Internet Resources for Statistics Version 0.2, 17 August 1993 Una Smith Department of Biology smith-una@yale.edu Yale University New Haven, CT 06511 USA -*- How to Use this FAQ This FAQ is best used as a supplement to other documents. To learn more about the Internet and Usenet, you may find it useful to read my FAQ for biologists (Smith 1993), or some of the other FAQs that are available in Usenet and on the rtfm.mit.edu anonymous FTP archive. Also, you might want to read one of the newly published Internet guidebooks such as Kehoe (1992), Krol (1992), or LaQuey and Ryer (1992). -*- Conditions of Use This FAQ may be freely distributed, provided that the text is not edited in any way beyond removal of the headers; the format may be changed in any way that is convenient for printed or electronic presentation. This FAQ may be freely adapted, provided that the source is acknowledged. However, this FAQ may not be sold for profit, in either the original or an adapted form, without permission from the author. Virtually every service or resource mentioned in this FAQ (and this FAQ itself) is the un-paid, voluntary contribution of scientists and students, both graduate and undergraduate. If you make significant use of any document, data or software provided via the Internet, the authors would be grateful if you would cite them or otherwise acknowledge their efforts. Any publicly available material should be considered formally published, and cited as such. Also, if you find an Internet archive to be especially useful in and of itself, please contact the administrator to ask about the prefered form of acknowledgement. -*- How to Get Updates Once this FAQ has matured a bit, it will become a formal Usenet FAQ, and will thus be distributed and archived in a number of places. If you would like to contribute material to this effort, please don't hesitate. All useful material will be incorporated and gratefully acknowledged in subsequent versions. -*- Networking Below are listed those Usenet newsgroups and mailing lists of particular interest to statisticians and scientists who use statistics. Usenet - When posting to more than one newsgroup, use the cross-posting feature so only one copy of your article goes out, but is seen by many people. - Post (and cross-post) sparingly to groups that have associated mailing lists, to give a break to people who must read the groups via e-mail. The cross-posting of articles to more than one gated newsgroup is strongly discouraged, since the e-mail subscribers will get multiple copies of any cross-posted articles. Usenet readers should be aware of proper etiquette for mailing lists when posting to gated newsgroups. -*- Statistics Newsgroups G - the newsgroup has a gateway to a mailing list (see below). F - a "FAQ" document is provided to answer frequently asked questions. sci.stat.consult G Statistical consulting sci.stat.edu G Journal of Statistics Education List sci.stat.math Mathematical statistics comp.soft-sys.khoros FG Khoros Discussion comp.soft-sys.matlab F MATLAB Discussion comp.soft-sys.sas G SAS Discussion comp.soft-sys.shazam G SHAZAM Discussion comp.soft-sys.spss G SPSS Statistical Discussion -*- Gated Mailing Lists There has been a growing trend in the past few years to link mailing lists and newsgroups. Reading the discussions via Usenet newsgroups is generally prefered to e-mail subscriptions, when both are available. sci.stat.consult is stat-l@vm1.mcgill.ca (LISTSERV, see below). sci.stat.edu is edstat-l@jse.stat.ncsu.edu (ListServer). comp.soft-sys.khoros is gated to a mailing list administered by khoros-request@chama.eece.unm.edu. comp.soft-sys.sas is sas-l@UGA.cc.uga.edu (LISTSERV). comp.soft-sys.spss is spssx-l@UGA.cc.uga.edu (LISTSERV). -*- LISTSERV Mailing Lists The following are mailing lists using the "LISTSERV" automated mailing list manager (MLM) program. To subscribe to any of these, send e-mail to the username "listserv" at the same address, with the text subscribe For example, if I wanted to subscribe to BIOMET-L, I would send e-mail to listserv@albnydh2.bitnet with the text "subscribe biomet-l Una Smith". For a brief guide to the LISTSERV, send the text "send listserv refcard". To find out who is the administrator of a list, and other details, send the text "review short". biomet-l@ALBNYDH2.bitnet Bureau of Biometrics at Albany bmdp-l@vm1.mcgill.ca BMDP Software Users morphmet@CUNYVM.cuny.edu Biological Morphometrics Mailing List pstat-l@IRLEARN.ucd.ie Discussion of Stats and Programming saspac-l@UMSLVMA.umsl.edu SAS Public Access Consortium -*- ListServer Mailing Lists The following mailing lists use an MLM named "ListServer" that accepts subscriptions with the same syntax that LISTSERV uses (see above), but differs in some important ways. For a help file, send the text "help". jse-announce@jse.stat.ncsu.edu J. Stat. Education announcements jse-talk@jse.stat.ncsu.edu J. Stat. Education discussion forum qmlist@tbone.biol.scarolina.edu Quantitative Morphology List -*- Other Mailing Lists Topic or name Mailing list address Subscription instructions ----------------------------------------------------------------------- Genstat statistics package discussion genstat@ib.rl.ac.uk Send "subscribe genstat " to listral@ib.rl.ac.uk. The S statistics package s-news@utstat.toronto.edu Send e-mail to s-news-request@utstat.toronto.edu. -*- Internet Archives Computer sites supporting some sort of public access, and of some interest to statisticians: Internet node name Topic/Agency Access method ------------------------------------------------------------------------- ftp.sas.com (NC USA) SAS-related information f jse.stat.ncsu.edu (NC USA) Journal of Stat. Educ. f G sunsite.unc.edu (NC USA) SAS stuff and more E f G T [1] martini.eecs.umich.edu (MI USA) Geographic Name Server t [2] ksuvxa.kent.edu (KY USA) Directory of lists f rtfm.mit.edu (MA USA) Usenet FAQ repository e f [3] stis.nsf.gov (DC USA) Nat. Science Foundation f G e - e-mail file requests (see notes this section for e-mail addresses). E - e-mail search requests (see notes this section). f - anonymous FTP (see Access by Email below if you cannot use FTP). g - gopher server G - gopher server plus WAIS index searches t - public telnet access T - public telnet access plus e-mail returns of search results W - WAIS server plus WAIS index searches Notes: 1: For help, e-mail info@sunsite.unc.edu; telnet username "swais" for WAIS seaches; telnet username "gopher" for plain gopher access if you do not have access to WAIS and gopher at your site. 2: Use port 3000, no username; "help" gets instructions. 3: See Anonymous FTP and Access by E-mail below. -*- Anonymous FTP The principal way of retrieving files (data, software, information) from Internet archives is to use "anonymous FTP". To receive a short guide explaining anonymous FTP and how to use it, send e-mail with the text "help" to info@sunsite.unc.edu. -*- Access by E-mail Bitnet does not support FTP, but many Bitnet nodes are also full Internet sites, and so do support FTP. For those who only have access to computers on Bitnet, Princeton University offers a file transfer service by e-mail. Bitftp@PUCC.bitnet will send a help file in response to the message "help". There is an identical server in Germany: Bitftp@DEARN from within Bitnet/EARN or bitftp@vm.gmd.de from the Internet. This server should be used only for FTP requests involving transfers within Europe. If you have neither full Internet access nor an account on a Bitnet node, you can still get files from anonymous FTP archives by e-mail courtesy of ftpmail@decwrl.dec.com, which will send instructions in response to the word "help" followed by "quit" on separate lines of an e-mail message. Also, you can retrieve FAQ documents via e-mail from the Usenet FAQ repository, rtfm.mit.edu: to get a help file and a list of all the FAQs stored there, send e-mail to mail-server@rtfm.mit.edu with the text help index -*- Suggested Reading Kehoe, B.P. (1992) "Zen and the Art of the Internet: A Beginner's Guide to the Internet", 2nd Edition (July). Prentice Hall, Englewood Cliffs, NJ. 112 pages. The 1st Edition, (February) is available in Postscript format via anonymous FTP from ftp.cs.widener.edu and many other Internet archives. Krol, E. (1992) "The Whole Internet: Catalog & User's Guide". O'Reilly & Associates, Inc., Sebastopol, CA. 376 pages. LaQuey, T.L. and J.C. Ryer (1992) "The Internet Companion: A Beginner's Guide to Global Networking". Addison-Wesley Publishing Co., Reading, MA. 208 pages. Smith, U.R. (1993) "A Biologist's Guide to Internet Resources". Usenet sci.answers. Available via anonymous FTP from rtfm.mit.edu, as file pub/usenet/news.answers/biology/guide. Thomas, E. (1993) "Revised LISTSERV System Reference Library". Listserv@BITNIC.educom.edu, release 1.7c. Retrievable from any listserver using the mail message "send listserv refcard". -*- Some Statistics This is an abbreviated set of data from the USENET readership report for June 1993, posted in news.lists. +-- Estimated total number of people who read the group, worldwide. | +-- Actual number of readers in sampled population | | +-- Propagation: how many sites receive this group at all | | | +-- Recent traffic (messages per month) | | | | +-- Recent traffic (kilobytes per month) | | | | | +-- Crossposting percentage | | | | | | +-- Cost ratio: $US/month/rdr | | | | | | | +-- Share: % of newsrders | | | | | | | | who read this group. V V V V V V V V 45000 793 81% 258 378.9 12% 0.01 1.9% sci.math.stat 17000 296 66% 226 421.5 2% 0.03 0.7% comp.soft-sys.matlab 12000 204 48% 40 65.3 0% 0.00 0.5% comp.soft-sys.shazam 7300 127 37% 426 828.0 1% 0.07 0.3% bit.listserv.sas-l 7100 125 36% 346 669.1 1% 0.06 0.3% bit.listserv.stat-l 7000 122 34% 68 131.6 14% 0.01 0.3% bit.listserv.edstat-l 6800 119 36% 83 147.0 1% 0.01 0.3% bit.listserv.spssx-l And July 1993, a few weeks after reorganization of the statistics newsgroups: 4400 71 21% 49 69.9 13% 0.01 0.2% sci.stat.math 2900 48 19% 47 84.8 2% 0.01 0.1% sci.stat.consult 19000 302 66% 281 483.4 4% 0.03 0.8% comp.soft-sys.matlab 8600 141 53% 24 23.9 0% 0.00 0.4% comp.soft-sys.shazam 2900 48 22% 22 29.1 0% 0.00 0.1% comp.soft-sys.sas 2500 40 22% 23 33.3 0% 0.00 0.1% comp.soft-sys.spss 48000 786 81% 266 463.6 12% 0.01 2.0% sci.math.stat 9600 156 37% 324 647.6 2% 0.04 0.4% bit.listserv.stat-l 9300 152 37% 416 821.3 0% 0.05 0.4% bit.listserv.sas-l 9000 147 33% 72 179.3 4% 0.01 0.4% bit.listserv.edstat-l 8800 144 36% 66 117.4 0% 0.01 0.4% bit.listserv.spssx-l The last 5 groups have been superceded and will be removed soon. Note that 6 times as many actual readers were polled for sci.math.stat as for bit.listserv.sas-l or bit.listserv.stat-l, yet both of the latter groups have more traffic than sci.math.stat. These groups have large e-mail readerships (although Usenet readership increased more than 10% in the past month alone). The Usenet survey data entirely overlooks e-mail subscribers to any newsgroup with a gated mailing list, but does record the traffic generated by those uncounted readers. It is possible to get a low estimate of e-mail subscribers by reviewing the subscription lists, but this does not account for the readers of local redistribution lists. Note also that the average propagation of bit.listserv.* groups is less than half that of the sci.* groups. The recent reorganization of the last five groups listed above into sci.stat.* and comp.soft-sys.* should permit many current e-mail subscribers to "upgrade" to reading these groups via Usenet. -*- The End -- Una Smith Department of Biology smith-una@yale.edu Yale University New Haven, CT 06511 USA