reid@decwrl.UUCP (Brian Reid) (09/01/86)
USENET READERSHIP SUMMARY REPORT for Aug 86
This is a monthly posting from the USENET Measurement Project at the DEC
Western Research Laboratory in Palo Alto, California.
This survey is based on a sample of data taken from various USENET sites.
At the end of this message there is a short explanation of the measurement
techniques and the meaning of the various statistics.
The complete set of readership data (of which this is a summary) is posted
in mod.newslists
Brian Reid
OVERALL SUMMARY:
This Estimated
Sample for entire net
Sites: 443 4200
Fraction reporting: 10.55% 100%
Users with accounts: 59515 564000
Netreaders: 13222 125000
Average readers per site: 30
Percent of users who are netreaders: 22.22%
Average traffic per day (megabytes): 1.447
Average traffic per day (messages): 614
Traffic measurement interval: last 21 days
Readership measurement interval: last 75 days
TOP 40 NEWSGROUPS IN ORDER BY POPULARITY
+-- Estimated total number of people who read the group, worldwide.
| +-- Actual number of readers in sampled population
| | +-- Recent traffic, in messages per month.
| | | +-- Recent traffic, in kilobytes per month.
| | | | +-- Participation ratio: msgs/month/Krdrs
| | | | | +-- Cost ratio: $US/month/reader
| | | | | | +-- Rating: % of all users who
| | | | | | | read this group.
| | | | | | | +-- Share: % newsreaders
| | | | | | | | who read this group.
V V V V V V V V
1 27000 3121 15 40.1 0 0.01 5.2% 23.6% net.general
2 24000 2836 554 639.0 23 0.12 4.8% 21.4% net.jokes
3 21000 2461 135 1319.9 6 0.28 4.1% 18.6% net.sources
4 18000 2089 110 281.0 6 0.07 3.5% 15.8% net.jobs
5 17000 2047 42 1563.7 2 0.41 3.4% 15.5% mod.sources
6 14000 1652 177 263.6 12 0.08 2.8% 12.5% net.unix
7 14000 1600 687 1247.7 49 0.39 2.7% 12.1% net.singles
8 13000 1577 111 118.5 8 0.04 2.6% 11.9% net.wanted
9 13000 1507 281 467.1 21 0.16 2.5% 11.4% net.unix-wizards
10 12000 1454 60 622.9 5 0.23 2.4% 11.0% net.sources.games
11 12000 1441 161 240.2 13 0.09 2.4% 10.9% net.micro
12 12000 1440 252 433.5 21 0.16 2.4% 10.9% net.audio
13 12000 1361 160 263.3 13 0.10 2.3% 10.3% net.rumor
14 12000 1353 21 50.2 1 0.02 2.3% 10.2% net.ai
15 12000 1349 285 1321.4 23 0.49 2.3% 10.2% net.micro.pc
16 11000 1346 71 138.8 6 0.06 2.3% 10.2% net.arch
17 11000 1323 34 85.7 3 0.03 2.2% 10.0% net.sources.bugs
18 11000 1315 207 470.2 18 0.19 2.2% 9.9% net.lang.c
19 11000 1310 298 488.7 27 0.20 2.2% 9.9% net.movies
20 11000 1306 7 14.8 0 0.01 2.2% 9.9% mod.newprod
21 11000 1292 8 16.5 0 0.01 2.2% 9.8% net.announce.arpa-i
22 11000 1262 410 762.8 37 0.31 2.1% 9.5% net.micro.mac
23 10000 1219 175 243.0 17 0.11 2.0% 9.2% net.consumers
24 10000 1219 80 103.6 8 0.05 2.0% 9.2% net.sources.d
25 10000 1176 57 162.4 5 0.07 2.0% 8.9% net.news
26 9900 1166 68 150.3 6 0.07 2.0% 8.8% net.graphics
27 9900 1155 532 1109.8 53 0.50 1.9% 8.7% net.women
28 9500 1117 74 53.6 7 0.03 1.9% 8.4% net.wanted.sources
29 9400 1106 161 206.4 17 0.10 1.9% 8.4% net.cooks
30 9400 1104 131 198.2 13 0.09 1.9% 8.3% net.misc
31 9400 1096 378 616.7 40 0.29 1.8% 8.3% net.music
32 9300 1091 385 639.3 41 0.30 1.8% 8.3% net.auto
33 9000 1056 167 307.0 18 0.15 1.8% 8.0% net.books
34 8900 1046 74 123.1 8 0.06 1.8% 7.9% net.news.group
35 8600 1011 17 363.3 1 0.19 1.7% 7.6% net.sources.mac
36 8600 1003 108 206.7 12 0.11 1.7% 7.6% net.invest
37 8400 984 15 21.4 1 0.01 1.7% 7.4% net.jokes.d
38 8400 984 2 32.9 0 0.02 1.7% 7.4% mod.announce
39 8400 982 342 889.2 40 0.47 1.7% 7.4% net.micro.amiga
40 8300 973 114 128.6 13 0.07 1.6% 7.4% net.travel
TOP 40 NEWSGROUPS IN ORDER BY PER-READER COST
+-- Estimated total number of people who read the group, worldwide.
| +-- Actual number of readers in sampled population
| | +-- Recent traffic, in messages per month.
| | | +-- Recent traffic, in kilobytes per month.
| | | | +-- Participation ratio: msgs/month/Krdrs
| | | | | +-- Cost ratio: $US/month/reader
| | | | | | +-- Rating: % of all users who
| | | | | | | read this group.
| | | | | | | +-- Share: % newsreaders
| | | | | | | | who read this group.
V V V V V V V V
1 5900 688 702 1747.9 119 1.30 1.2% 5.2% net.politics
2 5500 650 285 907.1 51 0.73 1.1% 4.9% net.micro.atari16
3 3700 439 231 604.4 62 0.72 0.7% 3.3% net.religion
4 4700 555 282 646.4 60 0.61 0.9% 4.2% net.comics
5 8200 964 650 1039.2 79 0.56 1.6% 7.3% net.sf-lovers
6 2400 287 75 294.6 31 0.54 0.5% 2.2% net.politics.theory
7 5900 691 32 702.6 5 0.53 1.2% 5.2% mod.mac.binaries
8 9900 1155 532 1109.8 53 0.50 1.9% 8.7% net.women
9 3700 430 115 414.8 31 0.50 0.7% 3.3% net.origins
10 12000 1349 285 1321.4 23 0.49 2.3% 10.2% net.micro.pc
11 3700 439 11 407.7 3 0.49 0.7% 3.3% mod.amiga.sources
12 3400 396 144 371.3 42 0.48 0.7% 3.0% net.religion.christ
13 8400 982 342 889.2 40 0.47 1.7% 7.4% net.micro.amiga
14 5800 685 215 592.9 37 0.45 1.2% 5.2% mod.politics
15 5400 637 200 521.6 37 0.43 1.1% 4.8% net.motss
16 17000 2047 42 1563.7 2 0.41 3.4% 15.5% mod.sources
17 6600 773 294 600.7 44 0.40 1.3% 5.8% net.legal
18 14000 1600 687 1247.7 49 0.39 2.7% 12.1% net.singles
19 3800 450 178 327.0 46 0.38 0.8% 3.4% net.sport.baseball
20 1700 200 85 140.0 50 0.36 0.3% 1.5% mod.music.gaffa
21 2900 336 70 229.2 24 0.35 0.6% 2.5% net.tv.soaps
22 5900 694 234 454.4 39 0.34 1.2% 5.2% net.physics
23 4400 514 151 335.1 34 0.34 0.9% 3.9% net.micro.cpm
24 4500 528 140 335.0 31 0.33 0.9% 4.0% net.games.frp
25 4200 496 177 313.1 42 0.33 0.8% 3.8% net.ham-radio
26 6400 754 224 456.4 35 0.32 1.3% 5.7% net.kids
27 11000 1262 410 762.8 37 0.31 2.1% 9.5% net.micro.mac
28 9300 1091 385 639.3 41 0.30 1.8% 8.3% net.auto
29 9400 1096 378 616.7 40 0.29 1.8% 8.3% net.music
30 21000 2461 135 1319.9 6 0.28 4.1% 18.6% net.sources
31 3400 404 92 203.7 27 0.27 0.7% 3.1% net.sport.football
32 4400 515 100 254.0 22 0.26 0.9% 3.9% net.philosophy
33 3000 357 12 178.5 4 0.26 0.6% 2.7% mod.politics.arms-d
34 2800 331 34 166.8 12 0.26 0.6% 2.5% net.ham-radio.packe
35 4500 530 18 242.6 4 0.24 0.9% 4.0% mod.risks
36 12000 1454 60 622.9 5 0.23 2.4% 11.0% net.sources.games
37 5600 659 184 284.5 32 0.23 1.1% 5.0% net.aviation
38 5800 674 17 272.2 2 0.21 1.1% 5.1% mod.mac
39 11000 1310 298 488.7 27 0.20 2.2% 9.9% net.movies
40 6400 748 210 291.8 32 0.20 1.3% 5.7% net.video
TOP 40 NEWSGROUPS IN ORDER BY MESSAGES PER READER
+-- Estimated total number of people who read the group, worldwide.
| +-- Actual number of readers in sampled population
| | +-- Recent traffic, in messages per month.
| | | +-- Recent traffic, in kilobytes per month.
| | | | +-- Participation ratio: msgs/month/Krdrs
| | | | | +-- Cost ratio: $US/month/reader
| | | | | | +-- Rating: % of all users who
| | | | | | | read this group.
| | | | | | | +-- Share: % newsreaders
| | | | | | | | who read this group.
V V V V V V V V
1 5900 688 702 1747.9 119 1.30 1.2% 5.2% net.politics
2 8200 964 650 1039.2 79 0.56 1.6% 7.3% net.sf-lovers
3 3700 439 231 604.4 62 0.72 0.7% 3.3% net.religion
4 4700 555 282 646.4 60 0.61 0.9% 4.2% net.comics
5 9900 1155 532 1109.8 53 0.50 1.9% 8.7% net.women
6 5500 650 285 907.1 51 0.73 1.1% 4.9% net.micro.atari16
7 1700 200 85 140.0 50 0.36 0.3% 1.5% mod.music.gaffa
8 14000 1600 687 1247.7 49 0.39 2.7% 12.1% net.singles
9 3800 450 178 327.0 46 0.38 0.8% 3.4% net.sport.baseball
10 6600 773 294 600.7 44 0.40 1.3% 5.8% net.legal
11 4200 496 177 313.1 42 0.33 0.8% 3.8% net.ham-radio
12 3400 396 144 371.3 42 0.48 0.7% 3.0% net.religion.christ
13 9300 1091 385 639.3 41 0.30 1.8% 8.3% net.auto
14 9400 1096 378 616.7 40 0.29 1.8% 8.3% net.music
15 8400 982 342 889.2 40 0.47 1.7% 7.4% net.micro.amiga
16 5900 694 234 454.4 39 0.34 1.2% 5.2% net.physics
17 11000 1262 410 762.8 37 0.31 2.1% 9.5% net.micro.mac
18 5800 685 215 592.9 37 0.45 1.2% 5.2% mod.politics
19 5400 637 200 521.6 37 0.43 1.1% 4.8% net.motss
20 6400 754 224 456.4 35 0.32 1.3% 5.7% net.kids
21 4400 514 151 335.1 34 0.34 0.9% 3.9% net.micro.cpm
22 6400 748 210 291.8 32 0.20 1.3% 5.7% net.video
23 5600 659 184 284.5 32 0.23 1.1% 5.0% net.aviation
24 4500 528 140 335.0 31 0.33 0.9% 4.0% net.games.frp
25 3700 430 115 414.8 31 0.50 0.7% 3.3% net.origins
26 2400 287 75 294.6 31 0.54 0.5% 2.2% net.politics.theory
27 11000 1310 298 488.7 27 0.20 2.2% 9.9% net.movies
28 5200 607 144 198.0 27 0.17 1.0% 4.6% net.consumers.house
29 3400 404 92 203.7 27 0.27 0.7% 3.1% net.sport.football
30 3200 380 87 52.5 27 0.07 0.6% 2.9% net.test
31 6300 736 170 278.5 26 0.20 1.2% 5.6% net.startrek
32 3700 439 92 137.3 25 0.16 0.7% 3.3% net.nlang.india
33 6500 761 157 259.7 24 0.18 1.3% 5.8% net.bicycle
34 2900 336 70 229.2 24 0.35 0.6% 2.5% net.tv.soaps
35 24000 2836 554 639.0 23 0.12 4.8% 21.4% net.jokes
36 12000 1349 285 1321.4 23 0.49 2.3% 10.2% net.micro.pc
37 7300 860 174 288.5 23 0.18 1.4% 6.5% net.med
38 4800 558 114 184.8 23 0.17 0.9% 4.2% net.music.synth
39 4400 515 100 254.0 22 0.26 0.9% 3.9% net.philosophy
40 2700 314 61 73.6 22 0.12 0.5% 2.4% net.micro.atari8
BOTTOM 10 NEWSGROUPS IN ORDER BY POPULARITY
+-- Estimated total number of people who read the group, worldwide.
| +-- Actual number of readers in sampled population
| | +-- Recent traffic, in messages per month.
| | | +-- Recent traffic, in kilobytes per month.
| | | | +-- Participation ratio: msgs/month/Krdrs
| | | | | +-- Cost ratio: $US/month/reader
| | | | | | +-- Rating: % of all users who
| | | | | | | read this group.
| | | | | | | +-- Share: % newsreaders
| | | | | | | | who read this group.
V V V V V V V V
207 2500 296 10 15.4 4 0.03 0.5% 2.2% net.rec.bridge
208 2500 293 7 9.1 2 0.02 0.5% 2.2% net.rec.birds
209 2500 292 18 47.4 7 0.08 0.5% 2.2% net.rec.skydive
210 2500 289 4 5.7 1 0.01 0.5% 2.2% net.sport.hockey
211 2400 287 75 294.6 31 0.54 0.5% 2.2% net.politics.theory
212 2200 262 7 18.0 3 0.04 0.4% 2.0% mod.computers.massc
213 1900 225 35 72.5 18 0.17 0.4% 1.7% net.music.makers
214 1700 200 85 140.0 50 0.36 0.3% 1.5% mod.music.gaffa
215 1000 118 1 2.0 1 0.01 0.2% 0.9% net.house
216 650 76 5 5.4 8 0.04 0.1% 0.6% net.rec.radio
Valid data received from these sites:
3comvax 3d.dec.com a60 aaec acetes adelie adobe aero aero2 akgua akgub
akguc akov68.dec.com alberta alliant alv amdahl amdcad amdimage ames
anasaz angora.dec.com aragorn argus arran.tcom.stc.co.uk arthur
arthur.cs.purdue.edu ascvax asd.dec.com ashby.dec.com astrovax atari
athena aurora avanti.dec.com axis bagels.dec.com bartok.dec.com basser
baxta.dec.com bcm5000 bdmrrr being.dec.com bek-mc bemis.dec.com bene
beno beno.css.gov beowulf beta.dec.com binkly.dec.com birtch
bizet.dec.com bnl boves.dec.com brand brspyr1 btnix bu-cs bubba
bucsb.bu.edu bucsd bute.tcom.stc.co.uk cadomin cae780 caip.rutgers.edu
calay calgary candy.dec.com carmel cascade casto.dec.com castor.dec.com
cavell cbosgd ccvaxa celica.dec.com cgl.ucsf.edu chalmers cheviot
chronon ci-dandelion circe cisunx cit-vax clio clt.dec.com cod
cogito.dec.com cogsci.berkeley.edu columbia comet.dec.com
comet2.dec.com concurrent.co.uk cookie.dec.com cooper cortex
cory.berkeley.edu cp1 cpw.columbia.edu crvax1.dec.com csadfa cuae2
curium.dec.com cuuxb cvl cwruecmp cxsea cybvax0 dairy.dec.com dalcs
darth davinci dciem dcl-csvax decuac decwrl desint diablo dicome dione
dmcnh donner.dec.com down drexel drillsys dssdev.dec.com dukempd dycom
ector.cs.purdue.edu edison elbereth.rutgers.edu elsie elwood.dec.com
enmasse entropy eros espn.dec.com euclid.dec.com exodus.dec.com fai
felix fgvaxu.dec.com foxvax5 fremen.dec.com fritz frog frog.nosc.mil
furilo.dec.com ganash garfield.columbia.edu garfield.mun gatech genrad
gitpyr glacier glimmer gould9 gouldsd gramps.dec.com grebyn greg gsc
gt-stratus hammer handel hao harvard hercules ho95e hocad hpldora
hscfvax ia-sun2 iapetus ic ichaya icom ihu1n im4u imagen imt3b2 imt3b2
infinet infopro ipso iscuva ishtar istg.dec.com jasper jimi jon.dec.com
jplgodo kaos02.dec.com kepler killer kirk.dec.com kodak koning.dec.com
kosman kpe kryptn.dec.com labrea lando.dec.com lerouf.dec.com ll-vlsi
lll-crg lll-lcc lmi-ang lmi-angel logic.dec.com luke lymph.dec.com
macbeth maccunix majestix masscomp mcc-pp mcgill- mck-csc me-ncr meccts
medea micomvax midacs midas.dec.com mighty.dec.com mips miracl.dec.com
mirror mit-eddie mit-trillian mnetor mntgfx monet.dec.com mordred
mordred.cs.purdue.edu mormps.dec.com mosaic.dec.com mss msudoc
mtblue.dec.com mtgzy mtgzz mulga munnari munsell myrias navajo nbires
ncoast ncr-sd ncrcae ncsuvx nike njitcccc noao nonode.dec.com novavax
nsc nttlab nymgr.dec.com oblio oblio.dec.com ocean oddjob ohgua ohgub
ohguc onecom opus orion orstcs osiris otto panda parcvax pbsvax.dec.com
pcasso.dec.com pegasus percival philabs phoenix phri phuxa phuxc pitt
pixar pldvax.dec.com plooba plus5 pogo popeye poseidon potomac
princeton prism psivax ptovax.dec.com pucc-h pucc-i pucc-j pucc-k
pulman.dec.com pyramid qnda01 quad1 ra rainbo.dec.com raster
raynal.dec.com rayssd reed regina.dec.com renko.dec.com ritcv rlvd
rochester rocky rtech rti-sel saber sandia sarah.dec.com saturn sauron
scfac.dec.com scicom scotty.dec.com scribe.dec.com sdcc12 sdcc13 sdcc3
sdcc6 sdcc7 sdcsvax se-sd seismo sems shasta shire.dec.com sicsten
sigma siva.dec.com sjuvax sneaky sneezy soma spastic sphinx spock
squirt.dec.com ssc-vax star.dec.com stat-l stride stsci styx su-isl
suadb sunybcs talcott tallis.dec.com teddy tekig5 teklds telesoft tesla
tflop thoth.dec.com tilt titan titn tkov58.dec.com tle.dec.com
tonto.dec.com topaz.rutgers.edu tuck tucos tulane turtlevax tut tutctl
twitch tymix ucla-cs ucsfcgl ugdist uiucuxa uiucuxc uiucuxe uiucuxf
ukma ulowell ultra.dec.com umd-cs umd-ua umd5.umd.edu umn-cs unirot
unmvax uqcspe.oz usc-obe usc-oberon usrcv1.dec.com ut-sally utah-gr
utcs vaxwrk.dec.com vianet viking.dec.com vino.dec.com vlnvax.dec.com
voder vu-vlsi vulcan walldata wang7 wanginst watale watarts watcal
watcgl watdaisy watdcsu watdragon wateng water watlion watmath watmum
watnot watopt watpix watrose watvlsi weitek well wisdom wookie.dec.com
yale yetti yogi.dec.com zeus
------------------------------------------------------------------------------
EXPLANATION OF THE MEASUREMENTS AND STATISTICS
Survey data is taken by having one person at each site run a program called
"arbitron", which looks at the news or notes files and determines the
newsgroups that the user has read within a recent interval. To "read" a
newsgroup means to have been presented with the opportunity to look at at
least one message in it. Going through a newsgroup with the "n" key counts
as reading it. For a news site, "user X reads group Y" means that user X's
.newsrc file has marked at least one unexpired message in Y. If there is no
traffic in a newsgroup for the measurement period, then the survey will show
that nobody reads the group. For a notes site, "user X reads group Y" means
that user X has been in the notesfile with the sequencer in the last 14 days.
The "14 days" interval for notesfiles corresponds to "unexpired" for news.
The "arbitron" program is periodically posted to net.sources, or is available
from me (decwrl!reid). The notesfiles version of the program should be
available through standard notesfiles software distribution channels as well.
SITES SURVEYED IN THIS SAMPLE
"This Sample" means the set of sites that have sent in an arbitron report
within the past "Readership measurement interval" days. In every case the
most recent report from each site is used. At the moment, some of the
readership reports are several months old. In future postings those reports
will have expired and will not be included.
One might argue that the sample is self-selected, like the famous Literary
Digest Dewey-Truman election poll sample. It does in fact have a certain
self-selection factor in it, because we only get data from sites at which
someone participates in the survey. However, we do not require the
participation of every user at a site, only one user. The survey program
returns data for every user on the system on which it was run. Since there
are an average of 30 people per site reading news, there is a certain amount
of randomness introduced that way. Of course, the sample is biased in favor
of large sites (they are more likely to have a user willing to run the survey
program) and software-development-oriented sites (more likely to have a user
*able* to run the survey program). I intend to post, reasonably soon, some
breakdowns of statistics about the sites that have responded.
NETWORK SIZE
I determine the network size by looking at the set of sites that are
mentioned in the Path lines of news articles arriving at decwrl. This number
is consistently higher than the number of sites that posted a message (as
measured and posted from Seismo) because it includes passive sites that are
on the paths between posting sites and decwrl. Each month I store the names
of the hosts that are named that month, and for this report I used the past
5 months worth of data.
There are 4136 different sites in the Path lines of articles that
arrived at decwrl in the last 5 months. There are 5969 different sites in
the mod.map data, but mod.map includes every site that participates in uucp;
there is a considerable number of machines that exchange uucp mail but do not
get USENET. Of those 4136 sites, 87 (2%) are DEC E-net hosts not part of
uucp, and which therefore are not included in the 5969 figure.
Despite these various difficulties, I believe that 4200 is the best
estimate for the size of USENET. Because it is actually a measurement of the
number of sites that have posted a message or that are on the path to a site
that has posted a message, it will be slightly smaller than the number of
sites that actually read netnews. Any site that believes it is not being
counted can just ensure that it posts at least one message a year, so that
it will be counted.
NUMBER OF USERS
The number of users at each site is determined in a site-specific fashion.
Sometimes it is done by counting the number of user accounts that have
shells and login directories. Sometimes it is done by counting the number of
people who have logged in to the machine in some interval. Sometimes other
techniques are used. This number is probably not very accurate--certainly
not more accurate than to within a factor of two.
ESTIMATED TOTAL NUMBER OF PEOPLE WHO READ THIS GROUP, WORLDWIDE
There are two sources of error in this number. The number is computed by
multiplying the number of people in the sample who actually read the group by
the ratio of estimated network size to sample size. The estimated total can
therefore be biased by errors in the network size estimate (see above) and
also by errors in the determination of whether or not someone reads a group.
Assuming that "reading a group" is roughly the same as "thumbing through a
magazine", in that you don't necessarily have to read anything, but you have
to browse through it and see what is there, then the measurement error will
come primarily from inability to locate .newsrc files, which can either be
protected or moved out of root directories. There is no way of measuring the
effect on the measurements from unlocated .newsrc files, but it is not likely
to be more than a few percent of the total news readers.
MESSAGES PER MONTH AND KILOBYTES PER MONTH
Traffic is measured at decwrl, in Palo Alto, California. Any message that has
arrived at decwrl within the last "Traffic measurement interval" days is
counted, regardless of when it was posted. Monthly rates are computed by
taking the total traffic, dividing by the number of days in the traffic
measurement interval, and multiplying by 30. Decwrl runs 2.10.3 news, which
does not store the "Date-Received", "Relay-version" or "Posting-version"
header lines; the amount of space occupied at your site might be higher, and
the number of bytes transmitted between machines is probably higher. By
definition this number is correct, because it is an exact measurement, but it
may differ from the traffic at your site by as much as 15% due to timing
differences and news version differences. Timing differences will be random,
but will average out in the long run. News version differences will cause a
systematic error that is additively uniform across all newsgroups, and which
therefore does not significantly affect ratios.
If a message is crossposted to several groups simultaneously, it is charged
only to the first-named group in the list.
PARTICIPATION RATIO: MESSAGES per MONTH per 1000 READERS
This number is exactly what it says: the number of messages per month in
that newsgroup, divided by the number of 1000 readers. It is an indication
of how involved the readers of the group are in the traffic, of whether they
are mostly listeners or mostly talkers. Its accuracy is limited by the
accuracy of its two components. The messages per month figure is exact; the
reader count is only as accurate as the network size estimate, which is in
worst case accurate to 40%. Therefore you should treat this number as having
an error margin of plus or minus 40%. However, ratios between participation
ratios for different newsgroups are quite accurate, since the network-size
component divides out.
COST RATIO: DOLLARS PER MONTH PER READER
The most controversial field in the survey report is the "$US per month per
reader". It is the estimated number of dollars that are being spent on
behalf of each reader, worldwide, on telephone costs to transmit this
newsgroup. The cost ratio does not include the cost of disk storage to store
the news or of computer time to process it; both of those are assumed to be
free.
The cost ratio is computed as follows:
$US/month/reader = ($USPerMonthPerSite * numberOfSites) / numberOfReaders
$USPerMonthPersite = KBytesTrafficPerMonth * $USPerKByte
$USPerKByte = ($USperMinute / KBytesPerMinute) * (1 - CompressionFactor)
$USperMinute = 0.10 [ten cents per minute avg phone cost]
KBytesPerMinute = 60 * BytesPerSecond / 1000
BytesPerSecond = 100 [average transfer rate over 1200-baud line]
CompressionFactor = 0.4 [40% compression is typical for netnews]
Combining all these gives
$USPerMonthPersite =
KBytesTrafficPerMonth * (0.10 / 6) * (1 - 0.4)
= KBytesTrafficPerMonth / 100
Therefore:
$US/month/reader =
(KBytesTrafficPerMonth * numberOfSites) / (100 * numberOfReaders)
The accuracy of this number is in fact better than the accuracy of the
participation ratio, because the source of error--the network size
estimate--is present both in the numerator and the denominator, and therefore
cancels out. The primary source of bias in this number comes from the bias in
the "estimated number of readers, worldwide", which is described above. Treat
this value as being accurate to within about 25%.
SITE PARTICIPATION
I would like to receive data from every site on USENET. The arbitron programs
(posted to net.sources along with this report) work on news 2.9 and 2.10.[1-3]
and on many versions of notesfiles.
Brian Reid
DEC Western Research Laboratory, Palo Alto CA
reid@decwrl.DEC.COM
{ihnp4,allegra,decvax,ucbvax,sun,glacier}!decwrl!reid