Reliability tells you whether the items of a scale consistently measure the same thing. Cronbach’s alpha (α) is the most common measure of internal consistency for Likert-scale questionnaires.
What do the values mean?
| Cronbach’s α | Common interpretation |
|---|---|
| ≥ .90 | Excellent (very high values may mean repetitive items) |
| .80 – .89 | Good |
| .70 – .79 | Acceptable |
| .60 – .69 | Questionable (sometimes accepted for new or short scales) |
| < .60 | Poor — review the items |
How to run it in SPSS
- Go to Analyze → Scale → Reliability Analysis.
- Move all items of one construct into the Items box.
- Model: Alpha. Click Statistics and tick “Scale if item deleted”.
- Run once for each construct separately.
Reverse-coded items
If some items are negatively worded (e.g. “I rarely feel motivated”), recode them first (Transform → Recode into Different Variables: 1→5, 2→4, 3→3, 4→2, 5→1). Forgetting this is the most common reason for a very low or negative alpha.
“Alpha if item deleted”
This column shows what alpha would be without each item. If deleting one item raises alpha a lot, check that item’s wording. Do not delete items just to chase a higher number — keep the construct’s meaning intact and justify any removal.
How to report it
Internal consistency was assessed using Cronbach’s alpha. All scales showed acceptable to good reliability: job satisfaction (5 items, α = .84), work engagement (9 items, α = .88) and turnover intention (3 items, α = .76).
A small table with construct, number of items and alpha is the cleanest way to present this in Chapter 3 or Chapter 4.
🤝 Need help with Questionnaire & Data Collection?
Tell us your topic, level and deadline. We reply with a clear plan and price — nothing is charged before you agree.
📲 Found this useful? Share it with a classmate on WhatsApp.
