similar to: Multivariate regression with constraints

Hi all, I'd like to fit a multivariate regression with the variance of the error term porportional to the predictors, like the WLS in the univariate case. y_1~x_1+x_2 y_2~x_1+x_2 var(y_1)=x_1*sigma_1^2 var(y_2)=x_2*sigma_2^2 cov(y_1,y_2)=sqrt(x_1*x_2)*sigma_12^2 How can I specify this in R? Is there a corresponding function to the univariate specification lm(y~x,weights=x)??

Hi all, I am going to sample two variables from two exponential distributions, but I want to specify a covariance structure between these two variables. Is there any way to do it in R? Or is there a "Multivariate Exponential" thing corresponding to the multivariate normal? Thanks in advance. Sincerely, Yanwei Zhang Department of Actuarial Research and Modeling Munich Re America Tel:

Hi all, I have a 4 by 4 matrix, and I want to switch row 2 and row 3 first, then switch column 2 and column 3. Is there an easy way to do it? The following is a tedious way to get what I want. But I wonder if there is a way to simplify this. > a=matrix(rnorm(16),4,4) > a [,1] [,2] [,3] [,4] [1,] 0.33833811 -0.9422273 -0.06181611 -1.8346134 [2,] -0.68167996

Hi all, Assume I have a random vector with four variables, i.e. A=(a,b,c,d). I am able to get the covariance matrix of vector A, but how can I get the covariance matrix of vector B=(a,c,b,d) by manipulating the corresponding covariance matrix of A? Thanks. Sincerely, Yanwei Zhang Department of Actuarial Research and Modeling Munich Re America Tel: 609-275-2176 Email:

Hi all, I have n independent variables A_1, A_2, A_3,......,A_n, and each with known variances var(A_1), var(A_2),..., but unknown mean. How can I get the approximation of the variance of the product of the variables using numerical computation, i.e. var(A_1*A_2*A_3*.....*A_n)? Thanks. Sincerely, Yanwei Zhang Department of Actuarial Research and Modeling Munich Re America Tel: 609-275-2176

Hi all, I met with a problem about the weighted least square regression. 1. I simulated a Normal vector (sim1) with mean 425906 and standard deviation 40000. 2. I simulated a second Normal vector with conditional mean b1*sim1, where b1 is just a number I specified, and variance proportional to sim1. Precisely, the standard deviation is sqrt(sim1)*50. 3. Then I run a WLS regression without the

Hi all, I got another VAR question here and really appreciate if somebody would help me out :) I have five time series, say A,B,C,D,E. My objective is to predict the series A using the rest, that is, B, C, D and E. A Vector Autoregression Model should work here. But first of all, I should select which series of B, C, D and E to be include in the VAR model, as well as the number of lags. I wonder

Hi all, Is there an easy way to do cumulative matrix multipliation in R? What's the syntex? Thanks. Sincerely, Yanwei Zhang Department of Actuarial Research and Modeling Munich Re America Tel: 609-275-2176 Email: yzhang@munichreamerica.com<mailto:yzhang@munichreamerica.com> [[alternative HTML version deleted]]

Dear list, I have the following matrix. How can I make the following plot? 1. The x-axis has index 1:7, and the first column is plotted against index 1, second against 2, and so on. 2. I want the points from the left upper conner including the antidiagonal to be plotted with col=2, and the rest with col=3 [,1] [,2] [,3] [,4] [,5] [,6] [,7] [1,] 0.589 0.857 0.923 0.944 0.954 0.963

Hi all, I was trying to fit a Gamma hierarchical model using "glmer", but got weird error message that I could not understand. On the other hand, a similar call to the glmmPQL leads to results that are close to what I expect. I also tried to change tha "nAGQ" argument in "glmer", but it did not solve the problem. The model I was fitting has a simple structure - one

Hi all, I have an old package installed, say "abc". Now I made some changes to the source, and built a new version of the source code "abc_0.1.1.tar.gz". How can I update the old package to this newer version from the local tar.gz file? I was running the following, but it did not work. setwd("directory where the tar.gz file locates")

Dear all, I need to compute tensor product of B-spline defined over equi-spaced break-points. I wrote my own program (it works in a 2-dimensional setting) library(splines) # set the break-points Knots = seq(-1,1,length=10) # number of splines M = (length(Knots)-4)^2 # short cut to splineDesign function bspline = function(x) splineDesign(Knots,x,outer.ok = T) # bivariate tensor product of

I've installed R-2.9.2 (64 bit), unixODBC-2.2.14-p2 (64 bit) and RODBC_1.2-5 (64 bit) on a 64 bit Redhat Linux server (Red Hat Enterprise Linux Server release 5.4 (Tikanga), x86_64) release 2.6.18-164.2.1.el5. I've tested the ODBC drive via isql and the test was success: [yzhang@ROracleTest ~]$ isql -v DRTST yzhang test +---------------------------------------+ | Connected!

Dear R-users, I learned today that there exists an interesting topic in numerical analysis names "best polynomial approximation" (BSA). Given a function f the BSA of degree k, say pk, is the polynomial such that pk=arginf sup(|f-pk|) Although given some regularity condition of f, pk is unique, pk IS NOT calculated with least square. A quick google tour show a rich field of research

Dear all, is there any way to transform a .Data directory created in S-plus 6.1 for windows in a .RData file? Thanks in advance, Patrizio Frederic

Dear R-helpers, I'm having a problem in using plot.design in Design Library. Tho following example code produce the error: > n <- 1000 # define sample size > set.seed(17) # so can reproduce the results > age <- rnorm(n, 50, 10) > blood.pressure <- rnorm(n, 120, 15) > cholesterol <- rnorm(n, 200, 25) > sex <-

library(mvtnorm) x = seq(-4,4,length=201) xy = expand.grid(x,x) sigma = (diag(c(1,1))+1)/2 d2 = matrix(dmvnorm(xy,sigma=sigma),201) xsamp = rmvnorm(200,sigma=sigma) contour(x,x,d2) points(xsamp,col=3,pch=16) pdf("pdftry.pdf") contour(x,x,d2) points(xsamp,col=3,pch=16) dev.off() postscript("pstry.ps") contour(x,x,d2) points(xsamp,col=3,pch=16) dev.off() # I can see

Dear all, I ran into problems with the function "optim" when I tried to do an mle estimation of a simple lognormal regression. Some warning message poped up saying NANs have been produced in the optimization process. But I could not figure out which part of my code has caused this. I wonder if anybody would help. The code is in the following and the data is in the attachment. da <-

hi all, I have a data frame such as: 1 blue 0.3 1 NA 0.4 1 red NA 2 blue NA 2 green NA 2 blue NA 3 red 0.5 3 blue NA 3 NA 1.1 I wish to find the last non-missing value in every 3ple: ie I want a 3 by 3 data.frame such as: 1 red 0.4 2 blue NA 3 blue 1.1 I have written a little script data = structure(list(V1 = c(1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L ), V2 = structure(c(1L, NA,

Dear all, I'm new to S4 classes and have a question on this. I want to use S4 because I want to define explicitly the slots that the new class can have. But other than that, the new class behaves exactly like a list. But this will not allow me to use the generic functions that are already defined for class "list", such as "$", "c", "[[",