Help calculating size.

[davidmiller]

Power calculation please.

[drcjar]

in addition to books dunno if http://jpktd.blogspot.co.uk/2013/03/statistical-power-in-statsmodels.html might be useful?

for first pass alpha = 5%, beta = 80%, two groups, assume data independant and normally distributed

[drcjar]

this may not be straight forward as also depends on statistical analysis planned and type of variable being measured... suggest delaying if problematic until I've organized worked examples for our example use cases

[davidmiller]

Couple of worked examples would be great.

On 10 May 2013 13:35, Carl Reynolds [email protected] wrote:

this may not be straight forward as also depends on statistical analysis
planned and type of variable being measured... suggest delaying if
problematic until I've organized worked examples for our example use cases

—
Reply to this email directly or view it on GitHubhttps://github.com//issues/66#issuecomment-17717766
.

Love regards etc

David Miller
http://www.deadpansincerity.com
07854 880 883

[davidmiller]

This now generates absolute nonsense numbers:

http://byta.randomizeme.org/trials/create-n1?step=3