A combination of the robust projection pursuit and
Mahalanobis distance method used by Hyndman and Shang (2010)
were employed to identify the daily PM10 anomalies in the form of
curves or functional data at three selected air quality monitoring
stations in the Klang Valley region of the Malaysian Peninsular. This
study shows that anomalies detection was a useful statistical
technique in studying and investigating abnormalities in the daily
PM10 process system. Using functional data analysis, the whole
structure of daily diurnal patterns of anomalies could be visualized.
It is also shown that functional data for extreme anomalies and
wind speed offers a solution to investigate the relationship
between two extreme data. The approach could overcome the
problem facing by Juneng et al. (2011) due to the incapability of
regression method used.
assessment