All Data is Relevant Only the Relevancy is Disputable
A lot of this “course would be rarely used who cares” perspective; stems from students have a difficult time finding relevance to their longer term interests and career goals. “I’m going to be a computer programmer, why do I need to take biology?” was my perspective until recently. It turns out that once you get into a career, having the core skills will only get a person so far. After that they need to draw on parallels from other disciplines to set themselves apart from their peers.
For example; this weekend I was researching how to determine if a citation source was good or not. This caused me to stumble into legal theory, because the parallel between selecting a witness and convincing jurors is not a far step from selecting a source and convincing readers. Because of this parallel I was able to take the work of Brodsky, Griffen, and Cramer’s Witness Credibility Scale and quantify if a source was useful. They used “a factor[ed] structure that consisted of four factors labeled, ‘knowledge,’ ‘likeability,’ ‘trustworthiness,’ and ‘confidence’ (WCS, 2010).” The same tests they applied also mapped back to the citation source.
From this parallel I started thinking that all disjoined data must be relevant in some manner. From a little more digging I stumbled across the statistician Karl Pearson, who made this same conclusion. He theorized that all data is relevant and that the distance between two variables is what determines relevancy (Wikipedia).
Jing and Hung expanded on this by sorting data into associative sets; then nearest neighbor theory can be applied to quantify the relevancy of two variables. These variables could be topics, articles or other associative sets. If the quantified value is high enough then we would say it is relevant (Jing & Hung, 2009).
This concept gives an interesting perspective determining what is relevant. Through their algorithm disjoined subjects and topics can have direct parallels identified. This discovery led to a light bulb turning on for myself. If two associative sets can be proven to be relevant then concepts of one can be applied to the other. Suddenly the subject lines are blurred and the number of references and case studies available to justify a point increased exponentially.
Ultimately it is all relevant just to what degree. The more we know of the associative sets, the more parallels we can draw. The more parallels the more we set ourselves apart from our peers, in turn allowing us to better excel in life both professionally and privately
Brodsky SL, Griffin MP, Cramer RJ (2010). The Witness Credibility Scale: an outcome measure for expert witness research. Behavioral Sciences & The Law, ISSN: 1099-0798, 2010 Nov-Dec; Vol. 28 (6), pp. 892-907
Guorui JING; Hai QING; Tiyun HUNG. (2009). A Personalized Recommendation Algorithm Based on Associative Sets. Journal of Service Science & Management, Dec2009, Vol. 2 Issue 4, p400-403
Wikipedia (2012); Pearson’s Product Moment Correlation Coefficient