Welch/Satterthwaite in practice [General Sta­tis­tics]

posted by ElMaestro  – Denmark, 2011-09-29 19:39 (5020 d 17:47 ago) – Posting: # 7396
Views: 16,291

Dear yicaoting & d_labes,

thanks for your kind advice.
Real life can be very cruel: I do not have SAS or Excel. I only have OpenOffice and R. Client-side the situation is typically Excel* and sometimes without admin. privileges to install anything else.

As far as I can see, OpenOffice Calc seems to have some limited options for programming in basic (not visual, though). It seems a slight waste of time to me if I make some code in OpenOffice Calc basic here which does not execute on the client's Excel machines. It's difficult to check in the absence of Excel here :-D
If I could find a portable (I mean portable between OOC and Excel) way to call a DLL, then I can prolly write the code in C or Delphi for that DLL and make it do approximately what I want. But that's an uphill struggle. Please do let me know if you have ideas along these lines.


*: Validation aspects deliberately left out ;-)

Pass or fail!
ElMaestro

Complete thread:

UA Flag
Activity
 Admin contact
23,424 posts in 4,927 threads, 1,686 registered users;
28 visitors (0 registered, 28 guests [including 10 identified bots]).
Forum time: 13:27 CEST (Europe/Vienna)

Complex, statistically improbable things are by their nature
more difficult to explain than
simple, statistically probable things.    Richard Dawkins

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5