Associate Professor Dr Shariffah Suhaila Syed Jamaludin
Department of Mathematical Sciences
Faculty of Science, Universiti Teknologi Malaysia
Malaysia

 

Dr Shariffah Suhaila Syed Jamaludin is an associate professor in the Department of Mathematical Sciences, Faculty of Science, Universiti Teknologi Malaysia. Currently, she is one of the research fellows at the UTM Centre for Industrial and Applied Mathematics (UTM-CIAM). She completed her Ph.D. degree in the field of Statistics in 2010 from the Universiti Kebangsaan Malaysia. In 1999, she received her Master's degree in Statistics from Universiti Kebangsaan Malaysia. She spent her undergraduate at Carleton University, Ottawa, Canada, and received a bachelor degree in Statistics in 1997. Her research interests include statistical modelling & analysis for climate and hydrological data, functional data analysis, spatial statistics, and disease modelling using generalized linear and additive models. She actively publishes several research articles and received several research grants from the government and university.

 

Application of Functional Data Analysis Tools in Hydroclimate and Health Science Areas

In the era of high-dimensional data, a growing research area has focused on the development of functional data analysis (FDA) as statistical tools in visualizing, exploratory, summarizing dataset and modelling. Modelling has become a difficult task, especially when dealing with complex and high-dimensional data. With the advancement of technology, a modern statistical tool known as functional data analysis (FDA) is increasingly being employed in various scientific domains, including biomedical, public health, biology, environmental sciences, climatological, hydrological, and demographic research. Functional data analysis is a new modern statistical method that converts data at discrete time intervals as observations over a continuum interval, viewed as a single entity or curve. The technique provides alternative ways to current conventional statistical methods by adding temporal aspects to the statistical analysis. The FDA's flexibility, such as the ability to provide additional information from smoothing functions and the lack of concerns about correlations between repeated measurements, makes the method extremely demanding. The objective of this study is to examine the applications of functional data analysis in hydroclimate analysis and health sciences areas. The methods such as functional descriptive, functional principal components, functional analysis of variances and graphical plots via rainbow plot, functional bagplot and functional high-density range plot are often used as functional tools. The outputs of functional approach were presented in terms of smoothing curves which provide additional information on the shape and variations; outliers; velocity and acceleration which could be analysed at any time interval which is not available from the current conventional statistical methods.