thr3ads.net - R help - [R] simulation [May 2011]

If this information is useful, please help other people find it:
Share via:

Stat Consult

2011-May-30 11:26 UTC

[R] simulation

Dear ALL

I want to simulate data from Multivariate normal distribution.

GE.N<-mvrnorm(25,mu,S)

S <-matrix(rep(0,10000),nrow=100)

for( i in 1:100){sigma<-runif(100,0.1,10);S
[i,i]=sigma[i];mu<-runif(100,0,10)}

for (i in 1:20){for (j in 1:20){if (i != j){S [i,j]=0.3*sigma[i]*sigma[j]}}}

for (i in 21:40){for (j in 21:40){if (i != j){S
[i,j]=0.3*sigma[i]*sigma[j]}}}

for (i in 41:60){for (j in 41:60){if (i != j){S
[i,j]=0.3*sigma[i]*sigma[j]}}}

for (i in 61:80){for (j in 61:80){if (i != j){S
[i,j]=0.3*sigma[i]*sigma[j]}}}

for (i in 81:100){for (j in 81:100){if (i != j){S
[i,j]=0.3*sigma[i]*sigma[j]}}}

How should I do when S is not positive definite matrix?

I saw this error: 'Sigma' is not positive definite.


best regards,

Gulia

	[[alternative HTML version deleted]]

Stat Consult

2011-Jun-06 06:50 UTC

head link

[R] simulation

Dear ALL
I want to simulate data from Multivariate normal distribution.
GE.N<-mvrnorm(25,mu,S)
S <-matrix(rep(0,10000),nrow=100)
for( i in 1:100){sigma<-runif(100,0.1,10);S
[i,i]=sigma[i];mu<-runif(100,0,10)}
for (i in 1:20){for (j in 1:20){if (i != j){S [i,j]=0.3*sigma[i]*sigma[j]}}}
for (i in 21:40){for (j in 21:40){if (i != j){S
[i,j]=0.3*sigma[i]*sigma[j]}}}
for (i in 41:60){for (j in 41:60){if (i != j){S
[i,j]=0.3*sigma[i]*sigma[j]}}}
for (i in 61:80){for (j in 61:80){if (i != j){S
[i,j]=0.3*sigma[i]*sigma[j]}}}
for (i in 81:100){for (j in 81:100){if (i != j){S
[i,j]=0.3*sigma[i]*sigma[j]}}}
How should I do when S is not positive definite matrix?
I saw this error: 'Sigma' is not positive definite.

best regards,
Sara

	[[alternative HTML version deleted]]

R help - May 2011 - simulation

[R] simulation

[R] simulation