[FieldTrip] One or two sided testing?

Eric Maris e.maris at donders.ru.nl
Fri Feb 11 15:01:01 CET 2011


Dear Emanuel,

 

 

 

I notice that there are many different views among scientists about the use
of one or two sided tests.
Most people say that you always have to test 2-sided. But is there a
rationale for this? When is it appropriate and allowed to test one-sided? 

Perhaps you can shed light on this topic, by giving your point of view or
perhaps you can recommend literature that provides insight on this debate?

If you have prior information that an effect will occur only on one side, or
if you are only interested in an effect at one side, then you should test
one-sided. Otherwise, you should test two-sided.

 

 

Best,

 

Eric

 

 

 

 

 

 

 

Thank you,

Best Emanuel




Het UMC St Radboud staat geregistreerd bij de Kamer van Koophandel in het
handelsregister onder nummer 41055629.
The Radboud University Nijmegen Medical Centre is listed in the Commercial
Register of the Chamber of Commerce under file number 41055629.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.science.ru.nl/pipermail/fieldtrip/attachments/20110211/9e73570c/attachment-0001.html>


More information about the fieldtrip mailing list