Page 411 - Contributed Paper Session (CPS) - Volume 2

CPS1911 Nurkhairary A. M. et al.
The simultaneous functional relationship model for circular variables
proposed by Mokhtar et al. (2015) is applied to these data and resulting the
parameter estimates of the data. The result is shown in Table 1.

Table 1. Parameter estimates of wind direction data
̂ 0.146597
1
̂ 6.099307
2

variance (̂ ) 0.018729

̃ 1.082606

variance (̃) 0.055049

Therefore, from Table 1, it can be said that the model of wind direction
data in Kota Kinabalu during northeast monsoon from 2015 to 2017 is
= 0.146597 + (mod 2) and = 6.099307 + ( 2)
2
1
with the error concentration parameter of 1.018729 where is the wind
1
direction of 2016, is the wind direction of 2017 and x represents the wind
2
direction of 2015.
From the parameter estimates, the rotation parameters ̂ and ̂ are very
1
2
close to each other and small error concentration
̃. This is in agreement with the representation of the rose diagrams.

4. Discussion and Conclusion
To conclude, this paper discusses about modelling wind direction data in
Kota Kinabalu coastal station in Malaysia during northeast monsoon for three
consecutive years using the simultaneous linear functional relationship for
multivariate circular. The wind direction data are considered with the von
Mises distribution in which the rotation parameter and the concentration
parameter are estimated using the maximum likelihood estimation. From this
model, we can say that the rotation parameter is very near to zero radian and
error concentration parameter of wind direction is less concentrated and
dispersed. Using the simultaneous linear functional relationship model, we
may conclude that the relationship between the three years is not strong with
relatively low ̃ value.

Acknowledgement
We would like to thank National Defence University of Malaysia and University
of Malaya (grant number: GPF006H-2018) for supporting this work.

400 | I S I W S C 2 0 1 9