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

To: ModelBreaker; cogitator

Run the numbers anyway. With an original p of 0.67 for the one data set, there’s probably a good chance that p will still exceed 0.05.


20 posted on 05/04/2008 2:30:42 PM PDT by Tolerance Sucks Rocks (To the liberal, there's no sacrifice too big for somebody else to make. --FReeper popdonnelly)
[ Post Reply | Private Reply | To 18 | View Replies ]


To: Tolerance Sucks Rocks
Run the numbers anyway. With an original p of 0.67 for the one data set, there’s probably a good chance that p will still exceed 0.05

I did. In my previous post, I told you that that four of the 125 data slices (one of them being the one you picked) show a statistically significant upward trend at the 95% confidence level (I didn't look for negative trends). That means P<=0.05 for those four only.

By random chance, we would expect that 6 would show a statistically significant trend by random chance. Of those 3, on average would be negative and three would be positive. So the fact that only four show a significant upward trend means that the upward trends found were most likely, random fluctuations due to picking the most favorable possible look at the data.

27 posted on 05/04/2008 11:36:44 PM PDT by ModelBreaker
[ Post Reply | Private Reply | To 20 | 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