Page 48 - Contributed Paper Session (CPS) - Volume 6

CPS1490 Nehall Ahmed Farouk Mohamed
a concept nascent and has uncertain origins. Diebold (2012) argues that the
term “big data . . . probably originated in lunch-table conversation at Silicon
Graphics Inc. (SGI) in the mid-1990s, in which John Mashey figured
prominently”. Different levels had been passed through studying big data.
There were several studies in big data, either from information technology (IT)
aspects or from official statistics aspects. The task of extracting and using big
data with official statistics had been discussed by many statistical agencies
around the world. According to previous published studies and discussion
papers, Australia, Netherland, and Italia have precedence over other countries
in using big data with official statistics. Using big data in official statistics still
an opened and important theme that needs investigations. On the other hand
there are many studies about big data that completely focus on the IT
perspectives only. So a shortage is considered in studying big data from both
IT aspects and official statistics aspects to gather in one research. Here it
should be remarked that, the main aim of this paper is to study big data in
official statistics using the latest IT methodologies and techniques. It is
important to get benefit from the previous experiences of using big data in
official statistics, whether to be used as main source of data or to be integrated
with official surveys data. Some of the projects that used big data in official
statistical offices should be mentioned, in order to consider their challenges.
The experience of Statistics Netherlands in the analysis of Traffic Loop
Detection Data and the analysis of social media massages is one of them, also
the Big Data Flagship Project of the Australian Bureau of Statistics (ABS). The
main effect that is resulted from using big data analytics by national statistical
offices (NSOs) should be mentioned as improving the international
development.

2. Methodology
The paper integrates big data from official statistics perspectives and big
data from IT perspectives. Through the first section, the paper explains using
big data in official statistics by NSOs, international organizations, and
statistical agencies. This will be clarified through several dimensions. The first
dimension is showing examples of huge statistical projects in big data in
different NSOs. Then the second one is naming the sources of big data that
can be considered officially by UN statistical commission. Thirdly, this section
produces the micro level that aggregates macro level effect of big data as
development applications. Finally, mentioning the opportunities while using
big data. Then the second section focuses on big data analytical techniques
for structured and unstructured big data. This section concentrates on big data
predictive analytics. This is the point where it is needed to make a prediction
from big data using IT techniques. So the last section illustrates how machine

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