[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums

Bob Koca, ask not for whom the bell tolls

Posted By: Timothy Chow
Date: Friday, 29 June 2012, at 12:36 a.m.

In Response To: Bob Koca, ask not for whom the bell tolls (Bill Phipps)

It's too bad that you don't see the dangers here.

For some years I worked at a government job where we were essentially forced to produce quantitative analyses in situations like this, where there was some data, but not enough to draw sound conclusions. Inevitably, the caveats were stripped from the reports, and the numbers used to create the impression that the conclusions were more "scientific" than they actually were. It doesn't take too long working at such a job to see the trouble that this can lead to.

In the end, all you'll really be able to conclude from quantitative analysis of this PR data is the qualitative conclusion that you already know, that it's very unlikely that Stick's numbers would be duplicated by someone with Mochy's numbers on a good day. Because you're doing a retrospective analysis, nothing more scientifically rigorous can be said than that. The only purpose I can see in trying to juggle some numbers is to make it seem like the conclusion is more solid than it really is. If you have no respect for scientific honesty, I can only shrug my shoulders.

Messages In This Thread

 

Post Response
Your Name:
Your E-Mail Address:
Subject:
Message:

If necessary, enter your password below:

Password:
 

 

[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums is maintained by Stick with WebBBS 5.12.