The multivariate lognormal distribution
Generates random amounts with a multivariate lognormal distribution, or gives the density of that distribution at a given point.
rlnorm.rplus(n,meanlog,varlog) dlnorm.rplus(x,meanlog,varlog)
n |
number of datasets to be simulated |
meanlog |
the mean-vector of the logs |
varlog |
the variance/covariance matrix of the logs |
x |
vectors in the sample space |
rlnorm.rplus gives a generated random dataset of class
"rplus" following a
lognormal distribution with logs having mean meanlog and
variance varlog.
dlnorm.rplus gives the density of the distribution with respect
to the Lesbesgue measure on R+ as a subset of R.
The main difference between rlnorm.rplus and
rnorm.aplus
is that rlnorm.rplus needs a logged mean. The additional difference
for the calculation of the density by dlnorm.rplus and
dnorm.aplus is the reference measure (a log-Lebesgue one in the
second case).
K.Gerald v.d. Boogaart http://www.stat.boogaart.de, Raimon Tolosana-Delgado
Aitchison, J. (1986) The Statistical Analysis of Compositional
Data Monographs on Statistics and Applied Probability. Chapman &
Hall Ltd., London (UK). 416p.
MyVar <- matrix(c( 0.2,0.1,0.0, 0.1,0.2,0.0, 0.0,0.0,0.2),byrow=TRUE,nrow=3) MyMean <- c(1,1,2) plot(rlnorm.rplus(100,log(MyMean),MyVar)) plot(rnorm.aplus(100,MyMean,MyVar)) x <- rnorm.aplus(5,MyMean,MyVar) dnorm.aplus(x,MyMean,MyVar) dlnorm.rplus(x,log(MyMean),MyVar)
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.