Open AccessExistence of Long Memory Phenomenon in Air Pollutant Concentrations using Surrogate Data
Author(s) -
Nuryazmin Ahmat Zainuri,
Noorhelyna Razali,
Hidayatulfathi Othman,
Alias Jedi,
Noraishikin Zulkarnain
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.b6868.129219
Subject(s) - hurst exponent , value (mathematics) , surrogate data , statistics , range (aeronautics) , variance (accounting) , ozone , mathematics , environmental science , meteorology , materials science , physics , accounting , nonlinear system , quantum mechanics , business , composite material
This study investigated the existence of long memory phenomenon in air pollutant concentrations specifically the ozone concentration obtained at six monitoring stations in Peninsular Malaysia. The main objective was to select the best method in detecting the long memory. Four methods used in this study were Rescaled Range (R/S) method, Aggregated Variance (V/S) method, Aggregated Absolute Value (A/S) method and Peng’s (P/S) method. Surrogate data testing was used to verify the existence of long memory. The average estimated Hurst value obtained by using VS and PS method are found to be near to the actual Hurst value compared to RS and AS method. The biased and MSE value also showed that the VS and PS method is the most appropriate method in estimating the H value. Based on the result obtained, it can be concluded that long memory exists in ozone concentration data used in the study. The VS and PS method are the best method in detecting the long memory phenomenon.