Omar, Muhammad Uthman (2024) Comparison Of Parameter Estimators Of Lognormal Distribution For Predicting Pm10 And Pm2.5 Concentrations. Masters thesis, Perpustakaan Hamzah Sendut.
![[img]](http://eprints.usm.my/style/images/fileicons/application_pdf.png) |
PDF
Download (1MB) |
Abstract
Pm₁₀ and pm₂.₅ are among the dominant air pollutants in malaysia and have caused severe adverse effects on human health, especially on children, pregnant mothers, and senior citizens. To better understand the distribution of pm₁₀ and pm₂.₅, statistical modelling using the lognormal distribution was used because of its positively-skewed nature and is regarded as the most appropriate distribution for particulate matter in malaysia. The lognormal distribution has two parameters namely location and scale parameters. Parameter estimation is a crucial step in getting the best prediction since the value of location and scale parameters can affect the error and accuracy of the prediction. In this study, four different estimators namely the method of moments (mom), maximum likelihood estimator (mle), probability weighted moments (pwm), and uniformly minimum variance unbiased estimator (umvue) were used to estimate the location and scale parameters. Hourly data of pm₁₀ and pm₂.₅ concentrations from 2017 to 2020 on four different classifications of monitoring stations namely jerantut as background, sungai petani as suburban, alor setar as urban, and perai as industrial were used.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | L Education > LC Special aspects of education > LC5800-5808 Distance education. |
| Divisions: | Pusat Pengajian Pendidikan Jarak Jauh (School of Distance Education) > Thesis |
| Depositing User: | Mr Hasmizar Mansor |
| Date Deposited: | 25 Feb 2026 01:20 |
| Last Modified: | 25 Feb 2026 01:20 |
| URI: | http://eprints.usm.my/id/eprint/63650 |
Actions (login required)
 |
View Item |
