Analysis of Fuel Prices in Australia: Techniques of Data Collection, Analysis, Interpretation and Presentation

University
Statistics and Data Analysis
By
Name
Date
Page 1 of 15
©<Your Name> 2019

Section 1
Part A
Introduction
Fuel expense is described to be amongst the highest consumer of Australian
residents’ income and the variations and fluctuations in the prices of fuel have a
direct impact of the standard of living. This has over the years resulted to raised
eyebrows about the Australia’s fuel prices making it the subject of several inquiries
(Valadkhani, 2013). Data on the patterns and trends in fuel prices is collected and
stored so that it can be analyzed to forecast the future price expectations by the
involved government entities in the country such as NRMA. The data is collected
using various methods ranging from direct surveys, digital data collections or
collection from secondary sources.
The assignment is therefore purposed to examine the ability of applying the
different techniques of data collection, analysis, interpretation and presentation on
primary and secondary datasets with the aim of delivering a reliable and
dependable solution that can be used as guide by a government entity NRMA to aid
them in delivering adequate media report about fuel prices in different locations of
Australia.
Part B
Description of Dataset 1
Two datasets namely dataset 1 and dataset 2 are used to reach the objectives of
the assignment. Dataset 1 is collected from the Australian Government Open Data
as a subset of the service station and price history September 2016 individual
Page 2 of 15
©<Your Name> 2019

sample file under the license of creative commons attribution 3.0 Australia. Dataset
2 is collected from surveying of 70 students.
Since dataset 1 is collected from an external source it is a secondary form of data
(Shao, 2010). This type of data has the merit of being readily available thereby
saving the time that would have been consumed in collection if it were to be
primary. On the other hand, then limitation of this type of data is that the end user
has no control over it (Selvanathan, Selvanathan, and Keller, 2017).
Dataset 1 has got seven variables namely; Service Station name, Address, Suburb,
Post code, Brand, Fuel Code and Price. Service Station Name, Address, Suburb,
brand and fuel code are categorical variables, Price is quantitative numeric variable
while postal code is a qualitative numeric variable (Watkins, Scheaffer, and Cobb,
2009). The cases are the individual items represented by the variables. For
example, the variable brand cases Caltex, Caltex Woolworth, Bp etc.
Part C
Description of Dataset 2
Dataset 2 is a primary type of data. It is collected by directly surveying 70 students
on their preferred fueling station. This method of data collection is commonly known
as face-to-face survey (Foster, Barkus, and Yavorsky, 2006). The merits of this type
are that the researcher or the end user has control over the data collected and the
probability of collection of reliable and dependable data is high. The disadvantages
of this type of data is that much time and resources are consumed during collection.
Additionally, the respondents may be unwilling to give the right information or they
may be sharing similar interest leading to collection of not as accurate data as
expected for any research. Dataset 2 has got three variables; date indicates the day
Page 3 of 15
©<Your Name> 2019

the respondent was approached; respondent id is a numeric discrete variable
indicating the unique identification of the respondent and address is categorical
variable indicating the address of the location where the respondents preferred
fueling station is collected. The cases are the individual elements represented by
the variables.
Section 2: Analysis of a Single Variable in Dataset 1
Part A
Numerical Summary and Frequency Distribution
To describe the shape of the distribution of the variable price, we use the
descriptive or the numeric summaries as well as the frequency histogram. The
numeric summaries include the mean, mode, median, standard deviation, variance,
quartiles and the interquartile range among others. The table below shows a
summary of the descriptive statistics.
Page 4 of 15
©<Your Name> 2019