Sum of population-weighted PDF objects.

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

Sum of population-weighted PDF objects.

arus.rm
This post has NOT been accepted by the mailing list yet.
Hi. I need to calculate an aggregated distribution as the population-weighted sum of the subgroup densities. The underlying distributions are assumed to be Weibulls. I have Weibull parameters (a,b) and population weights (w) in vectors as in: a=c(1.12,1.44,1.56,...); b=c(3345.5,4667.2,12987.1,...); w=c(0.227,0.217,0.05,..); To calculate the aggregated (y) i used the following codes: p=seq(0,100000,length.out=500000); y= rep(0,length(p)); for (i in 1:n) { y = y + w[i]*dweibull(p, shape=a[i], scale=b[i] } However, I am not perfectly sure of my results. I expected to see more "humps" where bigger subgroups' scale parameters are located. Any suggestions for improvements?