An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-devel/attachments/20111122/cb22e7b4/attachment.pl>
Generate Simulation
2 messages · savina partheni, Joris Meys
Not to be rude, but I'd suggest you first read the posting guide for the mailing lists again. The r-devel list is not meant to be used as a help forum. https://stat.ethz.ch/mailman/listinfo/r-devel This said, look at ?replicate. Cheers Joris
On Tue, Nov 22, 2011 at 4:08 PM, savina partheni <s2partheni at gmail.com> wrote:
Hallo everybody,
I'm new in r and I"ll appreciate some help!
I have a matrix of nrow=30 and ncoll=54,and I would like to generate 50
simulations with tha same size of the matrix!!!That is to say that I want
to generate 50 matrices -for my 50 simulations - with the same dimensions!
I took my 1st matrix according to the formula that I want to implement:
D<-mean_m + U_i*mat_DELTA
mean_m:vector
U_I:vector
mat_Delta:matrix(54,30)
Here is the loop:
#Define Simulations(IS)
?#Define Time Step(IT)
vec_IS<-c(1:50)
vec_IT<-c(1:30)
mat_delta<-matrix(nrow=54, ncol=30)
mat_DELTA<-matrix(nrow=54, ncol=30)
mat_Yr_m<-matrix(nrow=54, ncol=30)
D<-matrix(nrow=30, ncol=54)
DELTA<-(matrix(nrow=30,ncol=54))*50
for (i in 1:length(vec_IS)){
? ? ? ?for (j in 1:length(vec_IT)){
? ? ? ? ? ? ? ?Yr_m<-rnorm(54,m=0,sd=1)
? ? ? ? ? ? ? ?mat_Yr_m[,j]<-Yr_m
? ? ? ? ? ? ? ?delta_i<-lower_m%*%mat_Yr_m[,j]
? ? ? ? ? ? ? ?mat_delta[,j]<-as.vector(delta_i)
? ? ? ?}
? ? ? ?DELTA_1<-mat_delta[,1]
? ? ? ?DELTA_2<-mat_delta[,2]-a_1*mat_delta[,1]
? ? ? ? ? ? ? ?for (t in 3:length(vec_IT)){
? ? ? ? ? ? ? ? ? ? ? ?mat_DELTA[,t]<-mat_delta[,t] - a_1*mat_delta[,t-1]
- a_2*mat_delta[,t-2]
? ? ? ? ? ? ? ?}
? ? ? ? ? ? ? ?mat_DELTA[,1]<-DELTA_1
? ? ? ? ? ? ? ?mat_DELTA[,2]<-DELTA_2
? ? ? ? ? ? ? ? ? ? ? ?for (k in 1:length(nmesh)){
? ? ? ? ? ? ? ? ? ? ? ?mean_m<-as.numeric(vec_mean_col)
? ? ? ? ? ? ? ? ? ? ? ?DELTA<-U_i*mat_DELTA
? ? ? ? ? ? ? ? ? ? ? ?D<-mean_m + t(DELTA)
? ? ? ? ? ? ? ?}
? ? ? ?}
I want to implement this formula for 50 simulations!
any idea?
Thanks a lot!
? ? ? ?[[alternative HTML version deleted]]
______________________________________________ R-devel at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-devel
Joris Meys Statistical consultant Ghent University Faculty of Bioscience Engineering Department of Mathematical Modelling, Statistics and Bio-Informatics tel : +32 9 264 59 87 Joris.Meys at Ugent.be ------------------------------- Disclaimer : http://helpdesk.ugent.be/e-maildisclaimer.php