is the importance of statistical data analysis?
Statistics is the science of collecting, analyzing and making inference from
data. Statistics is a particularly useful branch of mathematics that is
not only studied theoretically by advanced mathematicians but one that is used
by researchers in many fields to organize, analyze, and summarize data.
Statistical methods and analyses are often used to communicate research
findings and to support hypotheses and give credibility to research methodology
and conclusions. It is important for researchers and also consumers
of research to understand statistics so that they can be
informed, evaluate the credibility and usefulness of information, and make
The field of
statistics is the science of learning from data. Statisticians offer essential
insight in determining which data and conclusions are trustworthy. When
statistical principles are correctly applied, statistical analyses tend to
produce accurate results. To produce conclusions that you can trust,
statisticians must ensure that all stages are correct.
Statisticians know how to:
§ Design studies that answers the question at hand
§ Collect trustworthy data
§ Analyze data appropriately
§ Draw reliable conclusions
Many Ways to Produce Misleading Conclusions
Statisticians should be a study’s
guide through a minefield of potential pitfalls, any of which could produce
misleading conclusions. The list below is but a small sample of these pitfalls.
A non-random sample can
bias the results from the beginning.
The results from one
population may not apply to another population. Statistical inferences are
always limited and you need to understand the limitations.
How do you know when X causes a
change in Y? Statisticians require tight criteria in order to assume causality.
Is the model too simple or
too complex? Does it adequately capture any curvature that is present? There
are many ways you can perform analyses, but not all of them are correct.
of the assumptions for an analysis
If you perform an analysis
without checking the assumptions, you cannot trust the results.
Even if everything passes
muster, an analyst can find significant results simply by performing many tests.
Statisticians keep track of all the tests in order to put the results in the
to the Rescue
short, there are many ways to produce misleading conclusions.
you want to use data to learn how the world works, you must have statistical
knowledge to trust your data and your results. There’s just no way around it.
Even if you are not performing the study, understanding statistics can help you
assess the quality of other studies and the validity of their conclusions.
world today produces more data than ever before, and this is why we are
celebrating statistics. It’s important to show others the impact statistics is
having on society, including all branches of science, industry, public health,
and public policy. Some analyses are straight up for science and others are
more partisan in nature. Are you ready? Will you know which conclusions to
trust and which studies to doubt? (Frost,
The importance of statistical data analysis regarding to the chosen
used by the novel approach introduced in this thesis is designed to address
potential inaccuracies of data, both in dependent variables and in explanatory
variables. The methodology also addresses the potential multivariate nature of
road safety analysis problems due to multiple dependent road safety outcomes
like the number of accidents and victims. The first aspect results in
non-homogeneous observation error variances and the needs for a multivariate
approach to modelling.
The second aspect
introduces structural but time varying covariance among (multivariate)
observation errors. Both issues are accounted for by readily available
statistical techniques derived from the Kalman filter (Kalman, 1960). In this
thesis a special form of Kalman (1960)’s model which is referred to as a
structural time series model is further developed. Structural time series
models originate from Muth (1960), and were made popular by Harvey (1983), and
applied in multivariate form by Harvey and Koopman (1997). A special form of
the latter model designed for road safety risk analysis is developed in this
thesis and was published as Bijleveld, Commandeur, Gould, and Koopman (2008) (Bijleveld, n.d.).
is the appropriate published literature in your area of research?
Statistical Analysis of Management Data provides a comprehensive
approach to multivariate statistical analyses that are important for
researchers in all fields of management, including finance, production,
accounting, marketing, strategy, technology, and human resources.
Statistical methods are widely used in research. There is a vast
amount of supporting theory, practical tips, examples of good practice, and so
on, to support these methods. However, some fundamental aspects of the way statistical
approaches are typically used sometimes seem problematic – even in studies
published in respected journals whose reviewing process ensures that the
obvious pitfalls are avoided.
The collection and analysis of statistical data drives some of the
most important conclusions that are drawn in today’s business world, such as
the preferences of a customer base, the quality of manufactured products, the
marketing of products, and the availability of financial resources. As a
result, it is essential for individuals working in this environment to have the
knowledge and skills to interpret and use statistical techniques in various
scenarios. Addressing this need, Methods and Applications of Statistics in
Business, Finance, and Management Science serves as a single, one-of-a-kind
resource that guides readers through the use of common statistical practices by
presenting real-world applications from the fields of business, economics,
finance, operations research, and management science.
The paper can be published in many forms like Website or Journal. It is important to be aware of the different
types of literature that exist and the variety of publication types within each
class. It is also important to honestly evaluate your work to determine what
publication type is most appropriate for your study.
Determining the appropriate target journal and publication type in
advance, and complying with the instructions set out in the Guide for Authors
of the target journal, as they relate to the relevant publication type, will
increase your chances of acceptance for publication and shorten the time from
initial submission to acceptance.
and Secondary literature
literature is divided into two basic categories – “primary” and
The most important distinction among publication types is that
between the primary and secondary literature. The primary literature refers to
the places in which original scientific research is first published in a
publicly accessible document. Primary sources are original sources of
information that have not yet been filtered through analysis, examination or
interpretation. Typically, primary sources are contemporary to the events and
individuals being researched. This includes most journal papers, conference
proceedings, theses and dissertations. The information published in the primary
literature is later condensed and reorganized into the secondary literature,
which includes textbooks, book chapters, review articles, indexing and
abstracting services and various other forms of information compilation.
A secondary source is not an original source. It has no direct
physical connection to the person or event being studied. Examples of secondary
sources might include: history books, articles in encyclopedias, prints of
paintings, replicas of art objects, reviews of research, academic articles. The
role of the primary literature is to share new findings with the broader
community; the role of the secondary literature is to compile and organize the
information in the primary literature into an easily accessible and
Some journals publish papers of both types in addition to features,
news and other sections, while some journals can be considered exclusively
primary journals (that is, publishing solely primary literature, the results of
original research) and others can be considered secondary journals
(specializing in review articles). It is worthwhile being aware of this when
choosing journals and establishing relationships with journal editors. It is
also worthwhile thinking about possible review article themes when you have
established some authority in your area of research.
and Types of publications
An explanation of the concepts of
scholarly, professional and popular science publications, and definitions of
the different output categories.
Among journals publishing primary research there is a great variety
of publication types. It is helpful to be aware of these when starting to think
about writing up your work, because one type of primary publication format
might be more appropriate for your work than another. Most academic journals
list the publication types they publish on their web pages. Some of the
possible types of manuscript include the following: Full-length papers, Rapid communications and Short
communications, Letters to the editor, Case reports, Technical or Laboratory
notes and Methods.
Each of these
publication types will have a slightly different format that will be set out in
the journal’s Guide for Authors. When preparing any manuscript, read the
instructions in the Guide for Authors closely and follow them precisely.
journal that is right for you, once you are satisfied that you have sufficient
findings to warrant publication, you need to decide on your target journal and
the publication type. To determine the best publication type for your work, you
need to self-evaluate it. It may also be helpful to ask a colleague to evaluate
it and provide an independent assessment.
Is there sufficient material for you to write a full article? If
so, great! If not, perhaps a short communication or letter would be more
appropriate. Are the results particularly exciting and timely, or are you
worried about a competitor publishing similar findings before you can? If so,
you might want to consider writing a rapid communication article. A number of
journals, such as Biochemical and Biophysical Research Communications,
specialize in this type of article and strive to achieve a very short lag between
acceptance of a manuscript and publication.
Sending an Enquiry
If you are not sure what format or journal is best for your work,
you can always send a journal editor a pre-submission enquiry. Many journals
offer this facility, and even for those that don’t, the editors will likely
reply to a polite enquiry about possible publication. Such an enquiry should
contain a brief outline of the research you wish to publish and why it is
particularly timely and of relevance to the readers of that journal. You should
mention how many potential display items your paper will contain and what each
of them shows.
manuscript submissions (see our information on ethics), pre-submission
enquiries can be sent to multiple journals simultaneously. When you receive a favorable
response, you can proceed with writing the introduction, discussion and
abstract, and reformatting the methods and results sections as appropriate.
This approach enables you to use the correct amount of references
(many journals/publication types have a limit on the number of references that
can be included) and comply with section word limits, preventing the need for
rewriting an existing manuscript (Ltd, 2015).
literature regarding to the chosen research paper:
The first study
within the context of this thesis was Bijleveld (1999). The objective of
Bijleveld (1999) was to improve the reliability of short-term prognosis of
general road safety outcomes, to be used as part of an annual review of the
development of road safety in the Netherlands. Specifically, such prognoses
were intended to be used to determine whether or not road safety outcomes in
the reviewed year were in line with what could be expected from road safety
developments just before that year. A comprehensive analysis of changes in the
development of road safety related indicators could help the road safety
researcher detect recent general changes in road safety conditions, if any.
After Bijleveld (1999), the objective was extended to the analysis of the
development of aspects of road safety in general, resulting in this thesis.