Search String: Display: Description: Sort:

Results:

References: [ +from:ezivot@u.washington.edu: 53 ]

Total 53 documents matching your query.

1. Re: Hidden Markov Models (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Wed, 3 May 2006 08:00:47 -0700
You can estimate hidden markov models using the state space functions in S+FinMetrics 2.0. The state space functions allow Markov regime switching in the state space system matrices. Estimation, filt
/archives/html/s-news/2006-05/msg00006.html (10,534 bytes)

2. book and website announcement (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Mon, 13 Mar 2006 10:05:46 -0800
G
/archives/html/s-news/2006-03/msg00045.html (8,102 bytes)

3. Re: calculating the hessian in a non-Gauss ssf (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Tue, 24 Jan 2006 12:56:32 -0800
For non Gaussian models, the Kalman filter is just the best linear forecasting model and is not the optimal filter. The likelihood estimation based on the normal distribution should be interpreted as
/archives/html/s-news/2006-01/msg00074.html (9,195 bytes)

4. Re: GMM estimation (score: 1)
Author: Eric Zivot <ezivot@u.washington.edu>
Date: Thu, 1 Dec 2005 10:12:53 -0800 (PST)
S+FinMetrics 2.0 contains a function gmm() for doing general linear and nonlinear GMM estimation. The function is very flexible. All you need to do is specify a function to compute the moment conditi
/archives/html/s-news/2005-12/msg00001.html (9,165 bytes)

5. Re: how to estimate var in multivariate state space (score: 1)
Author: cn>
Date: Tue, 27 Dec 2005 12:08:51 -0800
S+FinMetrics can handle a multivariate state space model. The specification of the measurement and transition equations allow for a multivariate response. I have some examples (see the term structur
/archives/html/s-news/2005-12/msg00083.html (8,506 bytes)

6. Re: Quick Question (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Tue, 16 Aug 2005 22:06:07 -0700
t
/archives/html/s-news/2005-08/msg00065.html (10,132 bytes)

7. Re: AR for short, not equally spaced TS (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Wed, 22 Jun 2005 10:41:33 -0700
One way to think of the irregular spacing is in terms of missing data. The true process works on equally spaced data but you ony observe data on specific dates. An AR type model can be fit using Kalm
/archives/html/s-news/2005-06/msg00080.html (9,056 bytes)

8. Re: S-Plus Finmetric (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Mon, 2 May 2005 09:34:55 -0700
The S+FinMetrics generic IC() will compute various information criteria (AIC, BIC, HQ and logLike) for various model fit objects. For example, IC.OLS() computes info criteria for OLS objects and IC.d
/archives/html/s-news/2005-05/msg00004.html (9,183 bytes)

9. Re: R Metrics for SPLUS? (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Fri, 27 May 2005 09:07:10 -0700
r
/archives/html/s-news/2005-05/msg00165.html (7,848 bytes)

10. Re: Splus book on Artificial Neural Network (score: 1)
Author: Eric Zivot <ezivot@u.washington.edu>
Date: Tue, 4 Jan 2005 09:00:11 -0800 (PST)
the book Analysis of Financial Time Series by Ruey Tsay (Wiley, 2002?) has a chapter on nonlinear modles including neural networks. For his examples he uses the nnet() function from the MASS library.
/archives/html/s-news/2005-01/msg00015.html (8,878 bytes)

11. Re: chol error in Finmetric's SUR (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Mon, 19 Apr 2004 14:11:38 -0700
The problem is not in FinMetrics but in the S-PLUS function chol() and the type of Intel processor (P3, P4 etc). The function chol() is very sensitive to small departures from symmetric. The trick of
/archives/html/s-news/2004-04/msg00098.html (11,448 bytes)

12. Re: Large data sets (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Tue, 27 Apr 2004 11:33:21 -0700
I believe that Splus 6.2 has a native interface to SQL server so that S-PLUS ODBC is no longer required. "Large" data set is all relative. Some people might think 1Mb is large, but that's actually ti
/archives/html/s-news/2004-04/msg00129.html (10,206 bytes)

13. m (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Tue, 6 Jan 2004 12:57:51 -0800
<?xml version="1.0" ?> Wolfgang You are not using the function aggregateSeries correctly. You should only be passing one time series (your ts). Your aggregation positions should be specified using a
/archives/html/s-news/2004-01/msg00018.html (11,198 bytes)

14. Re: Urgent:Putting legends on timeseries plots (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Wed, 5 Nov 2003 08:13:46 -0800
The plot method for timeSeries objects, plot.timeSeries, works a bit differently than the other plot methods. To specify line types, colors etc you must use the plot.args() argument. For example, to
/archives/html/s-news/2003-11/msg00029.html (9,397 bytes)

15. Re: Dickey Fuller (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Mon, 13 Oct 2003 07:58:00 -0700
Dickey-Fuller tests are implemented in S+FinMetrics and the R package tseries. However, the DF unit root test is just a simple regression with lagged regressors and can be done using lm. You would ha
/archives/html/s-news/2003-10/msg00122.html (9,573 bytes)

16. Re: [splus] granger causality (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Sun, 19 Oct 2003 12:25:32 -0700
/archives/html/s-news/2003-10/msg00191.html (8,185 bytes)

17. Re: a movjng average median (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Mon, 20 Oct 2003 13:58:48 -0700
g average as shown bel
/archives/html/s-news/2003-10/msg00201.html (10,603 bytes)

18. Re: Seemingly Unrelated Regression - Systemfit (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Fri, 12 Sep 2003 12:39:23 -0700
The SUR and NLSUR functions in Insightful's FinMetrics module can be used to fit linear and nonlinear seemingly unrelated regressions. Dear S-Plus users, I would like to perform a SUR-analysis in S-P
/archives/html/s-news/2003-09/msg00077.html (8,302 bytes)

19. Re: Principal Components Analysis on factor data. (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Wed, 27 Aug 2003 13:53:53 -0700
Sounds like you need to use a probabilistic discrete choice model (e.g. multinomial logit/probit or ordered logit/probit model). Insightful is developing a module for such analysis. Contact me if you
/archives/html/s-news/2003-08/msg00149.html (8,666 bytes)

20. Re: Simultaneously estimated nested logit (score: 1)
Author: "Eric Zivot" <ezivot@u.washington.edu>
Date: Wed, 27 Aug 2003 20:54:35 -0700
Ken Train has Gauss code for estimating a nested logit model using full information maximum likelihood on his UC Berkeley webpage (http://elsa.berkeley.edu/~train/ps.html). I believe the nested logit
/archives/html/s-news/2003-08/msg00153.html (13,231 bytes)


This search system is powered by Namazu