Re: reliability analysis for small sample

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

Re: reliability analysis for small sample

Margaret MacDougall
Dear Johnny
 
For the benefit of others, I provide an excerpt below from Steve Simon's excellent reply to a similar message which you sent to a separate list:
    "Since
     the goal of most reliability studies is to produce some sort of
     correlation, the sample size is adequate if the confidence limits around
     that correlation are reasonably narrow.

    "I elaborate a bit more about this at

    www.childrensmercy.org/stats/weblog2007/ValidityReliabilitySampleSize.asp
    "

For completeness, you may also find it helpful, however, to consult the following reference on statistical power calculations:

http://itchy.icw.com/ncss/PASSUG3.pdf

Regards

Margaret



----- Original Message ----
From: John Amora <[hidden email]>
To: [hidden email]
Sent: Thursday, 6 March, 2008 3:22:39 AM
Subject: reliability analysis for small sample

Hello everyone,

I am conducting reliability analysis using cronbach's
alpha for an instrument with k items.  My problem is
that sample size (n) is very small, that is, n is less
than k.  I have no other ways to increase the size of
n.  Your comments are highly solicited.  Thank you.

Johnny


      ____________________________________________________________________________________
Looking for last minute shopping deals?
Find them fast with Yahoo! Search.  http://tools.search.yahoo.com/newsearch/category.php?category=shopping

=====================
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


      ___________________________________________________________
Rise to the challenge for Sport Relief with Yahoo! For Good  

http://uk.promotions.yahoo.com/forgood/

====================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