In: Statistics and Probability
Correlation does not mean causation.
Look through a newspaper, or a magazine or even a journal article that cites correlational data to make a point. Identify other possible explanations for the correlation that don’t fit with the article’s conclusion.
Baseball and fly slack: Correlation does not infer causation
See the article "How stream slack impedes Major League Baseball execution" in volume 114 on page 1407.
This article has been refered to by different articles in PMC.
My consideration was attracted to the ongoing article by Song at al. entitled "How stream slack debilitates Major League Baseball execution", by its marginally irregular subject as well as more significantly in light of the fact that I thought about how one would ever really demonstrate the impact of fly slack on baseball execution.
In this paper, Song et al. figure out how to refine the outcomes gotten by Recht et al. as right on time as 1995, demonstrating that eastbound travel relates with diminished execution. In particular, by making utilization of expand insights on the specific extensive measure of Major League Baseball record databases accessible on the web, Song et al. found measurably noteworthy relationships of eastbound travel with a few factors identified with home-group hostile execution, and in addition with "grand slams permitted" for both home and away groups.
Despite the fact that I don't question the substantial measure of work included and would be well-near unequipped for making a decision about the legitimacy of the investigations performed, I should concede that I was shocked the way Song et al. methodicallly present the relationships they recognize as immediate evidence of causality between fly slack and the influenced factors. It is very exceptional to me that "connection" does not seem even once in the paper, when this is really what the writers have been taking a gander at and, as I would like to think, to be experimentally exact, the title of the article should peruse: "How stream slack associates with hindrances in Major League Baseball execution."
Given the specific extensive measure of writing on connections between's fly slack and diminished athletic execution in an entire assortment of games, I am obviously not debating that fly slack is the probably cause for the impacts recorded. What's more, taking a gander at the title of the articles in the reference rundown of the Song et al. report, this propensity to amalgamate relationship with causality is obviously to a great degree visit in this field of examination. Be that as it may, given the wide readership of PNAS and the subject of this article, I feel that it is probably going to be handed-off by the press and to draw in the consideration of numerous individuals, the two researchers and nonscientists.
Thinking about the present propensity to misconstrue logical information, by means of the abuse of measurements specifically, I feel that a diary, for example, PNAS should intend to teach by model, and subsequently should authorize more thoroughness in the introduction of logical articles in regards to the contrast among relationships and demonstrated causality.
For anybody waiting be persuaded that solid relationships don't really demonstrate causality, and to complete on an all the more cheerful note, I welcome them to visit the site of Tyler Vigen, which gives some truly fascinating models of false connections (www.tylervigen.com/misleading relationships).