Page 447 - Contributed Paper Session (CPS) - Volume 2
P. 447
CPS1922 Imran K. et al.
Statistics has certainly benefited from the developments in computer
technology and statistical software is now accessible to a wide audience,
however, the complexity of the questions under study in most disciplines
requires at least some form of expertise related to data analysis. The problem
is that most researchers don’t have time to acquire this specialized knowledge
along with the practical experience to apply it appropriately. There is a need
to involve someone who understands the scientific process and has the
quantitative skills to full fill this important role: the statistical consultant
(Cabrera and McDougall, 2002).
The researchers conduct the experiments or surveys to answer their
research question (RQ). To answer the RQ different types of errors are
committed like errors of Type I or Type II and Type III. In statistical hypothesis
testing while making a decision on the basis of a sample sometimes we may
fail to accept a correct null hypothesis (H0). Thus rejecting H0 when it’s true is
called Type I error e.g. a subject is declared having the disease (false positive)
when in fact it’s healthy. Similarly, if a researcher fails to reject an incorrect
H0i.e. accept H0 when in fact it’s false is called Type II error e.g., a subject is
declared healthy (false negative) when in fact it’s having the disease. Errors of
Type I and Type II are due to lack of evidence in the sample while the error of
Type III (Kemball 1957) is due to lack of communication between researcher
and the collaborator and, results in right answer to the wrong query. For the
Type-IV error, the questions posed can be right but the answers can be wrong,
the reasons for which are discussed in this paper.
In the earlier days, everyone used to consult the specialists possessing the
in-depth knowledge to get an answer to a particular problem, with a
threadbare discussion. But with the advent of computers along with internet
everyone has become self-styled specialists in almost all fields, and statistics
is not an exception. Google like other search engine sites is full of information
but as far as knowledge is concerned it is way behind. As Rutherford has rightly
said “we are drowning in information but lack knowledge”, the reason seems
to be searching everything on the internet instead collaborating with the
expert. The specialists have both information and knowledge. The drive for
writing this paper is to make researchers aware of the Type IV error which they
can commit, and in turn, leads to wastage of their hard work and resources
they put in while conducting the research. Researchers can possess knowledge
of their field but they can have only the information about other fields like
statistics.
2. Methodology
In this study 352 research papers were screened and 81 research papers
were found to have Type-IV error. Since it is not possible to present all the
findings hence a few cases have been discussed as an example. To maintain
436 | I S I W S C 2 0 1 9