Statistical insignificance is meaningless. Please show me a formal definition of it in statistics? It is not there period. Statistical insignificance is a term from marketing. Not stats. Statistical significance has a specific meaning. If a difference is considered not statistically significant, it is not insignificant, what it mean is that if you duplicated these results an infinite number of times 95%, 99%, 90%, or whatever arbitrary probability value you choose, of the results will fall within a certain range. Change the sample size and the result is no longer not significant. You will probably not find many reputable statisticians who use the phrase statistical insignificance.
The term is just a bastardization put forward by marketers not scientists. On Fri, Oct 5, 2012 at 1:25 PM, Judah McAuley <[email protected]> wrote: > > I disagree, Larry. Small fluctuations within the margin of error are > considered statistically insignificant. > > Of course the comments Jerry made have a built in presumption that the > electorate is a stable population, which isn't true. It very well > might be the case that very few people who voted for McCain in 2008 > will vote for Obama in 2012. The bigger movements, however, take place > amongst the people leaving the electorate (death, disenfranchisement, > or deciding not to vote) or entering the electorate (coming of age, > becoming citizens, voting this time but not in 2008). > > One of the more interesting (to me at least) stats of the last 4 years > is the change in party identification. Republicans (as a percentage of > the electorate) have plunged, Democrats have gained slightly and > Independents have soared, now becoming the single biggest block of > voters. I'm sure that some of that movement must be due to the Tea > Party who will (I imagine) likely back the Republican candidate in > most elections. But maybe not. And I'm curious what the other factors > are in the rise of the independents and what kind of demographics they > represent. > > It'll be really interesting to see how that all turns out come Election day. > > Judah > > On Fri, Oct 5, 2012 at 10:11 AM, Larry C. Lyons <[email protected]> wrote: >> >> Jerry there is no such thing as a statistically insignificant amount. >> If you're going to use the terms, at least use them correctly - >> http://en.wikipedia.org/wiki/Statistical_significance >> >> On Fri, Oct 5, 2012 at 12:08 PM, Jerry Barnes <[email protected]> wrote: >>> >>> "Wrong. I know at least 2 people who voted for McCain that are voting for >>> Obama - myself and my wife." >>> >>> You voted for McCain? Wow. >>> >>> And you admit you are voting for Obama? Double wow. Good on you for >>> having the courage to stand up on what you are doing. I can't say I >>> understand it, but it's your vote (there are other candidates besides >>> Romney). Now if only Obama would stand up and take credit for what he's >>> accomplished. >>> >>> Anyway, I can't speak for the oddsmaker, but when he says no one, I imagine >>> he means a statistically insignificant amount. That is, practically zero. >>> >>> >>> J >>> >>> - >>> >>> The middle class has been buried the last four years. - Joe Biden >>> >>> I mean, you got the first mainstream African-American who is articulate and >>> bright and clean and a nice-looking guy," Joe Biden on Barack Obama >>> >>> >>> >> >> > > ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~| Order the Adobe Coldfusion Anthology now! http://www.amazon.com/Adobe-Coldfusion-Anthology/dp/1430272155/?tag=houseoffusion Archive: http://www.houseoffusion.com/groups/cf-community/message.cfm/messageid:355815 Subscription: http://www.houseoffusion.com/groups/cf-community/subscribe.cfm Unsubscribe: http://www.houseoffusion.com/groups/cf-community/unsubscribe.cfm
