Talk:Statistics

Please click here to add new comments at the bottom of this page.

List of Classical Books and Contributors to the Statistics field

I read this article with interest, and missed a list of classical books on Statistics or a list of contributors who have done most to the field of Statistics in the past century. 76.30.100.77 (talk) 15:31, 14 March 2009 (UTC)Narayana Subramaniam

These may be what you are looking for:

• List of important publications in statistics
• Founders of statistics

—G716 <^T·_C> 22:49, 14 April 2009 (UTC)

Introduction: design and sampling need greater emphasis (equal to "data analysis" imho)

Statistics is better described as the methodology of scientific practice, which is concerned with both "making sense of data" and "producing data that makes sense".

(The practical concern with scientific practice distinguishes statistics from the philosophy of science.)

The introduction emphasizes the (passive) analysis of data, not the (active) production of useful data-sets, using the design of experiments and sampling.

The current description over-emphasizes modelling data---abduction, rather than inductive procedures whose properties are studied with deduction (to use the Peircean trilogy of deduction, induction, and abduction).

The title of C.R. Rao's book gives a better synapsis of our discipline "Statistics: Putting Chance to Work". A greater emphasis on experiments and sampling appears in the best works by the greatest statisticians---Fisher, Rao, Cochran, Peirce, Neyman, Cox, etc. —Preceding unsigned comment added by Kiefer.Wolfowitz (talk • contribs) 13:22, 24 May 2009 (UTC)

A suggested description of statistics

Statisticians (working as part of a research project) "create data that makes sense" with random sampling and with randomized experiments; the design of a statistical sample or experiment specifies the analysis of the data (before the data be available). When reconsidering data from experiments and samples or when analyzing data from observational studies, statisticians "make sense of the data" using the art of modelling and the theory of inference---with model selection and estimation; the estimated models and consequential predictions should be tested on new data.

From my contribution to description of statistics under mathematics

(UPDATED Kiefer.Wolfowitz (talk) 14:25, 26 May 2009 (UTC)) Kiefer.Wolfowitz (talk) 00:48, 26 May 2009 (UTC)

Discussion

This comment was made in response to a previous description of statistics, which had even more flaws. My thanks are due to the criticisms of this colleague ( Kiefer.Wolfowitz (talk) 14:25, 26 May 2009 (UTC) ).

"Statisticians help scientists..." is misleading. First, statisticians are scientists, and second, statistics has many applications outside the fields of "science" (law, public policy, business decision making, etc). Furthermore, "when scientists produce data from observational studies or bad experiments, statisticians "make sense of the data" " is nonsense: statisticians "make sense of data" (modelling, estimation, prediction, hypothesis testing, inference, etc) regardless of the source: observational or designed studies, good or bad experiments alike. What is a "bad" experiment anyway? —G716 <^T·_C> 02:45, 26 May 2009 (UTC)

REPLY: My earlier reply seems no longer relevant, since the updated revision was motivated to meet the above objections. Kiefer.Wolfowitz (talk) 10:49, 26 May 2009 (UTC) Kiefer.Wolfowitz (talk) 14:25, 26 May 2009 (UTC)

I do agree that design of experiments is a very big part of the subject. However I don't think we need a complete rewrite of the lead. The current lead does a good job of summarising a lot in a few paragraphs, a minor tweek might be more appropriate. --Salix (talk): 11:43, 26 May 2009 (UTC)

In the lead paragraph, I inserted the following sentence [which I hope falls under (permissible) "tweaking"]: "Statisticians improve the quality of data with the design of experiments and survey sampling."Kiefer.Wolfowitz (talk) 17:14, 7 June 2009 (UTC)

Statistics is a mathematical science but not part of applied mathematics

The mathematics article annexed statistics as a field of applied mathematics.

My correction follows:

Applied mathematics has significant overlap with the discipline of statistics, whose theory is formulated mathematically, especially with probability theory.

Kiefer.Wolfowitz (talk) 00:48, 26 May 2009 (UTC) Kiefer.Wolfowitz (talk) 14:25, 26 May 2009 (UTC)

what does statistics mean? i still don't get it. a teacher from our school asked us to explain it, but i don't understand. please help me. —Preceding unsigned comment added by 121.97.157.25 (talk) 11:43, 2 June 2009 (UTC)

Can you have negative weighting for sensors that measure a positive quantity?

Answer or referall to an academic expert appreciated.

Is it automatically unphysical to have a PCA reconstruction that has some stations negatively weighted? Would think that it could occur for both degeneracy and anticorrelation with the average (actual physical effects). Of course the summation must be positive, but is it automatically wrong if some of the stations have negative weights?

This is being debated on these blog threads. Unfortunatley, the debate has muddled particular examination of the Stieg Antarctic PCA-based recon with general absolute claims that negative weightings are bad, bad, bad.

Could you please adjuticate?

See here:

http://noconsensus.wordpress.com/2009/06/07/antarctic-warming-the-final-straw/#comment-6727

http://noconsensus.wordpress.com/2009/06/09/tired-and-wrong-again/#comment-6726

http://wattsupwiththat.com/2009/06/10/quote-of-the-week-9-negative-thermometers/#more-8362

http://www.climate-skeptic.com/2009/06/forgetting-about-physical-reality.html —Preceding unsigned comment added by 69.250.46.136 (talk) 17:27, 19 June 2009 (UTC)

Statistics Calculators Portal

I would like to add a new non-commercial resource to this article. The web-page is : http://www.solvemymath.com/online_math_calculator/statistics/index.php statistics calculators portal .

Please verify it's integrity and correctness, and if it respects Wikipedia's external resource guidelines add it to this article as a free resource. —Preceding unsigned comment added by Livius3 (talk • contribs) 15:21, 3 October 2009 (UTC)

Does anyone have anything against this link? —Preceding unsigned comment added by 91.201.193.45 (talk) 02:29, 11 October 2009 (UTC)

Statistics is branch of mathematics

I added the cited fact that statistics is a branch of mathematics. As references, I used a lot of books, some of them of notable "statisticians", which consist this fact. I rsepect the opinion of some great mathematicians and statisticians, that statistics is a science, and I put this sentence, after the lead one. The generally opinion is that, statistics is branch of mathematics.--Kiril Simeonovski (talk) 00:04, 5 October 2009 (UTC)

I do not think it is true that it is "generally accepted." I think people argue about this a lot. It is not a branch of mathematics like Algebra, Geometry, and Analysis (Calculus). It does use techniques of mathematics. You cited a zillion sources that agree with you but only one that gave the alternate definition. I could put in a zillion for the other, but I don't think it is a matter of who has more citations. I think some people say one and some say the other. I am editting the sentence to read that some consider it one thing and some consider it the other. GumbyProf: "I'm about ideas, but I'm not always about good ideas." (talk) 11:47, 23 October 2009 (UTC)