Hello,
I am wanting to run a simulation study in R comparing several different
bandwidth selection methods for data simulated from several different
distribution types (normal, lognormal, bimodal, etc.) and wanted to know how
to calculate the mean integrated square errors for the optimal smoothing
parameter values. Does anyone have insight on this? Also, I believe in
simulating this type of data and trying to solve for the optimal bandwidth
parameter some type of grid search may be necessary, does anyone have any
insight into this as well?
Thanks for your consideration.
--
View this message in context:
http://r.789695.n4.nabble.com/Kernel-Density-Estimation-in-R-tp3784714p3784714.html
Sent from the R help mailing list archive at Nabble.com.
