[R] Finding Confidence Intervals

[David Winsemius]

On Jul 11, 2011, at 10:51 AM, Abraham Mathew wrote:

> This is a very basic question, so please bear with me.
>

> (8.1, 11.8) # headline 1
> (9.2, 12.7) # headline 2
> # these confidence intervals for the two headlines overlap.
> # therefore, the variation (headline 2) isn't more effective
> # than the control headline

Not sound reasoning and very imprecise wording. You should study basic  
statistics more with particular attention to the conditions under  
which a two-sample t-test will return a "significant" result. R-help  
is not a statistics tutoring facility, so you should pursue this  
elsewhere. There was a Math Q&A site out of Drexel University at one  
time. <obvious google search> Yes, there it is:

  http://mathforum.org/

-- 
David Winsemius, MD
West Hartford, CT