm
- Forum: Bug Reports
- Topic: Near singular matrix in computing the steady state probabilities.
- Replies: 8
- Views: 8528
Re: Near singular matrix in computing the steady state probabilities.
Hi. Found the issue. It's EVIews 12 only. A patch has been posted. You can initiate by selecting Help/EViews Update... from the main EViews menu.
Sorry for the inconvenience. Let us know if you have any additional issues.
Sorry for the inconvenience. Let us know if you have any additional issues.
- Tue Aug 15, 2023 9:29 am
- Forum: Bug Reports
- Topic: Near singular matrix in computing the steady state probabilities.
- Replies: 8
- Views: 8528
Re: Near singular matrix in computing the steady state probabilities.
Still looking into this. The problem is that while I do see the error in the Student Lite version, it does not appear in the standard EViews 12, nor in any of our standard tests. Will continue to explore. Thanks for you patience.
- Wed Aug 09, 2023 12:26 pm
- Forum: Bug Reports
- Topic: Near singular matrix in computing the steady state probabilities.
- Replies: 8
- Views: 8528
Re: Near singular matrix in computing the steady state probabilities.
Okay. Thanks. Let me see what I can figure out.
- Wed Aug 09, 2023 10:25 am
- Forum: Bug Reports
- Topic: Near singular matrix in computing the steady state probabilities.
- Replies: 8
- Views: 8528
Re: Near singular matrix in computing the steady state probabilities.
Thanks. That's useful, but I still can't replicate. Could you send me a screenshot of your output. And can you take a look at the Help/About EViews main menu item and give me information about your version and build-date. Thanks.
- Wed Aug 09, 2023 8:28 am
- Forum: Bug Reports
- Topic: Near singular matrix in computing the steady state probabilities.
- Replies: 8
- Views: 8528
Re: Near singular matrix in computing the steady state probabilities.
Hi. I've tested this on various versions of EViews (not Student Lite yet, but I will if we can't pin this down) and in all cases, it converges and produces standard errors. But before going further, I did want to ask you if you are using the seetings in that equation without change, and if so, what ...
- Mon Jul 24, 2023 8:50 am
- Forum: Bug Reports
- Topic: Near singular matrix in unit root test
- Replies: 1
- Views: 5281
Re: Near singular matrix in unit root test
After a(n admittedly) cursory check, I don't think this is a bug. At first, I thought we might not be checking the required number of observations appropriately accounting for the lags. But I found that our check is appropriate. In this case, while there are enough observations to estimate the unit ...
- Mon Jul 10, 2023 6:09 pm
- Forum: Estimation
- Topic: State space model on Eviews
- Replies: 3
- Views: 25659
Re: State space model on Eviews
Just looking at the spec in your post I note that a problem arises since you can't have lagged state variables in the signal equation. To include the desired lags, you will have to create new states which correspond to the lags of the states you have already specified. That said I think you can resp...