Page 1 of 1

AVE

Posted: Sun May 08, 2011 6:25 am
by mazi
Hi every one:
I have one question
what does AVE state exactly and why does it use for assessing the indicator reliability and converegent validity

Posted: Sun May 08, 2011 12:35 pm
by Diogenes
See

Claes Fornell; David F Larcker. (1981). Evaluating structural equation models with unobservable variables and measurement error. JMR, Journal of Marketing Research, 18, p. (pre-1986); Feb 1981; 18(1), 39-50.

“If AVE is less than .50, the variance due to measurement error is larger than the variance captured by the construct…” [p.46].

Best regards,

Bido

Posted: Sun May 08, 2011 5:59 pm
by mazi
Thank you so much. your answer helped me alot

Posted: Mon May 09, 2011 12:47 pm
by husseins
what should I do if one of my construct has AVE less than 0.50? is there any treatment?

regard

Posted: Mon May 09, 2011 1:29 pm
by Diogenes
Hi,

The AVE is “average”, for this reason, if we remove the indicators with lower outer loading, the AVE will increase, but we should do this carefully because the content validity could be jeopardized.

Best regards,

Bido