Dear Stephane,
Is there any chance that you could add the prefiltering that erroneously got deleted in efcf6bd9c09fa43bcf78fdb88b7b2d3a4dae5e05 in master to makedataset.m? My fixing of the prefiltering and detrending requires this functionality.
Best,
Johannes
--------
Johannes Pfeifer
Friesenwall 104
50672 Köln
Mobil: +49-(0)170-6936820
jpfeifer@gmx.de
Hi Johannes,
I am working on it... Which mod file should I use to test my changes ?
I need also to rework the testsuite so that we can test more systematically the results (in general we only check that dynare returns a result) and also check the timings... But this will come later.
Best, Stéphane.
I need also to change the way we implement some of the tests
On 08/07/2014 14:34, Johannes Pfeifer wrote:
Dear Stephane,
Is there any chance that you could add the prefiltering that erroneously got deleted in efcf6bd9c09fa43bcf78fdb88b7b2d3a4dae5e05 in master to makedataset.m? My fixing of the prefiltering and detrending requires this functionality.
Best,
Johannes
Johannes Pfeifer
Friesenwall 104
50672 Köln
Mobil: +49-(0)170-6936820
jpfeifer@gmx.de
Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
Thanks.
I am working on a whole testsuite for the prefiltering and detrending part where I check the correctness of the returned estimates, not only if something is returned. The complication is that there are 2^4 different cases to check (prefilter, detrending, loglinear, ML/Bayesian). That is how I detected the variety of issues.
The attached mod-file should do the job for now. It should return correct parameter estimates. If prefiltering is not correctly taken care of, a unit root should be detected and an error be thrown out.
-------- Johannes Pfeifer Friesenwall 104 50672 Köln Mobil: +49-(0)170-6936820 jpfeifer@gmx.de
-----Ursprüngliche Nachricht----- Von: Dev [mailto:dev-bounces@dynare.org] Im Auftrag von Stéphane Adjemian Gesendet: Dienstag, 8. Juli 2014 15:29 An: List for Dynare developers Betreff: Re: [DynareDev] Prefiltering in Master
Hi Johannes,
I am working on it... Which mod file should I use to test my changes ?
I need also to rework the testsuite so that we can test more systematically the results (in general we only check that dynare returns a result) and also check the timings... But this will come later.
Best, Stéphane.
I need also to change the way we implement some of the tests
On 08/07/2014 14:34, Johannes Pfeifer wrote:
Dear Stephane,
Is there any chance that you could add the prefiltering that erroneously got deleted in efcf6bd9c09fa43bcf78fdb88b7b2d3a4dae5e05 in master to makedataset.m? My fixing of the prefiltering and detrending requires this functionality.
Best,
Johannes
Johannes Pfeifer
Friesenwall 104
50672 Köln
Mobil: +49-(0)170-6936820
jpfeifer@gmx.de
Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
_______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA256
Johannes, I pushed a fix for the prefilter option. I think that there is still something wrong but I hope this solves the issue you care about.
Stéphane.
On 08/07/2014 16:04, Johannes Pfeifer wrote:
Thanks.
I am working on a whole testsuite for the prefiltering and detrending part where I check the correctness of the returned estimates, not only if something is returned. The complication is that there are 2^4 different cases to check (prefilter, detrending, loglinear, ML/Bayesian). That is how I detected the variety of issues.
The attached mod-file should do the job for now. It should return correct parameter estimates. If prefiltering is not correctly taken care of, a unit root should be detected and an error be thrown out.
-------- Johannes Pfeifer Friesenwall 104 50672 Köln Mobil: +49-(0)170-6936820 jpfeifer@gmx.de
-----Ursprüngliche Nachricht----- Von: Dev [mailto:dev-bounces@dynare.org] Im Auftrag von Stéphane Adjemian Gesendet: Dienstag, 8. Juli 2014 15:29 An: List for Dynare developers Betreff: Re: [DynareDev] Prefiltering in Master
Hi Johannes,
I am working on it... Which mod file should I use to test my changes ?
I need also to rework the testsuite so that we can test more systematically the results (in general we only check that dynare returns a result) and also check the timings... But this will come later.
Best, Stéphane.
I need also to change the way we implement some of the tests
On 08/07/2014 14:34, Johannes Pfeifer wrote:
Dear Stephane,
Is there any chance that you could add the prefiltering that erroneously got deleted in efcf6bd9c09fa43bcf78fdb88b7b2d3a4dae5e05 in master to makedataset.m? My fixing of the prefiltering and detrending requires this functionality.
Best,
Johannes
Johannes Pfeifer
Friesenwall 104
50672 Köln
Mobil: +49-(0)170-6936820
jpfeifer@gmx.de
_______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
_______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
_______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
- -- Stéphane Adjemian
Thanks, I will have a look at it.
Is there a way to change the name of the detrend operator to demean. Detrending should be demeaning and subtracting a linear trend as is the Matlab syntax of this command. Using detrend to denote just demeaning is confusing.
Am 09.07.2014 15:41, schrieb Stéphane Adjemian:
-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA256
Johannes, I pushed a fix for the prefilter option. I think that there is still something wrong but I hope this solves the issue you care about.
Stéphane.
On 08/07/2014 16:04, Johannes Pfeifer wrote:
Thanks.
I am working on a whole testsuite for the prefiltering and detrending part where I check the correctness of the returned estimates, not only if something is returned. The complication is that there are 2^4 different cases to check (prefilter, detrending, loglinear, ML/Bayesian). That is how I detected the variety of issues.
The attached mod-file should do the job for now. It should return correct parameter estimates. If prefiltering is not correctly taken care of, a unit root should be detected and an error be thrown out.
-------- Johannes Pfeifer Friesenwall 104 50672 Köln Mobil: +49-(0)170-6936820 jpfeifer@gmx.de
-----Ursprüngliche Nachricht----- Von: Dev [mailto:dev-bounces@dynare.org] Im Auftrag von Stéphane Adjemian Gesendet: Dienstag, 8. Juli 2014 15:29 An: List for Dynare developers Betreff: Re: [DynareDev] Prefiltering in Master
Hi Johannes,
I am working on it... Which mod file should I use to test my changes ?
I need also to rework the testsuite so that we can test more systematically the results (in general we only check that dynare returns a result) and also check the timings... But this will come later.
Best, Stéphane.
I need also to change the way we implement some of the tests
On 08/07/2014 14:34, Johannes Pfeifer wrote:
Dear Stephane,
Is there any chance that you could add the prefiltering that erroneously got deleted in efcf6bd9c09fa43bcf78fdb88b7b2d3a4dae5e05 in master to makedataset.m? My fixing of the prefiltering and detrending requires this functionality.
Best,
Johannes
Johannes Pfeifer
Friesenwall 104
50672 Köln
Mobil: +49-(0)170-6936820
jpfeifer@gmx.de
_______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
_______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
_______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
Stéphane Adjemian -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 Comment: Using GnuPG with Icedove - http://www.enigmail.net/
iF4EAREIAAYFAlO9RmgACgkQrQOaeEU5AZekoAEAtGbgiQaAlGiIC8Myq2rql0wd e0CmYRpL66QXfm1wKHMBAJ2nQBM9L4NW385jtagKxWoYLQhAp7edAujFJwCh51gZ =6p7d -----END PGP SIGNATURE----- _______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
The detrend method removes polynomial trends... That explains the name, even if I use it only for removing the mean in makedataset function.
ts.detrend(0) or ts.detrend() removes means from variables in ts, ts.detrend(1) removes linear trends from variables in ts, ts.detrend(2) removes quadratic trends from variables in ts, ...
We may add a method demean as an alias for detrend(0)... But I do not have any problem with the current name.
Stéphane.
On 09/07/2014 17:15, Johannes Pfeifer wrote:
Thanks, I will have a look at it.
Is there a way to change the name of the detrend operator to demean. Detrending should be demeaning and subtracting a linear trend as is the Matlab syntax of this command. Using detrend to denote just demeaning is confusing.
Am 09.07.2014 15:41, schrieb Stéphane Adjemian: Johannes, I pushed a fix for the prefilter option. I think that there is still something wrong but I hope this solves the issue you care about.
Stéphane.
On 08/07/2014 16:04, Johannes Pfeifer wrote:
Thanks.
I am working on a whole testsuite for the prefiltering and detrending part where I check the correctness of the returned estimates, not only if something is returned. The complication is that there are 2^4 different cases to check (prefilter, detrending, loglinear, ML/Bayesian). That is how I detected the variety of issues.
The attached mod-file should do the job for now. It should return correct parameter estimates. If prefiltering is not correctly taken care of, a unit root should be detected and an error be thrown out.
-------- Johannes Pfeifer Friesenwall 104 50672 Köln Mobil: +49-(0)170-6936820 jpfeifer@gmx.de
-----Ursprüngliche Nachricht----- Von: Dev [mailto:dev-bounces@dynare.org] Im Auftrag von Stéphane Adjemian Gesendet: Dienstag, 8. Juli 2014 15:29 An: List for Dynare developers Betreff: Re: [DynareDev] Prefiltering in Master
Hi Johannes,
I am working on it... Which mod file should I use to test my changes ?
I need also to rework the testsuite so that we can test more systematically the results (in general we only check that dynare returns a result) and also check the timings... But this will come later.
Best, Stéphane.
I need also to change the way we implement some of the tests
On 08/07/2014 14:34, Johannes Pfeifer wrote:
Dear Stephane,
Is there any chance that you could add the prefiltering that erroneously got deleted in efcf6bd9c09fa43bcf78fdb88b7b2d3a4dae5e05 in master to makedataset.m? My fixing of the prefiltering and detrending requires this functionality.
Best,
Johannes
Johannes Pfeifer
Friesenwall 104
50672 Köln
Mobil: +49-(0)170-6936820
jpfeifer@gmx.de
_______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
_______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
_______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
-- Stéphane Adjemian
Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
I see. Fin e with me.
I had a look at the fix and it greatly serves my immediate needs. What did you mean with there you think is still something wrong?
Am 09.07.2014 17:34, schrieb Stéphane Adjemian:
The detrend method removes polynomial trends... That explains the name, even if I use it only for removing the mean in makedataset function.
ts.detrend(0) or ts.detrend() removes means from variables in ts, ts.detrend(1) removes linear trends from variables in ts, ts.detrend(2) removes quadratic trends from variables in ts, ...
We may add a method demean as an alias for detrend(0)... But I do not have any problem with the current name.
Stéphane.
On 09/07/2014 17:15, Johannes Pfeifer wrote:
Thanks, I will have a look at it.
Is there a way to change the name of the detrend operator to demean. Detrending should be demeaning and subtracting a linear trend as is the Matlab syntax of this command. Using detrend to denote just demeaning is confusing.
Am 09.07.2014 15:41, schrieb Stéphane Adjemian: Johannes, I pushed a fix for the prefilter option. I think that there is still something wrong but I hope this solves the issue you care about.
Stéphane.
On 08/07/2014 16:04, Johannes Pfeifer wrote:
Thanks.
I am working on a whole testsuite for the prefiltering and detrending part where I check the correctness of the returned estimates, not only if something is returned. The complication is that there are 2^4 different cases to check (prefilter, detrending, loglinear, ML/Bayesian). That is how I detected the variety of issues.
The attached mod-file should do the job for now. It should return correct parameter estimates. If prefiltering is not correctly taken care of, a unit root should be detected and an error be thrown out.
-------- Johannes Pfeifer Friesenwall 104 50672 Köln Mobil: +49-(0)170-6936820 jpfeifer@gmx.de
-----Ursprüngliche Nachricht----- Von: Dev [mailto:dev-bounces@dynare.org] Im Auftrag von Stéphane Adjemian Gesendet: Dienstag, 8. Juli 2014 15:29 An: List for Dynare developers Betreff: Re: [DynareDev] Prefiltering in Master
Hi Johannes,
I am working on it... Which mod file should I use to test my changes ?
I need also to rework the testsuite so that we can test more systematically the results (in general we only check that dynare returns a result) and also check the timings... But this will come later.
Best, Stéphane.
I need also to change the way we implement some of the tests
On 08/07/2014 14:34, Johannes Pfeifer wrote:
Dear Stephane,
Is there any chance that you could add the prefiltering that erroneously got deleted in efcf6bd9c09fa43bcf78fdb88b7b2d3a4dae5e05 in master to makedataset.m? My fixing of the prefiltering and detrending requires this functionality.
Best,
Johannes
Johannes Pfeifer
Friesenwall 104
50672 Köln
Mobil: +49-(0)170-6936820
jpfeifer@gmx.de
_______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
_______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
_______________________________________________ Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
-- Stéphane Adjemian
Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
Dev mailing list Dev@dynare.org https://www.dynare.org/cgi-bin/mailman/listinfo/dev
-
Johannes Pfeifer -
Stéphane Adjemian -
Stéphane Adjemian