Most of the research revolves around the use of statistics. Though statistics is understood differently by many people, understanding of the question at hand is more important than the logic behind the statistical values. Hence, research can be considered to be based on logic and accuracy and its importance should mean a lot to the people involved. Most of the failures resulting from statistical values are due to misunderstanding of the significance of the problem since most of people are considered not to visualize the solution properly. Though statistics from the video is considered to fool juries, researchers have a lot of responsibility when it comes to convicting guilty or innocent individuals.
Most people do not understand how statistics are obtained and in many occasions, they make wrong conclusion from the calculated results. In the video, Donnelly talks about how people react to uncertainty when it comes to human mistakes. He considers that research should not only capture an opinion or result, but how the outcome is dependent on correct calculations (Donnelly, 2005). While we consider data to give substantial information, the fallacy of big data doesn’t proportionately imply more information. Thus, the information from big data can be overrated. Simple statistics that are not presented properly can mislead the people in situation where substantial information to decipher it is not available (Allen, 2007). Thus, it is not right when our intuitions give wrong conclusions on statistics because intuitions are based on statistics. Although expectations are based on uncertainty, statistics contradicts the expectations of many people hence making them implausible and uncomfortable.
Statistical evidence on the probability of non-culpatory causes should not be used in criminal courts to establish the material fact of causation. Like for example in the video, the role of statistical evidence in Clark’s case is much overrated as the prosecution case was strong without statistics. This explanation is similar to that of expert statisticians, that is, probability makes sense only when it is compared with the smothering probability. As described by Allen (2007), English court of appeals explicitly rejected Bayesian methods as they are considered for plunging the jury into unnecessary and inappropriate realms of complexity and theory deflecting them from their proper responsibilities. Hence, before examining the technical complexities of how to analyze, gather, and present statistical evidence which shows exact probability values, individuals should ensure that raising probability questions is appropriate in the given context (Dawid, 2001).
People cite statistical resultts and consider them to be substantial proof of something. Factors such as a source of funding, population under study, identification of randomized trials, study time frames, response survey rates, and accurate description of the study outcome and exposure should always be taken care of (Donnelly, 2009). The statistical main result should quantify on the absolute risks and the accuracy of the figures used. Hence statistic should never be taken out of context without knowing the substantial claims. The use of scientific or technical language should be sparingly used in the explanation of statistical information for easy understanding by the audience.
The use of simple words to present information has the power in its critical understanding. Though many people quote or use statistics without performing their in depth research on the population/sample size, questions raised, and study design, people should realize that there is a big difference between statistical values and information (Allen, 2007). Statistical information should be easily interpretable, show substantial relevance, and must be novel to be insightful. While we can consider statistics in most instances to be misleading, we should always understand of its importance. Hence, the use of statistics should help us get the logic and an accurate understanding of what we want.