On Saturday 04 October 2014 00:40:44 meik michalke wrote:
> today i've started working on a plugin for power analysis/sample size
> calculation. most of what you can get from the pwr package is already
> implemented, open issues are handling of sample size estimation for designs
> with two samples, and maybe a nicer printout...
> here's the generator script:
>  http://reaktanz.de/stuff/R/rkwarddev_power_plugin_script.R

looks really nice, already. Some first thoughts:

- Don't forget to require(pwr)
- I was rather confused by the distinction between "greater" and "less" 
alternatives for one-sided tests. This should not really make any difference, 
or should it? Then I tried, and didn't believe my eyes, until I figured out 
that for "less" you want to specify a _negative_ effect size (and in fact, you 
can't enter that in the GUI). I suggest, either going with "greater", only, or 
showing a warning, when the specified effect size contradicts the hypothesis.
- I wouldn't write the results to the workspace _by default_. I guess the more 
common case is that the printout is all you want.
- This is really something where a "generalized preview" (similar to the plot 
previews, but showing e.g. a piece of HTML printout) would be nice. But of 
course, we don't have that, yet...


Attachment: signature.asc
Description: This is a digitally signed message part.

Meet PCI DSS 3.0 Compliance Requirements with EventLog Analyzer
Achieve PCI DSS 3.0 Compliant Status with Out-of-the-box PCI DSS Reports
Are you Audit-Ready for PCI DSS 3.0 Compliance? Download White paper
Comply to PCI DSS 3.0 Requirement 10 and 11.5 with EventLog Analyzer
RKWard-devel mailing list

Reply via email to