Fitting Malaysian wind speed via log-normal distribution

Lognormal is one of the distributions in the family of the extreme distribution type. The lognormal distribution is a single tailed probability distribution of any random variables whose logarithm is normally distributed. As may be concluded by the name, the lognormal distribution has certain simil...

Full description

Bibliographic Details
Main Authors: Mohamed, N.S., Kamisan, N.A.B., Zubairi, Y.Z., Hussin, A.G.
Format: Conference or Workshop Item
Language:English
Published: 2008
Subjects:
Online Access:http://eprints.um.edu.my/9308/1/All.pdf
Description
Summary:Lognormal is one of the distributions in the family of the extreme distribution type. The lognormal distribution is a single tailed probability distribution of any random variables whose logarithm is normally distributed. As may be concluded by the name, the lognormal distribution has certain similarities to the normal distribution and describes many naturally occurring populations; for example, lognormal distribution has been used in many disciplines such as economics, life sciences and meteorology. Thus paper evaluates the performance of lognormal as a model to describe the Malaysian annual maximum wind speed for four locations (Alor Setar, Langkawi, Melaka and Senai). Based on rigorous tests of root mean square error, mean absolute error, and mean absolute percentage error and density plots, the results suggest that the lognormal is an adequate model in describing the maximal wind speed, thus contributing towards a better understanding of extreme wind behavior via robust statistical model.