Date: Sat, 02 Mar 2002 12:25:03 -0800 From: Terry Lambert <tlambert2@mindspring.com> To: "Jeremy C. Reed" <reed@reedmedia.net> Cc: freebsd-chat@FreeBSD.ORG Subject: Re: Open Source Software Study Message-ID: <3C81351F.C63F3687@mindspring.com> References: <Pine.LNX.4.43.0203020923410.2796-100000@pilchuck.reedmedia.net>
next in thread | previous in thread | raw e-mail | index | archive | help
"Jeremy C. Reed" wrote: > On Sat, 2 Mar 2002, Terry Lambert wrote: > > > > > http://floss1.infonomics.nl/announce/ > > > > > > > > It is hopelessly biased towards Linux... > > > > > > Why "hopelessly biased"? > > > > I think it's because you can read the results in the questions > > without having to wait for the survey to be completed. > > I never noticed that. I don't recall seeing the results until I chose to > after I completed the five pages. You misunderstand. I can read the results by reading the questions, without having to read the results themselves. In other words, the survey will get the results it was designed to get, rather than results that tell them anything. Soft scientists seem to be unfamiliar with the term "double blind". Most UI "testing" seems to be designed to get the answers the "researchers" want as well. It's real easy to design a survey to prove conclusions which you already hold to be true. This is not a scientific survey; despite the claim that partial results are not statistically significant, I'd have to say that full results are also not going to be statistically significant. If you want me to take apart the bias question by question, I can do so. -- Terry To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-chat" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3C81351F.C63F3687>