AS far as I know what you say is correct. Be careful. The mater is
more confusing as what many texts define as Kurtosis is in effect what
Gretl calls excess kurtosis (i.e. the fourth standardised moment -3)
and not the fourth standardised moment.
Best Regards
John
On 7 March 2012 21:57, Peter Tozer <prexpsu(a)hotmail.com> wrote:
Dear All,
This may seem a simple question, but is the excess kurtosis value calculated
by GRETL in the summary statistics command, the excess above the value 3,
which is the kurtosis value of a normal curve, i.e. if I have an excess
kurtosis value of 3.12, does that mean the kurtosis value is 6.12. I would
like to know as I am trying to determine if several distributions I have are
significantly different from the normal distributions and the tests depend
on the value of the kurtosis not the excess kurtosis, which in GRETL may or
may not be the same.
Thanks in advance
Peter
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
--
John C Frain
Economics Department
Trinity College Dublin
Dublin 2
Ireland
www.tcd.ie/Economics/staff/frainj/home.html
mailto:frainj@tcd.ie
mailto:frainj@gmail.com