If you are talking about a point (sharp) null hypothesis, true (unless, of course, you have the entire population of scores on hand), -- but testing point null hypotheses is pretty silly anyway. If we must test null hypotheses, they should be range (loose) null hypothesis - that is, the null is that the effect is in the range that we consider so small as to be null. In this case, one can accept the null, given that power is sufficiently high. If Type I errors are equally serious to Type II errors, I'd argue that means 95% power given the usual .05 criterion.
Bioequivalence testing is well adapted to accepting a range null
hypothesis.
Cheers,
[cid:image001.jpg@01CC3010.280A85D0]<http://core.ecu.edu/psyc/wuenschk/klw.htm>
From: michael sylvester [mailto:msylves...@copper.net]
Sent: Thursday, June 16, 2011 2:42 PM
To: Teaching in the Psychological Sciences (TIPS)
Subject: [tips] Null hypothesis
True or False One never accepts the Null hypothesis but only fails to reject
the Null hypothesis.
Michael
---
You are currently subscribed to tips as:
wuens...@ecu.edu<mailto:wuens...@ecu.edu>.
To unsubscribe click here:
http://fsulist.frostburg.edu/u?id=13060.c78b93d4d09ef6235e9d494b3534420e&n=T&l=tips&o=11017
(It may be necessary to cut and paste the above URL if the line is broken)
or send a blank email to
leave-11017-13060.c78b93d4d09ef6235e9d494b35344...@fsulist.frostburg.edu<mailto:leave-11017-13060.c78b93d4d09ef6235e9d494b35344...@fsulist.frostburg.edu>
---
You are currently subscribed to tips as: arch...@jab.org.
To unsubscribe click here:
http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5&n=T&l=tips&o=11093
or send a blank email to
leave-11093-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu<<inline: image001.jpg>>
