I want to generate multiple multivariate normal samples with different
mean vectors
and common covariance matrix.
I can do this with a loop, but can't quite figure out how to do it with
apply and friends.
In the example below, I want values to have 3 columns: group, x, y
# number of groups, and group means
x <- jitter(seq(2,10,by=2))
y <- x + rnorm(length(x), 0, .5)
means <- cbind(x,y)
Sigma <- matrix(c(6,3,3,2),2,2)
# loop version
n<- 10
values <- NULL
for (i in 1:length(x)) {
val <- mvrnorm(n, means[i,], .5*Sigma, empirical=TRUE)
values <- rbind(values, val)
}
group <- factor(rep(letters[1:length(x)], each=n))
values <- cbind(group=group, values)
> str(values)
num [1:50, 1:3] 1 1 1 1 1 1 1 1 1 1 ...
- attr(*, "dimnames")=List of 2
..$ : NULL
..$ : chr [1:3] "group" "x" "y"
# trying apply
vals <- apply(means, 1, function(x) mvrnorm(n, x, Sigma, empirical=TRUE))
str(vals)
head(vals)
But this gives me a 20 x 5 matrix, with the groups as columns and 10
pairs of rows
representing x, y values.
> str(vals)
num [1:20, 1:5] 4.055 -0.124 3.469 -1.169 0.872 ...
> head(vals)
[,1] [,2] [,3] [,4] [,5]
[1,] 4.0551667 4.640607 8.448465 11.795849 12.117418
[2,] -0.1242431 2.480197 7.496188 3.140649 11.473915
[3,] 3.4688356 -0.415469 5.709368 8.188018 6.832460
[4,] -1.1691558 6.579454 2.153095 10.607982 9.053140
[5,] 0.8722773 5.121265 2.168577 7.392535 6.557844
[6,] 7.2737826 2.583776 9.490320 8.144200 11.243709
>
--
Michael Friendly Email: friendly AT yorku DOT ca
Professor, Psychology Dept.
York University Voice: 416 736-5115 x66249 Fax: 416 736-5814
4700 Keele Street Web: http://www.datavis.ca
Toronto, ONT M3J 1P3 CANADA
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
