[R] p values from GLM
spencer.graves at effectivedefense.org
Sat Apr 2 18:51:20 CEST 2016
On 4/2/2016 11:07 AM, David Winsemius wrote:
>> On Apr 1, 2016, at 5:01 PM, Duncan Murdoch <murdoch.duncan at gmail.com> wrote:
>> On 01/04/2016 6:46 PM, Bert Gunter wrote:
>>> ... of course, whether one **should** get them is questionable...
>> They're just statistics. How could it hurt to look at them?
> Like Rolf, I thought that this utterance on April 1 deserved fortune enshrinement. It reminded me of one of my favorite articles: "P-Values are Random Variables".
> Unfortunately a legal copy of that paper is still behind a corporate firewall for which you would need to fork over USD 50.00, but a google search for "P-Values are Random Variables The American Statistician" should yield options for the less squeamish. (My copy was obtained when I did have legal access.)
How much did money or do the authors of that paper receive in
That's important, because the purpose of US copyright law is, "To
promote the Progress of Science and useful Arts, by securing for limited
Times to Authors and Inventors the exclusive Right to their respective
Writings and Discoveries." (E.g., Wikipedia, "Copyright law of the
few if any refereed academic papers are written for financial gain:
Lawrence Lessig said that congressional representatives rarely hear
counterarguments to the garbage they get from corporate lobbyists. The
Trans Pacific Partnership (TPP, and probably also the Transatlantic
Trade and Investment Partnership) will strengthen the rights of
corporations in this area. If you think that will limit the progress of
science and the useful arts, as I do, I suggest you contact your elected
representatives and tell them so -- if you are a citizen of a country
with elected representatives. I think we should also ask the American
Statistical Association how much money they make from that and what it
would take to put all that material in the public domain. I think
professional organizations should come out strongly against these
provisions of US copyright law and trade agreements that strengthen
rather than weaken the stranglehold that major corporations have on the
intellectual heritage of humanity.
This relates to R, because R is based on an assumption that the
dissemination of publications, articles and software, for which the
authors are not remunerated from copyright proceeds should not be
limited by pre-internet rules that stifle unnecessarily the distribution
of knowledge and with it improvements in productivity and economic growth.
More information about the R-help