Examine generalized lambda distribution fitting performance: An application to extreme share return in Malaysia

Understand the extreme volatility in the market is important for the investor to make a correct prediction. This paper evaluated the performance of generalized lambda distribution (GLD) by comparing with the popular probability distribution namely generalized extreme value (GEV), Generalized logisti...

Full description

Saved in:
Bibliographic Details
Main Authors: Marsani, Muhammad Fadhil, Shabri, Ani, Mat Jan, Nur Amalina
Format: Article
Language:English
Published: Penerbit UTM Press 2017
Subjects:
Online Access:http://eprints.utm.my/id/eprint/81294/1/MuhammadFadhilMarsani2017_ExamineGeneralizedLambdaDistributionFittingPerformance.pdf
http://eprints.utm.my/id/eprint/81294/
http://dx.doi.org/10.11113/mjfas.v13n3.599
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Understand the extreme volatility in the market is important for the investor to make a correct prediction. This paper evaluated the performance of generalized lambda distribution (GLD) by comparing with the popular probability distribution namely generalized extreme value (GEV), Generalized logistic (GLO), generalized Pareto (GPA), and Pearson (PE3) using Kuala Lumpur composite index stock return data. The parameter for each distribution estimated using the L-moment method. Based on k-sample Anderson darling goodness of fit test, GLD performs well in weekly maximum and minimum period. Evidence for preferring GLD as an alternative to extreme value theory distribution also described.