Several statistical distributions are used in generating synthetic temperature data such as normal, gamma and others distribution. However, selecting a best marginal distribution from a variety of distribution is time consuming. If the marginal distribution is misidentified, it led to the underestimation of multivariate model. Hence, this synthetic temperature data failed to represent the actual temperature data. Therefore, a more accurate and general application of probability distribution and a study on how to reduce the discrepancy between variance of observed and synthetic data are needed. In this study, the values of the synthetic variances are observed by incorporating the appropriate level of dependence among the individual monthly amount. Three selected meteorological stations which are Alor Setar, Bayan Lepas and Chuping are used from January 1994 to December 2017. The gamma distribution is proposed to fit the marginal distribution which will be used later to transform the data to uniform unit formed. The correlation coefficient is calculated. Next, the synthetic data will be generated using skew-t copula and the correlation coefficient will be noted. The correlation coefficient of the observed data will be matched to the correlation coefficient of the synthetic data. The result shows gamma distribution is suitable for modelling the marginal distribution of the temperature data. It is found that the skew-t copula can be used to generate synthetic temperature data that is close to the observed data with strong correlation values between the temperature stations. It also shown that the skew-t copula is ideal for modelling synthetic temperature data for strong correlated stations. The synthetic generation of temperature data is important in cases where data is limited or unavailable. The copula model is also expected to reflect approximately real situation of the temperature data in Malaysia that can support flood risk management.

1.
N.
Masseran
, &
A. M.
Razali
,
Modeling the wind direction behaviors during the monsoon seasons in Peninsular Malaysia
(
Renewable and Sustainable Energy Reviews)
,
56
,
1419
1430
(
2016
).
2.
S. A.
Ahmad
,
Kuala Lumpur: A hot humid climate. Bioclimatic housing: Innovative designs for warm climates
,
269
293
(
2008
).
3.
H.
Hasan
,
N.
Salam
, &
M. B.
Adam
,
Modelling extreme temperature in Malaysia using generalized extreme value distribution.
World Academy of Science and Technology
,
78
,
435
441
(
2013
).
4.
M.
Pachali
,
Modeling dependence among meteorological measurements and tree ring data
(
2012
).
5.
P.
Krupskii
,
R.
Huser
, &
M. G.
Genton
,
Factor copula models for replicated spatial data
(
Journal of the American Statistical Association)
113
(
521
),
467
479
(
2018
).
6.
B.
Fan
,
L.
Guo
, &
N.
Li
,
Copula in temporal data mining: The joint return period of extreme temperature in Beijing
.
In 2012 6th International Conference on New Trends in Information Science, Service Science and Data Mining (ISSDM2012
) (pp.
592
597
).
IEEE
(
2012
).
7.
F. P.
Lees
, Preface to first edition.
In Lees’ Loss Prevention in the Process Industries
(pp.
xi
xiv
).
Butterworth-Heinemann
(
2005
).
8.
R. B.
Nelsen
,
An introduction to copulas
.
Springer Science & Business Media
(
2007
).
9.
A.
Sklar
,
Random variables, distribution functions, and copulas: a personal look backward and forward. Lecture notes-monograph series
,
1
14
(
1996
).
10.
T.
Ghizzoni
,
G.
Roth
, &
R.
Rudari
,
Multivariate skew-t approach to the design of accumulation risk scenarios for the flooding hazard.
Advances in Water Resources
,
33
(
10
),
1243
1255
(
2010
).
11.
T.
Yoshiba
,
Maximum likelihood estimation of skew t-copula
.
Bank of Japan, The Institute of Statistical Mathematics
(
2014
).
12.
A. M.
Karakas
,
Modelling temperature measurement data by using copula functions
.
Bitlis Eren University Journal of Science and Technology
,
7
(
1
),
27
32
(
2017
).
13.
W.
Wang
,
X.
Chen
,
P.
Shi
, &
P. H. A. J. M.
Van Gelder
,
Detecting changes in extreme precipitation and extreme streamflow in the Dongjiang River Basin in southern China
(
2008
).
14.
M.
Aslam
,
Introducing Kolmogorov–Smirnov Tests under Uncertainty: An Application to Radioactive Data
ACS Omega
(
2019
).
15.
H.
Surendra
, &
H. S.
Mohan
,
A review of synthetic data generation methods for privacy preserving data publishing
.
Int J Sci Technol Res
,
6
(
3
),
95
101
(
2017
).
16.
H.
Wu
,
Y.
Ning
,
P.
Chakraborty
,
J.
Vreeken
,
N.
Tatti
, &
N.
Ramakrishnan
,
Generating realistic synthetic population datasets. ACM Transactions on Knowledge Discovery from Data (TKDD)
,
12
(
4
),
1
22
(
2018
).
This content is only available via PDF.
You do not currently have access to this content.