----- Original Message ----- From: "Erik Reuter" <[EMAIL PROTECTED]> To: "Brin-L" <[EMAIL PROTECTED]> Sent: Wednesday, December 26, 2001 6:14 PM Subject: Re: Tragedy in Israel
> On Wed, Dec 26, 2001 at 03:44:23PM -0600, Dan Minette wrote: > > > > From: "Erik Reuter" <[EMAIL PROTECTED]> > > > > > On Wed, Dec 26, 2001 at 11:43:23AM -0600, Dan Minette wrote: > > > > But, its not just that. A poll was taken among Palestinians, and 65% > > > > supported the terrorist attacks. > > > > > > I hadn't heard about this. It sounds like it would be a difficult poll > > > to handle well. Do you have a reference? > > > > > It was an AP poll that was referenced both on the net and on CNN. I look for > > about 10 minutes for an internet reference today and couldn't find it. It > > was taken between 1 and 2 weeks ago. > > > > Looking for it, I found another source with similar numbers. It is: > > > > http://www.freep.com/news/nw/isra25_20010825.htm > > > > This quotes a poll that shows 70% supporting the suicide bombings. The two > > numbers are within typical statistical errors. > > The problem with polls is, depending on how you conduct the poll (who > you question, when, where, and how), and the exact phrasing of the > question, you can get about any answer you want. > > The article you referenced did not talk about a poll for "suicide bombings" > nor "terrorist attacks". What the article said was, > > "And 70 percent of Palestinian support suicide attacks, up from 20 > percent in 1996." > > But seeing how you changed the meaning in your mention of it, perhaps > the article writer did too. (Not to mention possible language > translation difficulties). I think such evidence is completely > worthless. First of all, the suicide bombings are factually the same things as the terrorist attacks. Why is the evidence conmpletely worthless? If the same question is asked both times, why shouldn't the shift be worthwhile. I know, as a engineer/scientist working with imperfect data is an absolute requirement. If one requires that data are perfect before they are considered, then one will eschew all data and make decisions based on things other than data. You work in a technical area, do you really throw away data that is less than perfect in your work? >The methodology needs to be explained in far more detail for > me to place any credibility in such a poll. Unfortunately, the authors > of newspaper articles almost never give a reference for the poll so that > one can delve into the details. > AP does have a reputation for polling. They have a track record. Even if there are biases in the polls, one should expect +/-10%. Plus, the second poll was from a totally different organization, which is Palestinian in origin. So, we have a Western news agency poll and a Palestinian poll agree, and its still worthless? Dan M. > > -- > "Erik Reuter" <[EMAIL PROTECTED]> http://www.erikreuter.com/
