Hi,
You assumed
scale=229678.21 and shape=0.41
and the procedure estimated
\hat{scale}=427196.6 and \hat{shape}=0.2092887
I think these estimates are natural, since
1) you use a simulated generated data with n=100, and 2) the true value your
scale parameter is very large.
Hope this helps
Be
Hi,
I have a problem in fitting GPD distribution.
i generate random numbers from gpd distribution from specific parameters
using pot packege then i used fitgpd function to estimete the parameters.The
estimated parameters are not matched with the given parameters i.e.from
which i generate random nu
I'm not particularly familiar with EVT but it seems that here the term
exists to scale down the time base to that wherein extreme values were
identified. Just a hunch though...
If you want more accurate clarification you may wish to contact the
package maintainer, but to be honest I wouldn't worry
> npy <- length(events1[, "obs"])/(diff(range(ardieres[, "time"],
+ na.rm = TRUE)) - diff(ardieres[c(20945, 20947), "time"]))
This line is from the mannual "A user's Guide to POT Approach". I am just
trying to ask why the values 20945, 20947 are used??
Regards
On Fri, Oct 21, 2011 at 4:19 PM, R.
Perhaps you could tell us what function you are talking about npy
is not part of the POT package in the version on my machine and those
letters don't seem to show up anywhere consecutively at all on my
system, according to ??npy. Similarly, this trick produces no results:
sapply(ls("package:PO
Hi Sir
It is requested to please tell the reason why the range of c(20945, 209547)
is used in this function
> npy <- length(events1[, "obs"])/(diff(range(ardieres[, "time"],
+ na.rm = TRUE)) - diff(ardieres[c(20945, 20947), "time"]))
Please tell logic.
Looking for quick response.
Regards
--
This may be a simple misunderstanding on my part, but I need help
understanding what POT is plotting. I'm trying to analyze a few different
datasets. If my dataset covers 500 years, but I have 60 points above my
threshold, what should be plotted as the (empirical) return period for the
largest valu
7 matches
Mail list logo