41
edits
Changes
Jump to navigation
Jump to search
Line 109:
Line 109: + + + + + + + + + + + + + +
Talk:Mystery:Why Do Non-Conservatives Exist? (view source)
Revision as of 15:47, January 6, 2009
, 15:47, January 6, 2009no edit summary
:::::::: Drek, you really "take the cake" for the most long-winded liberal rant in recent memory here. The field of statistics does include estimates, and no one doubts that that there are percentages for each category listed. Are the estimates off slightly? Perhaps, but be specific about which one you think may be off.--[[User:Aschlafly|aschlafly]] 13:48, 16 December 2008 (EST)
:::::::: Drek, you really "take the cake" for the most long-winded liberal rant in recent memory here. The field of statistics does include estimates, and no one doubts that that there are percentages for each category listed. Are the estimates off slightly? Perhaps, but be specific about which one you think may be off.--[[User:Aschlafly|aschlafly]] 13:48, 16 December 2008 (EST)
::::::::::Mr. Schlafly,
::::::::::It has taken me a long time to respond to your more or less final remarks on this subject. This has been due to travel during the Christmas holidays so that my wife and I would be with family as well as a desire to take my time in thinking before responding. I will attempt to answer each of your remarks directly.
::::::::::First, I am sorry that you regard my concerns as a "liberal rant." I am not interested in the politics of this article but only in the legitimacy of labeling your estimates with the heading of "Statistical Analysis." Labeling my arguments "liberal" does nothing to refute them.
::::::::::Second, I never claimed that statistics do not include estimates. Indeed, in the second paragraph of my original comments I remarked, "...it refers to an estimate or "statistic" rather than to a true population parameter." Your response to me that "The field of statistics does include estimates..." has nothing to do with what I said. Do I think your estimates off "slightly"? Without question- all estimates can safely be said to deviate from the true population values by at least a small amount. This is a statistical reality. As to which I think may be off- I regard all of them suspect as you have provided no information about where these estimates derive from.
::::::::::Except, that isn't really true. In a response to FernoKlump at 21:22 on December 16, 2008 you remark that, "Like any estimate, it's based on experience and logic." This is the only time you have ever provided anything even approximating a citation for these estimates. Unfortunately, it does nothing to alay my fears. In regards to "experience," as I know you are familiar with the common statistical saying "Correlation does not equal causation," allow me to remind you of another common statistical saying: "The plural of 'anecdote' is not 'data.'" That is to say, no individual's experiences- no matter how reasonable and observant they are- can substitute for properly gathered information. The reason is simple: the world is a large place and we are, individually, very small. We only perceive the small slice of reality that we ourselves occupy and fail to observe the world from any other position. As such, even if we suppose that there are no biases in our perceptions whatsoever (a superhuman claim) it is vanishingly unlikely that those perceptions match perfectly with observable reality. In regards to "logic" I can only remind you that logic is a poor guide if one has flawed information. If we believe that ill health is caused by imbalances in the humors of the body, it is perfectly logical to treat a variety of disorders with bloodletting. Yet, if we evaluate this practice scientifically we find that in most cases it does more harm than good. Good logic is no substitute for good data.
::::::::::I suspect that you will not find my arguments above compelling, so please allow me to present a handful of additional points. The 2006 edition of the American Heritage Dictionary defines "statistics" as: "1. The mathematics of the collection, organization, and interpretation of numerical data, especially the analysis of population characteristics by inference from sampling. 2. Numerical data." WordNet 3.0 defines it as, "a branch of applied mathematics concerned with the collection and interpretation of quantitative data and the use of probability theory to estimate population parameters." The American Heritage Science Dictionary defines it as, "1. The branch of mathematics that deals with the collection, organization, analysis, and interpretation of numerical data. Statistics is especially useful in drawing general conclusions about a set of data from a sample of the data. 2. Numerical data." Finally, if we examine Conservapedia's own article on statistics we find this in the first paragraph: "Statistics is the application of mathematics to the understanding of data. It involves all stages of data collection and processing from the initial collection, to the analysis and ultimately to the conclusions and interpretations of the data." You will note the primacy of data in all of these definitions. Nowhere do any of these sources refer to "experience" or "logic" with the same emphasis as they do to "data." Likewise, I can review my books on statistics as long as you like and will never find a term in any equation where "experience" is to be added, while all deal in one way or another with data.
::::::::::At this point I consider that you have finally revealed that as these estimates are based on "experience and logic" rather than data, you have conceded that they are not the product of statistical analysis. I do not object to your referring to them as estimates, but do object in the strongest terms to your labeling them "statistical analysis." Your estimates are not the product of statistics. You can accuse me of producing another liberal rant, but that does not make me wrong. You can scold people for "carping," but that does not make your estimates reliable. This is not politics, this is mathematics. -Drek
::::::::: He's not claiming the statistics are wrong, he's saying that they are meaningless if the method of finding them is withheld. '''[[user:FernoKlump|<font color="#000066" >FernoKlump</font>]]'''<sup>[[User:FernoKlump/petition|<font color="#bd2433" >Mr. Schlafly! Look at this petition!]]</font></sup> 20:09, 16 December 2008 (EST)
::::::::: He's not claiming the statistics are wrong, he's saying that they are meaningless if the method of finding them is withheld. '''[[user:FernoKlump|<font color="#000066" >FernoKlump</font>]]'''<sup>[[User:FernoKlump/petition|<font color="#bd2433" >Mr. Schlafly! Look at this petition!]]</font></sup> 20:09, 16 December 2008 (EST)