Sandbox: Difference between revisions

From ChanceWiki
Jump to navigation Jump to search
No edit summary
No edit summary
Line 9: Line 9:
The original article was discussed in Chance News 36 [http://chance.dartmouth.edu/chancewiki/index.php/Chance_News_36#Sex_and_Cereal here] by Paul Alper so we would advice you to look at this also.
The original article was discussed in Chance News 36 [http://chance.dartmouth.edu/chancewiki/index.php/Chance_News_36#Sex_and_Cereal here] by Paul Alper so we would advice you to look at this also.


Beck writes


<blockquote>Some statisticians argue for a tougher standard of proof when researchers are fishing in large data sets. One method, a Bonferroni adjustment, requires dividing the usual mathematical formula by the number of variables; if 100 foods are studied, the link must be 100 times as strong as usual to be considered significant. Otherwise, statisticians say only strict clinical trials with a control group and a test group and one variable can truly prove a cause-and-effect association.<br><pr>


Epidemiologists argue that a Bonferroni adjustment throws out many legitimate findings, and that it's irrelevant how many other factors are studied simultaneously. They also note that controlled clinical trials are costly, time-consuming and sometimes unethical. The link between smoking and cancer, for example, was seen in many observational studies, but forcing subjects to smoke for years to prove it would be untenable.</blockquote>


To be continued.


Submitted by Laurie Snell
Submitted by Laurie Snell

Revision as of 20:20, 31 January 2009

Does Bran Make the Man? What Statistics Really Tell Us

Annette Georgey wrote to the Isolated Statisticans

An article came out in today's Wall St. Journal that would be fun to use for introductory stats classes. It touches on several concepts--the limits of observational studies, confounding, spurious correlations, type I errors.

The author, Melinda Beck, usas as example an article"You are what your mother eats" in the Proceedings of the Royal Society B and on a criticism of this article: "Cereal-Induced gender selection? Most likely a multiple testing false positive" in the same journal.

The original article was discussed in Chance News 36 here by Paul Alper so we would advice you to look at this also.

Beck writes

Some statisticians argue for a tougher standard of proof when researchers are fishing in large data sets. One method, a Bonferroni adjustment, requires dividing the usual mathematical formula by the number of variables; if 100 foods are studied, the link must be 100 times as strong as usual to be considered significant. Otherwise, statisticians say only strict clinical trials with a control group and a test group and one variable can truly prove a cause-and-effect association.
<pr> Epidemiologists argue that a Bonferroni adjustment throws out many legitimate findings, and that it's irrelevant how many other factors are studied simultaneously. They also note that controlled clinical trials are costly, time-consuming and sometimes unethical. The link between smoking and cancer, for example, was seen in many observational studies, but forcing subjects to smoke for years to prove it would be untenable.


Submitted by Laurie Snell


http://online.wsj.com/article/SB123301860344617927.html?mod=todays_us_nonsub_pj Does Breakfast Cereal Affect a Baby's Gender?


Here we will have a discussion of an article in the Wall Street Journal

which is based on an article"You are what your mother eats" in the Proceedings of the Royal Society and on a criticism of this article: "Cereal-Induced gender selection? Most likely a multiple testing false positive" in the same journal.

You might want to read these articles before we figure out something wise to say about the articles.

To be continued.

Submitted by Laurie Snell