similar to: Kalman Filtering with Singular State Noise Covariance Matrix

Inicio del mensaje reenviado: > De: Arnau Mir <arnau.mir@uib.es> > Fecha: 14 de noviembre de 2011 13:24:31 GMT+01:00 > Para: Martin Maechler <maechler@stat.math.ethz.ch> > Asunto: Re: [R] How to compute eigenvectors and eigenvalues? > > Sorry, but I can't explain very well. > > > The matrix 4*mp is: > > 4*mp > [,1] [,2] [,3] > [1,]

Hi all R gurus out there, Im a kind of newbie to kalman-filters after some research I have found that the dlm package is the easiest to start with. So be patient if some of my questions are too basic. I would like to set up a beta estimation between an asset and a market index using a kalman-filter. Much littarture says it gives superior estimates compared to OLS estimates. So I would like to

Can somebody help me with the following issue (SEM in R), please:   When I run the model (includes second order models) in R, it gives me the following:   1)       In sem.default(ram = ram, S = S, N = N, param.names = pars, var.names = vars,  :   Could not compute QR decomposition of Hessian. Optimization probably did not converge.   2)       I have aliased parameters and NaNS   or sometimes when

  Hello All,   I am working with dlm for the purpose of estimating and forecasting with a Kalman filter model. I have succesfully set up the model and started generating results. Of course, I need to somehow be sure that the results make sense. Without any apparent target to compare with, my natural selection is the results by odinary least square. The idea being that if I choose a diffuse prior,

I am trying to check the results from an Eigen decomposition and I need to force a scalar multiplication. The fundamental equation is: Ax = lx. Where 'l' is the eigen value and x is the eigen vector corresponding to the eigenvalue. 'R' returns the eigenvalues as a vector (e <- eigen(A); e$values). So in order to 'check' the result I would multiply the eigenvalues

Hello to everybody, I have a quadratic programming problem that I am trying to solve by various methods. One of them is to use the quadprog package in R. When I check positive definiteness of the D matrix, I get that one of the eigenvalues is negative of order 10^(-8). All the others are positive. When I set this particular eigenvalue to 0.0 and I recheck the eigenvalues in R, the last

but maybe of use to some: http://gifi.stat.ucla.edu/psychoR/derivatives Computes generalized eigenvalue solutions Ax=\lambda Bx and generalized singular value solutions Rz=\gamma Px and R'x=\gamma Qy for matrices that are differentiable functions of a vector of parameters. Along with the decomposition the code returns arrays with all first-order partial derivatives of the values/vector wrt

I have built a Kalman Filter model for flu forecasting as shown below. Y - Target Variable X1 - Predictor1 X2 - Predictor2 While forecasting into the future, I will NOT have data for all three variables. So, I am predicting X1 and X2 using two Kalman filters. The code is below x1.model <- dlmModSeas(52) + dlmModPoly(1, dV=5, dW=10) x2.model <- dlmModSeas(52) + dlmModPoly(1, dV=10,

Dear all, I am currently trying to use the "dlm" package for Kalman filtering. My model is very simple: Y_t = F'_t Theta_t + v_t Theta_t = G_t Theta_t-1 + w_t v_t ~ N(0,V_t) = N(0,V) w_t ~ N(0,W_t) = N(0,W) Y_ t is a univariate time series (1x1) F_t is a vector of factor returns (Kx1) Theta_t is the state vector (Kx1) G_t is the identity matrix My first

Dear Peter, thank you very much for your answer. My problem is that I need to calculate the following quantity: solve(chol(A)%*%Y) Y is a 3*3 diagonal matrix and A is a 3*3 matrix. Unfortunately one eigenvalue of A is negative. I can anyway take the square root of A but when I multiply it by Y, the imaginary part of the square root of A is dropped, and I do not get the right answer. I tried

1. Martin Maechler's comments should be taken as replacements for anything I wrote where appropriate. Any apparent conflict is a result of his superior knowledge. 2. 'eigen' returns the eigenvalue decomposition assuming the matrix is symmetric, ignoring anything in m[upper.tri(m)]. 3. The basic idea behind both posdefify and nearPD is to compute the

Thanks for your message! Actually it works quite well for me too. If I then take the trace of the final result below, I end up with a number made up of both a real and an imaginary part. This does not probably mean much if the trace of the matrix below givens me info about the degrees of freedom of a model... Simona >----Messaggio originale---- >Da: RVaradhan at jhmi.edu >Data:

Hi, I am using eigen to get an eigen decomposition of a square, symmetric matrix. For some reason, I am getting a column in my eigen vectors (the 52nd column out of 601) that is a column of all NAs. I am using the option, symmetric=T for eigen. I just discovered that I do not get this behavior when I use the option EISPACK=T. With EISPACK=T, the 52nd eigenvector is (up to rounding error) a

Hello, could anyone explain what am I doing wrong. When I use colldiag function from package perturb I get different Variance Decomposition Proportions matrix in R than in SAS, although the eigenvalues and indexes are the same. Thanks for your attention. Results: in R: eigen(cor(indep2)) $values [1] 4.197131e+00 6.674837e-01 9.462858e-02 4.070314e-02 5.323022e-05 colldiag(indep2,c=T)

Dear all, I encounter some covariance matrix with quite small eigenvalues (around 1e-18), which are smaller than the machine precision. The dimension of my matrix is 17. Here I just fake some small matrix for illustration. a<-diag(c(rep(3,4),1e-18)) # a matrix with small eigenvalues b<-matrix(1:25,ncol=5) # define b to get an orthogonal matrix b<-b+t(b) bb<-eigen(b,symmetric=T)

I should have remembered that there was a problem with eigen() in 0.64.0. In the patched versions of R-release (available under src/devel at the CRAN sites) that bug has been fixed. In case anyone else is interested, I redid the determinant calculations in Version 0.64.0 Patched (unreleased snapshot) (April 19, 1999) using the method from Stephan Steinhaus's script (det0), the method based

Hi, I have just seen Stefan Steinhaus' web page : http://www.uni-franfurt.de/~stst/ncrunch.html I think it would be nice to include "R" as well. I have taken Forrest Young's email on stat-lisp list and changed the stuff for "R" :) Here it is: (someone please check this so we can also send it to Stefan Steinhaus.

Hi, I want to simulate a data set with similar covariance structure as my observed data, and have calculated a covariance matrix (dimensions 8368*8368). So far I've tried two approaches to simulating data: rmvnorm from the mvtnorm package, and by using the Cholesky decomposition (http://www.cerebralmastication.com/2010/09/cholesk-post-on-correlated-random-normal-generation/). The problem is

>From: "Ivaha C (AT)" <civaha at glam.ac.uk> >Date: 2008/04/10 Thu AM 08:51:14 CDT >To: R Help <r-help at r-project.org> >Subject: [R] Structural Modelling in R-project if you have a univariate time series and you want to break it into its various components, then you get the scalars based on a decomposition. if you have a kalman filter/ basic strucutural

Hi, the function makeARIMA(), designed to construct some state space representation of an ARIMA model, uses a C function called getQ0, which can be found at the end of arima.c in R source files (library stats). getQ0 takes two arguments, phi and theta, and returns the covariance matrix of the state prediction error at time zero. The reference for getQ0 (cited by help(arima)) is: