Spreadshit addiction [General Sta­tis­tics]

posted by ElMaestro  – Denmark, 2011-10-01 13:13 (5371 d 05:58 ago) – Posting: # 7401
Views: 19,645

Dear yicaoting and HS,

❝ Based on the result of R, It seems that BETAINV() in OO Calc has higher precision than that in Excel.


For my part I am very happy now that I have a solution, and it isn't of paramount importance to have 17 correct decimals. If a client of mine should ask for 17 decimals I would most likely tell him to go [to protect minors this sentence has been partly and pirately censored] himself :pirate:.

Decisions re. BE are made on basis of two decimals when we talk ordinary BE, so one can try and argue the same in my case.

I cannot find info on the actual implementations in neither Excel nor OO. A great paper comparing certain numeric precision aspects here.

Couldn't help laughing when I read page 19 ("Microsoft claims...."), by the way. Life is great. But then again, it is my impression that people at SAS aren't particularly informative either re. their implementations. That's why R so rules, imho.

Happy national day, yicaoting.

Pass or fail!
ElMaestro

Complete thread:

UA Flag
Activity
 Admin contact
23,654 posts in 4,992 threads, 1,570 registered users;
118 visitors (0 registered, 118 guests [including 13 identified bots]).
Forum time: 19:11 CEST (Europe/Vienna)

The idea is to try and give all the information to help others
to judge the value of your contribution;
not just the information that leads to judgment
in one particular direction or another.    Richard Feynman

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