Linked by Howard Fosdick on Tue 17th Jul 2012 04:53 UTC
Thread beginning with comment 527152
To view parent comment, click here.
To read all comments associated with this story, please click here.
To view parent comment, click here.
To read all comments associated with this story, please click here.
Always those very few who masquerade themselves have something against stats - you know, there's any easy way to correct the error... (but don't expect any significant changes)
Anyway, not sure why the title of your response to MikeCarter is "Exactly" - while his point was clearly that, for estimating what general population uses on their PCs, some data sources (like web hits on ~Wikipedia) are almost certainly much more statistically valid than others (Distrowatch, your VM servers - BTW those: http://w3techs.com/blog/entry/debian_is_now_the_most_popular_linux_... )




Member since:
2005-07-22
When 'fanbois' rant on about how popular *buntu is and use frankly bogis stats to justify their stance, it does matter.
MY web browsers tell the world that I'm running Windows XP. I'm not so how valid are the stats based upon web browsing now?
How many people using Firfox block all these hit counter sites and adverts with tools like NoScript and Adblock? What price valid web browising stats then?
The simplistic picture that these sites (and even dictro watch) present isn't statistically valid. There are enough holes in them to make Emmenthal look solid.