Authors :
Adefabi Adekunle; Ajare Emmanuel Oloruntoba
Volume/Issue :
Volume 8 - 2023, Issue 7 - July
Google Scholar :
https://bit.ly/3TmGbDi
Scribd :
https://tinyurl.com/78nyt4us
DOI :
https://doi.org/10.5281/zenodo.8304849
Abstract :
The main objective of this study is to use
GFTSC (Group for Time Series Components) to identify
the components of time series present in the seasonal
data of (UK GDP). This data is the GDP yearly data of
United Kingdom gross domestic product (UK GDP). The
(UK GDP) data spanned for the period of twenty years.
The GDP of UK is a secondary data obtained from the
DataStream of Universiti Utara Malaysia Library. The
weaknesses of BFAST (Break for Additive Seasonal and
Trend) were corrected by the extension of BFAST to
GFTSC which resulted into creation of a new technique
named Group for Time Series Components. BFTSC was
created to capture the cyclical and irregular components
that was not captured by BFAST technique. BFTSC is
designed to present the image of all the 4 time series
components. BFAST only identifies trend and seasonal
components only. Evaluation using simulation data was
conducted to verify the accuracy of GFTSC using
monthly simulated of 144, 000 data unit. This data
contained 48 months small monthly sample size, 96
monthly medium sample size, 144 months large sample
size. Each of the sample size was replicated 100 time
each. GFTSC is effective and better than BFAST
because it was able to identify approximately 100% of
the data with the basic four time series components
monthly. BFTSC detects 99.99% of the entire
components in the time series monthly data that was
tested. Empirical data were employed to BFTSC and
subsequently determine the next forecasting technique
after which one step forecast is made ahead. The
simulated and real data findings suggested that GFTSC
can provide a better alternative to BFAST technique,
hence GFTSC is recommended.
Keywords :
Group for Time Series Components, Seasonal Data, Gross, Cyclical , Irregular Components.
The main objective of this study is to use
GFTSC (Group for Time Series Components) to identify
the components of time series present in the seasonal
data of (UK GDP). This data is the GDP yearly data of
United Kingdom gross domestic product (UK GDP). The
(UK GDP) data spanned for the period of twenty years.
The GDP of UK is a secondary data obtained from the
DataStream of Universiti Utara Malaysia Library. The
weaknesses of BFAST (Break for Additive Seasonal and
Trend) were corrected by the extension of BFAST to
GFTSC which resulted into creation of a new technique
named Group for Time Series Components. BFTSC was
created to capture the cyclical and irregular components
that was not captured by BFAST technique. BFTSC is
designed to present the image of all the 4 time series
components. BFAST only identifies trend and seasonal
components only. Evaluation using simulation data was
conducted to verify the accuracy of GFTSC using
monthly simulated of 144, 000 data unit. This data
contained 48 months small monthly sample size, 96
monthly medium sample size, 144 months large sample
size. Each of the sample size was replicated 100 time
each. GFTSC is effective and better than BFAST
because it was able to identify approximately 100% of
the data with the basic four time series components
monthly. BFTSC detects 99.99% of the entire
components in the time series monthly data that was
tested. Empirical data were employed to BFTSC and
subsequently determine the next forecasting technique
after which one step forecast is made ahead. The
simulated and real data findings suggested that GFTSC
can provide a better alternative to BFAST technique,
hence GFTSC is recommended.
Keywords :
Group for Time Series Components, Seasonal Data, Gross, Cyclical , Irregular Components.
