|
Assessment of Parameter Estimator of Lognormal Distribution for a Better Long-Term Prediction of PM10 Concentrations in Suburban Areas |
|---|---|
| รหัสดีโอไอ | |
| Creator | 1. Muhammad Uthman Omar 2. Hazrul Abdul Hamid |
| Title | Assessment of Parameter Estimator of Lognormal Distribution for a Better Long-Term Prediction of PM10 Concentrations in Suburban Areas |
| Publisher | Thai Society of Higher Education Institutes on Environment |
| Publication Year | 2565 |
| Journal Title | EnvironmentAsia |
| Journal Vol. | 15 |
| Journal No. | 2 |
| Page no. | 23-33 |
| Keyword | Air pollution, PM10, Statistical distribution, Parameter estimation |
| URL Website | https://tshe.org/main/ea-journal-online |
| Website title | EnvironmentAsia Journal |
| ISSN | 1906-1714 |
| Abstract | Lognormal distribution is one of the parent distributions commonly used in air pollution modelling. The nature of lognormal distribution that is skewed to the right makes it suitable for non-extreme air pollution data. Parameter estimation is a critical step in getting the best prediction result with this distribution since the values of parameters might affect the accuracy and errors of the prediction. The main objective of this study is to compare and determine the most appropriate estimator to predict the PM10 concentration in suburban area. Using PM10 concentrations in Jerantut, Sungai Petani, Muar, and Kuantan, this study assessed the performance of four distinct estimators; method of moments, maximum likelihood estimation, probability weighted moments, and uniformly minimum variance unbiased estimator. The method of moments proved to be the best estimator when five performance indicators were used. It is also worth noting that the method of moments has the lowest scale parameter value and the highest shape parameter value for both Jerantut and Sungai Petani. Not only method of moments show good results, uniformly minimum variance unbiased estimator also shows a good result in terms of accuracy of prediction in Muar and Kuantan. |
