Pete, With the greatest respect that is absolute rubbish. Any correctly taken statistical sample if done with the correct techniques and "confidence values" will yield a correct result within a set of "confidence limits" which are detarmined by well founded mathematical formulae.
Take for instance exit polls for elections. The representative sample may well be extremely small but the accuracy is amazing - in excess of 98% here in the UK. Don’t mistake the "pre election" polls as being representative of Statistical surveys as what the presenters NEVER do is provide the confidence intervals which invariably go with these polls and can be as small as 20% i.e 20% confidence that the result is correct. Having majored in Stats and computing I always find that implimentation of Statistics gets a very bad press e.g Lies damned lies ...and statistics, purely because the results are presented in a biased manner with scant regard to the "confidence" in the result which has always been calculated (or should have been) by the researcher. Sloppy research will ALWAYS yield sloppy results as in systems design and programming etc. My ex wife runs a Market Research bureau which I wrote all the software for back in the mid 80's and it is still running in the same format - apart from being windows based as opposed to DOS based. However the basic sampling techniques haven't changed one bit, but the speed of analysis has. If you find that your theories cannot be taken seriously then maybe it is your sampling techniques and research gatherers that should be better educated. Dave Crozier The secret to staying young is to live honestly, eat slowly, and to lie about your age -----Original Message----- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Pete Theisen Sent: 16 October 2006 10:50 To: ProFox Email List Subject: Re: [JOB] VFP to .NET update On Monday 16 October 2006 05:06, Virgil Bierschwale wrote: Hi Virgil! No, I understand the point. What you don't understand is that now that there are computers, they *have* to be used. You can't present research based on twenty cases or even twenty thousand cases, it won't be accepted. You have to have twenty million cases to be taken seriously, perhaps more coming from the alternative side as we are. If we can't do it on the computer, we can't do it. > Pete, you're missing the point entirely.. > > Everything is done on paper first. > Speed is brought into the equation via a computer as is searchability, > analysis, etc... > But you could do all that by hand, it just takes a lot longer... -- Regards, Pete http://www.pete-theisen.com/ [excessive quoting removed by server] _______________________________________________ Post Messages to: [email protected] Subscription Maintenance: http://leafe.com/mailman/listinfo/profox OT-free version of this list: http://leafe.com/mailman/listinfo/profoxtech ** All postings, unless explicitly stated otherwise, are the opinions of the author, and do not constitute legal or medical advice. This statement is added to the messages for those lawyers who are too stupid to see the obvious.
