On Sun, 2007-10-28 at 16:40 +0530, Sudev Barar wrote: [...] > Now that data and graphs all nice and tidy ... what conclusions are to > be drawn? Will this improve the list quality or quantity? This thread > has already done the latter ;-)
Conclusions? I am afraid that conclusions cost extra. For what it is worth, here are the mean no. of postings per day: 2005: 10.8 +/- 0.43 2006: 6.4 +/- 0.26 2007: 9.8 +/- 0.58 which says that 2005, and 2007 were comparable within errors, but 2006 was clearly lower. I have updated the last graph to show these averages as horizontal bars. One might argue that 2007 was distorted by that huge spike (probably the Microsoft at Linux-Asia thread), so here are the numbers throwing out events beyond 5-sigma from the mean: 2005: 10.7 +/- 0.41 2006: 6.4 +/- 0.26 2007: 9.5 +/- 0.49 i.e., not that much of a difference. Of course, the fallacy of counting posts to the list as a measure of quality should be evident from the fact that the Microsoft at Linux-Asia thread added lots of posts, but very little of value. Regards, Gora _______________________________________________ ilugd mailinglist -- ilugd@lists.linux-delhi.org http://frodo.hserus.net/mailman/listinfo/ilugd Next Event: http://freed.in - September 28-29, 2007 Archives at: http://news.gmane.org/gmane.user-groups.linux.delhi http://www.mail-archive.com/ilugd@lists.linux-delhi.org/
