Problem is anecdotally, there's enough outliers/counter examples to almost anything to fill an attention span.... What we need to do is categorize the anecdotes and add them up in a chart.,,,,,
-
-
I think this is a statement on interpretation rather than statistics alone
-
I have seen many times people unwittingly cite numbers that don't really support what they're saying. I think this as phenomenon has more to do with illiteracy/innumeracy of the speaker or expected in the audience. The point of numbers is insight.
-
Part of getting the insight correct is understanding where your data comes from. Samples of data that are biased can still be useful if you understand where it is coming from- -take the ww2 bomber armor problem: Navy was going to uparmor spots frequently hit, not accounting for..pic.twitter.com/UuyAJcVjNX
-
where their data came from.. a statistician pointed out that their source data for hit locations was only from planes that returned home. Unrecovered were ones that were fatally hit. The implication of this bias meant the data was like a film negative of the desired insight
-
Social sciences, often using questionnaires, experiments, or public data there is, the common sampling biases are more along the lines of "we don't have data on many substrata of the pop" or "this is a picture of who our method can reach & find cooperative" limits valid insight.
-
Often the desired deeper insight isn't really probed at or accessible. "Do you approve of Papa John's leadership?" Who is answering the question? How is it being asked? Even if a Herculean effort to find a set representative answers of gen pop, what does it really mean? Not much.
-
yes of course. this has always been the main problem, the translatability of a sample group to the gen-pop. questionnaires seem to be the most troubling in terms of bias from a social science perspective. as for citing numbers, read any click bait huffpo/buzzfeed article with
-
stats and you find the most "shocking!" revelations that will "MIC DROP" on their ideological enemies. every single time you actually look up the papers they cite, and the picture is either nuanced, or downright the opposite of their conclusions.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.