From: Dennis Shea <shea_at_nyahnyahspammersnyahnyah>

Date: Tue, 19 Sep 2006 14:40:05 -0600 (MDT)

Date: Tue, 19 Sep 2006 14:40:05 -0600 (MDT)

*>My question:
*

*>In NCL, how do you random vectors (gaussian) with Lognormal distribution?
*

*>How can I display a histogram of probability density function?
*

*>
*

*>I see the commands for cumulative distribution function. Can I create
*

*>a pdf histogram of such data in NCL?
*

*>
*

*>Any suggestion would be greatly appreciated.
*

*>_______________________________________________
*

*>
*

NCL does not have a built-in function to generate

numbers with a log-normal distribution.

If you have the NAG math libraries available

you can use the G05DEF function to generate

a log-normal distribution.

--- On the other hand ... lognormal variables are those whose logarithms follow normal distributions. Seems to me that you could use random_normal to generate numbers with a normal distribution http://www.ncl.ucar.edu/Document/Functions/Built-in/random_normal.shtml av = 10.0 sd = 3.0 nor = random_normal(av, sd, (/100/)) ; nor(1000) then lognor = exp( nor ) ; lognormal <== exponetial(normal) ------ plot the lognor using histograms. http://www.ncl.ucar.edu/Applications/histo.shtml _______________________________________________ ncl-talk mailing list ncl-talk_at_ucar.edu http://mailman.ucar.edu/mailman/listinfo/ncl-talkReceived on Tue Sep 19 2006 - 14:40:05 MDT

*
This archive was generated by hypermail 2.2.0
: Mon Sep 25 2006 - 11:45:06 MDT
*