While estimating convergent validity, one latent factor gets AVE value less than 0.5. however, factor loadings gets values greater than 0.6 and model fitted well with fit indices. In this case, shall I accept the latent factor for model fitting or do I need to remove the latent factor from the model as it has AVE value less than 0.5?
HI Yogarajah
I tend to agree with Marcie. AVE < .5 does not convey sufficient variance for the variables (items/questions) to converge into a single construct, which means items are less-than-effective measure of the latent construct. There's more error variance than explained variance.
The logic is that:
- when an item loading is .71, then it's communality is .50 because communality is the loading square.
- Thus, AVE < .50 means, on average item loading is less than .70 (Hair et al., 2010, p.777)
- This also explains while your loadings are good (.60), AVE is less than perfect (< .50.).
Remedies:
Shall you need to see other cut-off points for both measurement and structural models assessment, the link below provides you with a pre-edit document that summarises those values.
Best wishes
Saiyidi
Ref:
Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2010). Multivariate data analysis (7 ed.). Upper Saddle River, NJ, USA: Prentice-Hall, Inc.
Chapter Partial least square in a nutshell | Saiyidi MAT RONI 2 0 1 4
Is there any case to accept the latent factor even AVE is less than 0.5.?
HI Yogarajah
I tend to agree with Marcie. AVE < .5 does not convey sufficient variance for the variables (items/questions) to converge into a single construct, which means items are less-than-effective measure of the latent construct. There's more error variance than explained variance.
The logic is that:
- when an item loading is .71, then it's communality is .50 because communality is the loading square.
- Thus, AVE < .50 means, on average item loading is less than .70 (Hair et al., 2010, p.777)
- This also explains while your loadings are good (.60), AVE is less than perfect (< .50.).
Remedies:
Shall you need to see other cut-off points for both measurement and structural models assessment, the link below provides you with a pre-edit document that summarises those values.
Best wishes
Saiyidi
Ref:
Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2010). Multivariate data analysis (7 ed.). Upper Saddle River, NJ, USA: Prentice-Hall, Inc.
Chapter Partial least square in a nutshell | Saiyidi MAT RONI 2 0 1 4
I am facing the same problem, AVE is below .05, can i round off because the CFA and SEM seems to be fine?
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Applied Statistics