Re: Cronbach alpha sensitivity to small samples
Posted by
Art Kendall on
Jan 27, 2012; 12:03pm
URL: http://spssx-discussion.165.s1.nabble.com/Cronbach-alpha-sensitivity-to-small-samples-tp5434804p5435201.html
Is this a pre-existing scale? I would certainly use it to double check keying of an
existing scale. It should help spot items with the wrong sign. It
might point out items that should be on other scales.
It could also be useful to demo what kinds of output RELIABILITY
has.
Art Kendall
Social Research Consultants
On 1/27/2012 3:39 AM, Mark Webb wrote:
I'm aware that Alpha is sensitive to the number
of statements used.
Can members please comment on the pros/cons of using this
statistic if sample sizes are low {e.g. N=16} - the number of
statements are > 12.
Regards
--
Mark Webb
Line +27 (21) 786 4379
Cell +27 (72) 199 1000 [Poor reception]
Fax +27 (86) 260 1946
Skype tomarkwebb
Email [hidden email]
Client ftp http://targetlinkresearch.co.za/cftp/
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Art Kendall
Social Research Consultants