Statistical evidence -- RSQUBF discussion forum

[ Show ]

Support VoyForums

[ Shrink ]

VoyForums Announcement: Programming and providing support for this service has been a labor of love since 1997. We are one of the few services online who values our users' privacy, and have never sold your information. We have even fought hard to defend your privacy in legal cases; however, we've done it with almost no financial support -- paying out of pocket to continue providing the service. Due to the issues imposed on us by advertisers, we also stopped hosting most ads on the forums many years ago. We hope you appreciate our efforts.

Show your support by donating any amount. (Note: We are still technically a for-profit company, so your contribution is not tax-deductible.) PayPal Acct: Feedback:

Donate to VoyForums (PayPal):

[ Login ] [ Contact Forum Admin ] [ Main index ] [ Post a new message ] [ Search | Check update time | Archives: [1], 2, 3, 4, 5, 6, 7, 8, 9, 10 ]

[ Next Thread | Previous Thread | Next Message | Previous Message ]

Date Posted: 12:17:25 03/28/05 Mon
Author: Mike K.
Subject: Statistical evidence
In reply to: Joe 's message, "Re: Cult Apologist Lobby" on 22:15:23 03/25/05 Fri

"If you have out of a hundred or two hundred thousand Jehovah�s Witnesses, 10 or 15 who say something like that

Fact is, any statistician would treat this very, VERY differently.
One in a million is an odd occurrence.
Two may be variance, but 10 already... hey, that's not ten in a million, but one in hundred thousand.
And since we're talking like 1000 in 500000, we're already talking in the area of percentage.
And it's not like their testimony is "white noise", but forms a consistent pattern.

During my investigation of medical data, it was for those "one in ten thousand" things I was to look for, NOT for the 9999 that were not special.

Medicine actually is a good example:
if you have a body, and 9999 times, your heart frequency and blood pressure show no anomaly, it may indicate that you're healthy. BUT: no doctor would be such a fool to ignore the one instance when heart frequency and blood pressure exceeded normal bounds.
To diagnose sickness, this one "abnormal" instance is MUCH more important than all other instances.

In the investigations I made, I even went to "filter out" all those 99.99% of normal occasions, and my job was to locate patterns in the remaining 0.001% - yes, you have VERY little raw data, but it's your duty to find the patterns there.

And it's not like you can't find patterns in the report of dropouts.

So, be the good doctor and filter the "normal cases" out.

In Christ,
Mike K.

[ Next Thread | Previous Thread | Next Message | Previous Message ]