Since the 1700s, researchers have already been using statistical testing in search for answering many scientific or non-scientific questions (McLean & Ernest, 1998). From deciding a serious issue such as whether a patient needs a certain treatment, to a trivial matter such as deciding whether to buy a certain car or apartment, significant tests are used as a part of our decision’s making process. It provides us with conveniences and nurtures our quick decision-making process. It is so embroiled in our life that we seem to trust it so much without considering the significant errors it might have. There have been many ongoing debates by professionals from social sciences, researchers and doctors in deciding whether the abolishment of significance test is needed as it contains many controversies that are worthy to note (Lecoutre, Poitevineau & Lecoutre, 2005). While significant …show more content…
As mentioned previously by Lecoutre, Poitevineau and Lecoutre (2005), a p-value does not tell us about the magnitude of the effect. However, when combined with a descriptive statistic, we could obtain an interval estimate, which is able to interpret the effect size. This further confirmed that despite many shortcomings of significant test, there are still many areas of it that are essential in producing a sound judgment. Moreover, human errors are very common in significant test. More often than not, it is individual’s own misinterpretations that lead to unreliable conclusions. To minimize these mistakes, it takes many years of training and experience for one to make an accurate interpretation (McLean & Ernest, 1998). Therefore, the theory behind significance test is not entirely wrong, with more guidance and modifications to ensure accurate interpretations; significant test is still deemed to be