Efficiency and Performance of Transport Industry in Australia

Statistical Modelling 1
Statistical Modelling
Name of Student
Course
Tutor
University
City/State

Statistical Modelling 2
Statistical Modelling
1 (a)
Transport and logistics industry one of the most important sector in the economy of Australia.
The size of the country and vast distances between major urban centres implies that many
consumers and businesses rely on the efficiency of freight businesses for access to many vital
products. For that reason, ensuring that the sector operates safely and effectively is of critical
concern. Yet, incomplete structural reforms and insufficient investments continue to negatively
affect Australian economy in terms of revolutionising its large transport system. Urban transport
problems in Australia are increasing, as a consequence of inadequate traffic management and
weak policy coordination (Best of Business, 2016).
After years of decline, public transport investment in Australia is finally rising. But then again
the Australian’ government has been caught on the hop. Poor planning has contributed to dozens
of serviceable Hitachi trains being scrapped just as commuters began returning to the train
network in droves. Crowding on trains (in addition to bus and tram routes) has given rise to, and
mean the effect of just one cancelled service is severe. According to Wade (2014), the value of
transport lies not so much in the service itself, however in its power to allow people to move
around and enjoy the things that they consider necessary to them. As such, the improvement of
the transport in Australia should mostly focus on reliability, productivity, access and efficiency.
Decisions that are made by consumers about transport are very long-lived, not only compelling
people to years of infrastructure maintenance besides locking them into today’s usage and
technological innovations. With this knowledge, the focus of this paper is on the development of

Statistical Modelling 3
strategies to assess and improve the efficiency and performance of the transport industry in
Australia.
1 (b)
This dataset offers counts of tap ons and tap offs created on the Opal-ticketing system for the
duration of two non-consecutive weeks in 2016 (Open Data, 2016). This data is secondary data
as it was retrieved from the online site of Opal-ticketing system. According to Cooper and
Schindler (2014), secondary data constitutes data that has been gathered by somebody other than
the user. Conventional sources of secondary data include censuses, government publications,
peer-reviewed journals, newspapers, magazines etc. The advantages of secondary data are
several. First, they are economical in terms of time and resources. Second, secondary data offer a
basis for comparison for the data that is collected by other investigators. Third, secondary data
sources are readily available (Cooper & Schindler, 2014). Finally, secondary data helps improve
the understanding of the problem being investigated. On the other side, secondary data has been
faulted for various reasons including providing inappropriate data as the data is collected by
other people, lack of control by the researcher over data quality and quality issues.
The dataset, in this case, is constituted by both categorical and numeric variables. Categorical
variables according to Saunders et al. (2016), are variables that someone can assign categories,
but the groups have no natural order. In this case, the categorical variables in dataset 1 are the
mode of transport (train, bus and light rail), location, tap, and date. On the other side, the values
of a numerical variable are numbers (Fahimnia et al., 2013). The numeric variable in this data set
is time (which is a continuous variable) and count (which is a desecrate variable). Discrete can
be further categorized into continuous or discrete variables (Van Buuren., 2007). The discrete

Statistical Modelling 4
variable only take on a finite number of values while continuous variable has an infinite number
of possible values (Saunders et al., 2016).
1 (c)
The dataset 2 is primary data as I collected it personally for a specific reason. According to
Nguyen and Tongzon (2010), primary data is an original data that is collected first-hand by the
investigator in a particular research project or project. Primary data has several advantages
according to researchers. First, primary data is very reliable as an investigator can duplicate the
procedure to check the validity of the results, as they understand how the data was gathered and
analysed (Cooper & Schindler, 2014). Second, primary data collection provides the latest data as
data obtained from previous years is less likely to answer the questions that a researcher wants to
address consistently. Lastly, primary data allow researchers to be subjective in types of data they
are gathering in line with the hypothesis they are trying to test. Regardless of the advantages of
primary data, this method of data collection is faulted for being expensive regarding resources
and time consuming (Nguyen and Tongzon, 2010).
The main methods of collecting primary data include direct observations, survey questionnaires,
and conducting interviews (oral or phone interviews) (Nguyen and Tongzon, 2010).). In our
contest, an online survey questionnaire was randomly distributed to the targeted respondents and
the responses recorded for analysis. Simple random sampling is a research technique where each
sample element of a given size has an equal chance of being selected ((Nguyen and Tongzon,
2010). The use of online questionnaire was preferred in this survey as it is less costly regarding
administration and is convenience as it enables respondents to participate in any study at any
place provided they are connected to the internet. Gadgets like mobile phones, tablets, pcs and
desktops usually allow participation or respondents in online surveys.