[R] did my searching but still couldn't find anything for bayesian dlm
I familarized myelf with kalmanlike and structts which are approaches for building and estimating ( and forecasting ) state space models ( or the equivalent arima models ). back in 2003, gavin simpson wrote an email describing the west and harrison apprach to estimate state space models and asked if anything was out there for using that approach. the goals of this approach are the same as kalman like and structts but priors are put on the variances and a bayesian approach is used to estimate the next "state". in this manner, , all numerical optimization is avoided ( but obviously the results are different also so it's not necessarily a "better" approach. just different ). i'm dealing with minute by minute data so , for me, it's essential to avoid computing likelihoods over and over. is it possible, that , since gavin's email, the west and harrison approach has been built in one of the many packages out there. i looked really hard but i couldn't find it. my guess is that the answer is no. thanks for any input. mark This is not an offer (or solicitation of an offer) to buy/sell the securities/instruments mentioned or an official confirmation. Morgan Stanley may deal as principal in or own or act as market maker for securities/instruments mentioned or may advise the issuers. This is not research and is not from MS Research but it may refer to a research analyst/research report. Unless indicated, these views are the author's and may differ from those of Morgan Stanley research or others in the Firm. We do not represent this is accurate or complete and we may not update this. Past performance is not indicative of future returns. For additional information, research reports and important disclosures, contact me or see https://secure.ms.com/servlet/cls. You should not use e-mail to request, authorize or effect the purchase or sale of any security or instrument, to send transfer instructions, or to effect any other transactions. We cannot guarantee that any such requests received via ! e-mail will be processed in a timely manner. This communication is solely for the addressee(s) and may contain confidential information. We do not waive confidentiality by mistransmission. Contact me if you do not wish to receive these communications. In the UK, this communication is directed in the UK to those persons who are market counterparties or intermediate customers (as defined in the UK Financial Services Authority's rules). [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] did my searching but still couldn't find anything for bayesian dlm
On Tue, 2006-10-31 at 19:12 -0500, Leeds, Mark (IED) wrote: > I familarized myelf with kalmanlike and structts which are approaches > for building and estimating ( and forecasting ) state space models ( or > the equivalent arima models ). > back in 2003, gavin simpson wrote an email describing the west and > harrison apprach to estimate state space models and asked if anything > was out there for > using that approach. the goals of this approach are the same as kalman > like and structts but priors > are put on the variances and a bayesian approach is used to estimate the > next "state". in this manner, , all numerical optimization is avoided ( > but obviously the results are different also so it's not necessarily a > "better" approach. just different ). > > i'm dealing with minute by minute data so , for me, it's essential to > avoid computing likelihoods over and over. is it possible, that , since > gavin's email, the west and harrison approach has been built in one of > the many packages out there. i looked really hard but i couldn't find > it. > my guess is that the answer is no. thanks for any input. Not sure how far the Bayesian bit has advanced, but DLMs are now becoming part of R in add-on packages sspir and dlm, thanks to a number of people, Claus Dethlefsen and Søren Lundbye-Christensen (sspir), and Giovanni Petris (dlm). IIRC, I saw some of Giovanni's materials from his website that contains information about doing Bayesian analysis with his dlm package, but I don't have the link on my home PC to confirm this. Whether these will be suitable for your use, I don't know. All the best, G > > > mark > > > This is not an offer (or solicitation of an offer) to buy/sell the > securities/instruments mentioned or an official confirmation. Morgan Stanley > may deal as principal in or own or act as market maker for > securities/instruments mentioned or may advise the issuers. This is not > research and is not from MS Research but it may refer to a research > analyst/research report. Unless indicated, these views are the author's and > may differ from those of Morgan Stanley research or others in the Firm. We > do not represent this is accurate or complete and we may not update this. > Past performance is not indicative of future returns. For additional > information, research reports and important disclosures, contact me or see > https://secure.ms.com/servlet/cls. You should not use e-mail to request, > authorize or effect the purchase or sale of any security or instrument, to > send transfer instructions, or to effect any other transactions. We cannot > guarantee that any such requests received via ! > e-mail will be processed in a timely manner. This communication is solely > for the addressee(s) and may contain confidential information. We do not > waive confidentiality by mistransmission. Contact me if you do not wish to > receive these communications. In the UK, this communication is directed in > the UK to those persons who are market counterparties or intermediate > customers (as defined in the UK Financial Services Authority's rules). > > [[alternative HTML version deleted]] > > __ > R-help@stat.math.ethz.ch mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. -- %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% Gavin Simpson [t] +44 (0)20 7679 0522 ECRC [f] +44 (0)20 7679 0565 UCL Department of Geography Pearson Building [e] gavin.simpsonATNOSPAMucl.ac.uk Gower Street London, UK[w] http://www.ucl.ac.uk/~ucfagls/ WC1E 6BT [w] http://www.freshwaters.org.uk/ %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] did my searching but still couldn't find anything for bayesian dlm
thanks gavin : i'll check those out. On Wed, 1 Nov 2006, Gavin Simpson wrote: > On Tue, 2006-10-31 at 19:12 -0500, Leeds, Mark (IED) wrote: > > I familarized myelf with kalmanlike and structts which are approaches > > for building and estimating ( and forecasting ) state space models ( or > > the equivalent arima models ). > > back in 2003, gavin simpson wrote an email describing the west and > > harrison apprach to estimate state space models and asked if anything > > was out there for > > using that approach. the goals of this approach are the same as kalman > > like and structts but priors > > are put on the variances and a bayesian approach is used to estimate the > > next "state". in this manner, , all numerical optimization is avoided ( > > but obviously the results are different also so it's not necessarily a > > "better" approach. just different ). > > > > i'm dealing with minute by minute data so , for me, it's essential to > > avoid computing likelihoods over and over. is it possible, that , since > > gavin's email, the west and harrison approach has been built in one of > > the many packages out there. i looked really hard but i couldn't find > > it. > > my guess is that the answer is no. thanks for any input. > > Not sure how far the Bayesian bit has advanced, but DLMs are now > becoming part of R in add-on packages sspir and dlm, thanks to a number > of people, Claus Dethlefsen and Søren Lundbye-Christensen (sspir), and > Giovanni Petris (dlm). > > IIRC, I saw some of Giovanni's materials from his website that contains > information about doing Bayesian analysis with his dlm package, but I > don't have the link on my home PC to confirm this. > > Whether these will be suitable for your use, I don't know. > > All the best, > > G > > > > > > > mark > > > > > > This is not an offer (or solicitation of an offer) to buy/sell the > > securities/instruments mentioned or an official confirmation. Morgan > > Stanley may deal as principal in or own or act as market maker for > > securities/instruments mentioned or may advise the issuers. This is not > > research and is not from MS Research but it may refer to a research > > analyst/research report. Unless indicated, these views are the author's > > and may differ from those of Morgan Stanley research or others in the Firm. > > We do not represent this is accurate or complete and we may not update > > this. Past performance is not indicative of future returns. For > > additional information, research reports and important disclosures, contact > > me or see https://secure.ms.com/servlet/cls. You should not use e-mail to > > request, authorize or effect the purchase or sale of any security or > > instrument, to send transfer instructions, or to effect any other > > transactions. We cannot guarantee that any such requests received v ia ! > > e-mail will be processed in a timely manner. This communication is solely > > for the addressee(s) and may contain confidential information. We do not > > waive confidentiality by mistransmission. Contact me if you do not wish to > > receive these communications. In the UK, this communication is directed in > > the UK to those persons who are market counterparties or intermediate > > customers (as defined in the UK Financial Services Authority's rules). > > > > [[alternative HTML version deleted]] > > > > __ > > R-help@stat.math.ethz.ch mailing list > > https://stat.ethz.ch/mailman/listinfo/r-help > > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > > and provide commented, minimal, self-contained, reproducible code. > __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
