PLS-SEM · Step 1

Assessing a measurement model in SmartPLS: the 6 criteria and what to do when they fail

AVE under 0.5, HTMT over 0.9, outer loadings stuck at 0.6: which item do you drop without breaking the model? All the thresholds from Hair et al. (2022), with how to fix each one.

⏱ ~6 min readSource: Hair et al. (2022)Updated:

You run the PLS algorithm and every table has a red cell: one construct’s AVE is 0.46, HTMT between two constructs hits 0.92, a few outer loadings sit around 0.6. Which item do you drop to make the scale pass without breaking the model? This guide covers assessing a measurement model in SmartPLS using the 6 criteria from Hair et al. (2022), with examples, thresholds and a process for when a criterion fails.

Customer Satisfaction construct with four indicators, CS4 flagged for review at an outer loading of 0.591
CS4 is in the review zone, but the scale’s AVE and CR still pass.
📚 Reference

The standards come mainly from Hair, Hult, Ringle & Sarstedt (2022), A Primer on Partial Least Squares Structural Equation Modeling (PLS-SEM), 3rd edition. This article applies to reflective measurement models.

1Outer loadings: what value is acceptable?

An outer loading shows how strongly each indicator correlates with the construct it measures. The larger the value, the better the indicator reflects the concept.

Example

The construct Customer Satisfaction is measured by four indicators:

  • CS1: I am satisfied with the product quality.
  • CS2: The product meets my expectations.
  • CS3: I will keep using the product.
  • CS4: I will recommend the product to others.
IndicatorOuter loading
CS10.892
CS20.876
CS30.842
CS40.591

CS1–CS3 reflect the concept very well. CS4 (0.591) is in the review zone: whether to keep it depends on its effect on CR and AVE, and on what it contributes to the concept (see section 7).

  • ≥ 0.708: Acceptable
  • 0.40 to 0.708: Review (keep or remove)
  • < 0.40: Remove

2Cronbach’s alpha: internal consistency

The traditional measure of consistency among the indicators of a concept. In PLS-SEM it is treated as a lower bound of reliability, because it assumes every indicator carries equal weight.

Example

A Brand Trust scale with 5 items: alpha = 0.865, so the items are highly consistent. An alpha of just 0.52 would mean some items need another look.

  • 0.70 to 0.95: Acceptable (0.80–0.90 is ideal)
  • 0.60 to 0.70: Acceptable in exploratory research
  • < 0.60: Unacceptable · > 0.95: Items repeat each other
📏
Read more
Low Cronbach’s alpha: 6 causes and fixes
Reversed items, wrong coding, off-topic questions and more.
→

3rho_A: a more exact reliability measure

From Dijkstra & Henseler (2015) and recommended by Hair et al. (2022), rho_A uses the actual loadings, so it sits between Cronbach’s alpha (the lower bound) and CR (the upper bound), giving a closer picture of true reliability.

Example

A Perceived Value scale: alpha = 0.812, rho_A = 0.847, CR = 0.886.

  • 0.70 to 0.95: Acceptable
  • < 0.70: Below standard · > 0.95: Possibly redundant

4Composite reliability (CR)

CR accounts for each indicator’s actual contribution, showing how well the indicators together measure one concept.

Example

Service Quality: SQ1 = 0.88, SQ2 = 0.84, SQ3 = 0.86, SQ4 = 0.91 gives CR = 0.93. The indicators work very well together.

  • 0.70 to 0.95: Acceptable
  • < 0.70: Below standard
  • > 0.95: The items are too alike; information is redundant

5AVE: what value shows convergent validity?

From Fornell & Larcker (1981), average variance extracted (AVE) is the share of the indicators’ variance explained by the construct. It tells you whether the indicators really converge on one concept.

Example

Purchase Intention: AVE = 0.684 explains 68.4% of the variance, above 50%, so convergent validity holds. At AVE = 0.39, more than half the variance is measurement error.

  • AVE ≥ 0.50: Convergent validity holds
  • AVE < 0.50: Not established

6HTMT: what value shows discriminant validity?

From Henseler, Ringle & Sarstedt (2015), and treated by Hair et al. (2022) as the main criterion for discriminant validity, HTMT shows whether two concepts are really different or are measuring the same thing.

Example
Pair of constructsHTMT
Service Quality ↔ Customer Satisfaction0.73

HTMT = 0.73 (below 0.85) means clearly distinct. At 0.96, the two constructs may well be measuring the same thing.

  • < 0.85: Good (conceptually different constructs)
  • < 0.90: Acceptable for conceptually similar constructs
  • ≥ 0.90: Signs of a discriminant validity problem
🔎 A stronger check

Also look at the bootstrap confidence interval for HTMT: if its upper bound is below the threshold (0.85 or 0.90), discriminant validity is on firmer ground. Fornell–Larcker can be reported alongside but should not be your only evidence.

7When a criterion fails: what to do

🔁 Handling outer loadings, AVE and CR
  1. Remove any indicator with an outer loading below 0.40.
  2. For indicators between 0.40 and 0.708, try removing the single lowest and re-run.
  3. Keep the removal only if it lifts AVE or CR past the threshold and does not damage what the concept means.
  4. Repeat one at a time, and keep at least 3 indicators per construct where you can.

HTMT ≥ 0.90

  • Reread both constructs’ items: does any straddle the two?
  • Check cross-loadings: items loading high on the other construct are candidates for removal
  • If theory allows, consider merging the constructs

Alpha or CR above 0.95

  • The items nearly repeat each other
  • Consider removing duplicated content
  • Check for straight-lined responses
⚠️ Do not force the numbers

Each removal needs a statistical and a content reason, and a record. Never edit data to make a criterion pass. If a scale stays weak, report it honestly under limitations.

Six criteria with thresholds: outer loading, Cronbach’s alpha, rho_A, composite reliability, AVE and HTMT
The six criteria to check and their thresholds.

8Reporting the measurement model in your thesis

This usually takes 3 tables: (1) outer loadings; (2) reliability and convergent validity; (3) HTMT.

ConstructAlpharho_ACRAVE
Service Quality0.8960.8990.9280.762
Perceived Value0.8120.8470.8860.722
Purchase Intention0.8460.8510.8960.684

See the tables before you run the real thing

Draw your model on The Light Data’s model canvas, pick SmartPLS, and read outer loadings, reliability, AVE and HTMT tables on simulated data. It is a handy way to practice and outline your results chapter. Simulated data never replaces real data.

🧭
Free
Open the model canvas
Draw a model and see sample SmartPLS tables.
→
🎯 Checklist for a sound measurement model
  • Outer loading ≥ 0.708 · alpha, rho_A and CR within 0.70–0.95.
  • AVE ≥ 0.50 (convergent) · HTMT below 0.85 or 0.90 (discriminant).
  • Remove indicators step by step, with reasons, and record the process.
  • All passed → move on to the structural model.
②
Next step
Assessing the structural model
Test hypotheses with VIF, R², f², Q², β, T and P.
→

Frequently asked questions

Must I delete an item with an outer loading below 0.708?

No. Items between 0.40 and 0.708 should go only if removing them lifts AVE or composite reliability past the threshold, without damaging what the construct means (Hair et al., 2022). Items below 0.40 should go.

What do I do if AVE is below 0.5?

Look at the construct’s lowest outer loadings and consider removing those items one at a time, re-running and checking AVE and composite reliability after each removal.

How do I fix an HTMT above 0.9?

Check whether the two constructs overlap in content, consider removing items that correlate strongly with the other construct, or merge the constructs if theory allows. Also check the bootstrap confidence interval for HTMT.

Do I still need to report Fornell–Larcker?

Hair et al. (2022) recommend HTMT as the main criterion. You can report Fornell–Larcker as well since many committees know it, but it should not be your only evidence.

Are formative constructs assessed the same way?

No. Formative constructs are assessed with convergent validity (redundancy analysis), collinearity among indicators (VIF), and the significance and relevance of the outer weights.