Reply To: Questions regarding DPF.

[Brian H]

Breakable wrote:

Here’s some info about how unclean the AGW data is: http://69.84.25.250/blogger/post/ClimateGate-Data-Series-Part-I-A-break-down-of-large-data-file-for-manipulating-global-temperature-trends-from-2006-2009.aspx

I am not a statistics expert, but this article is flawed. Type I error does not make hypothesis invalid:

The hypothesis can be inappropriately rejected, this is called type I error, or one can inappropriately fail to reject the hypothesis, this is called type II error

?? That’s not what it says. Strict protocols use the null hypothesis as a basis.
The basic hypothesis is a contrary one: “This effect is insignificant or non-existent.” You quickly get into double and triple-negatives, when discussing type Is and alphas, etc.

I took a combined degree in Psych and Statistics once upon a time, and had “null hypothesis” pounded into my skull till it bled!

Using it, you never get to formally conclude anything positive about a theory, you just get tired of trying to disprove it and move on to a more vulnerable target somewhere else. 😆