1) The Pareto P(alfa) distribution is defined by its density f(x|alfa)
=alfa*X^(-alfa-1) over (1 to infinity). Show that it can be generated as the
-1/alfa power of a uniforme variate. Plot the histogram and the density.
2) The Poisson distribution P(lambda) is connected to the exponential
distribution through the Poisson process in that it can be simulated by
generating exponential random variables until their sums exceeds 1. That is, if
Xi~Exp(lambda) and if K is the first value for which summation(i=1 to k+1)Xi>1
então K~P(lambda). Compare this algorithm with rpois.
3) Se U e V are i.i.d U[0,1], the distribuiton of
(U^1/alfa)/((U^1/alfa)+V(1/beta)), conditional on U^1/alfa+V^1/beta<=1, is the
beta(alfa, beta) distribution. Compare this algorithm for both small and large
values of alfa and beta.
[[alternative HTML version deleted]]
______________________________________________
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.
