Free Republic
Browse · Search
General/Chat
Topics · Post Article

To: DoctorBulldog

A non peer-reviewed article, published by two people who have no institutional affiliation, one of whom gives their address as a P.O. Box, using nothing but statistical analysis to derive a correlation that supports what appears to be a predetermined conclusion?

No, I am not at all convinced.

Google tells me that Miller is a journalist, and Goldman is a computer scientist. In other words, they are not researchers and have no research training. I’m even less convinced.

Show me meaningful analysis. Show me where the infant mortality was compared, apples to apples—infants from the same backgrounds, vaccinated vs. non-vaccinated.

I happen to know, because I’ve read hundreds of statistical analyses (I hesitate to call them “studies” because they contain no experimental data), and I shared an office with a statistician for three years, that the vast majority of statistical analyses are junk. Get a good statistician to analyze the data, and almost any hypothesis can be “proven” with statistics. It all depends on which number sets are included, and how they’re combined.


86 posted on 11/25/2011 3:21:23 AM PST by exDemMom (Now that I've finally accepted that I'm living a bad hair life, I'm more at peace with the world.)
[ Post Reply | Private Reply | To 85 | View Replies ]


To: exDemMom

https://www.cia.gov/library/publications/the-world-factbook/rankorder/2091rank.html


88 posted on 11/25/2011 8:53:12 AM PST by DoctorBulldog (I'm a Cainiac! Get over it. -- If the dress aint got no stain, you MUST acquit Cain! 999!!!)
[ Post Reply | Private Reply | To 86 | View Replies ]

Free Republic
Browse · Search
General/Chat
Topics · Post Article


FreeRepublic, LLC, PO BOX 9771, FRESNO, CA 93794
FreeRepublic.com is powered by software copyright 2000-2008 John Robinson