Academic and research
How to calculate Cronbach's alpha
Cronbach's alpha shows whether the items of a questionnaire scale measure the same thing. You will arrange the scores, see how alpha is calculated, read it against common thresholds, find weak items and report the result.
Alpha assumes the items measure one idea and are scored in the same direction. A high alpha does not prove the scale measures what you intend; that is validity.
Open Cronbach's alpha calculatorContents
Open the Cronbach's alpha calculator on cv.cm
Copy the item columns from Excel, Google Sheets or SPSS and paste them: one row per respondent, one column per item, with or without a header row.
Open Cronbach's alpha calculatorRecode reverse-worded items first
If agreeing with an item means the opposite of the others, flip its scores before pasting. On a 1–5 scale the new score is 6 minus the old one.
See how alpha is calculated
α = k ÷ (k − 1) × (1 − Σ item variances ÷ variance of the total score), where k is the number of items. When items move together, the total varies much more than the items do separately, and alpha rises.
Item scores in rows and columns: alpha compares the item variances with the variance of the total. Read the result
The example scale (5 items, 10 respondents) has α = 0.935. A common rule of thumb: 0.9 and above excellent, 0.8 good, 0.7 acceptable, 0.6 questionable, 0.5 poor. Many fields want at least 0.7.
Common thresholds for Cronbach's alpha, with the example scale at 0.935. Check the items
Look at the corrected item-total correlation (below about 0.3 is weak) and alpha if item deleted. An item whose removal raises alpha (marked ↑) may not fit the scale, or may still need recoding.
Report it
Write the number of items and respondents with it: "The scale showed excellent internal consistency, Cronbach's α = .93 (5 items, n = 10)." APA uses two decimals, and 0.93499 rounds down to .93. Report alpha for each subscale separately.
FAQ
What is a good Cronbach's alpha?
0.7 or higher is usually acceptable, 0.8 good and 0.9 excellent. Values above about 0.95 can mean the items repeat each other.
Can Cronbach's alpha be negative?
Yes, usually because some items are reverse-worded and not recoded, or because the items do not measure the same thing.
How many items does Cronbach's alpha need?
At least two, but alpha is more stable with three or more. It also rises with the number of items, so a long scale can look reliable even when its items correlate weakly.
What is standardized alpha?
Alpha computed from the average correlation between items instead of their variances. It is useful when items use different scales.
How do I calculate Cronbach's alpha in SPSS?
Analyze → Scale → Reliability Analysis, move the items in, choose Alpha, and tick "Scale if item deleted" under Statistics.