Publication: Predicting occurrence of rainfall using discriminant analysis
Loading...
Date
2009-04-01
Authors
Kee, Pei Hoon
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Malaysia has a tropical climate that is consistently hot with high frequent rainfall. Water is one of the most vital natural resources for all life on Earth. So, it is important to quantify it accurately. Rainfall rate is affected by some unpredicted weather conditions such as humidity, air pressure, temperature and wind speed which are liable to change. The relationship between the rainfall rate (dependent variable) to the humidity, temperature, air pressure, and wind speed (independent variables) is analyzed by the method of discriminant analysis using the SPSS 15.0 software. A total of 340 cases for year 2008 were used to develop a model to discriminate among the 2 levels of rainfall rate which is rain or no rain. The aim of this project is to develop a set of discriminating functions to predict the category of the rainfall rate. The usefulness of a discriminant model is based upon its accuracy rate, or ability to predict the categories of the dependent variable. As a conclusion, the discriminant analysis in this study successfully estimates the categories of the rainfall rate. The accuracy is high that is 84.7%. So, the results show that the discriminant analysis can be considered as an effective tool in forecasting the type of rainfall condition.