Composite Reliability
Statistics & analysis
A reliability measure for latent constructs (also called rho_c) that weights items by their loadings; 0.70 or higher is the usual threshold in SEM.
Composite reliability, sometimes written rho_c or Joreskog's rho, estimates the internal consistency of a latent construct using the actual standardised loadings from the measurement model rather than assuming every item contributes equally.
That is its advantage over Cronbach's alpha. Alpha assumes tau-equivalence — equal loadings across items — and tends to underestimate reliability when that assumption fails, while also inflating simply because a scale is long. Composite reliability relaxes the equal-loading assumption, which is why it is preferred in CFA and PLS-SEM.
The conventional threshold is 0.70 for established scales, with 0.60 sometimes tolerated in exploratory research. Values above roughly 0.95 suggest redundant items inflating the estimate artificially. Report composite reliability alongside AVE; many journals now expect alpha, CR and AVE together in the same table.
Where it's used
- Reporting internal consistency in PLS-SEM and CB-SEM measurement models
Software used
Related concepts
Guides on this topic
- Convergent and discriminant validity thresholds (AVE, HTMT, Fornell-Larcker)
- Average variance extracted (AVE) explained
- HTMT ratio for discriminant validity
- SPSS vs SmartPLS: which should you use?
- Model fit indices in AMOS explained
- Interpreting SmartPLS bootstrapping results
- What is SmartPLS? PLS-SEM explained
- What is jamovi? The free SPSS alternative
Guides that use this concept
All guidesNot sure where to start?
Book a free 15-minute consult. We'll map your next three steps — no obligation.