Cronbach’s Alpha Calculator
Estimate the internal-consistency reliability of a scale from the number of items, the sum of item variances and the variance of total scores.
How it works
α = k ÷ (k−1) × (1 − Σsᵢ² ÷ s²ₜ)
If items measure the same construct, their scores co-vary and the total-score variance is much larger than the sum of the individual item variances. Alpha turns that ratio into a 0–1 reliability index. It rises with more items and with stronger inter-item correlation.
Worked example
k = 10, Σsᵢ² = 12.5, s²ₜ = 60 → α = 1.111 × (1 − 0.2083) = 0.880.
Frequently asked questions
What is a good alpha?
0.70 is the usual floor for research scales; 0.80+ for applied decisions. Above 0.95 may mean redundant items.
Can alpha be negative?
Yes, when items are negatively correlated — usually reverse-scored items that were not recoded.
Related calculators
For education — check assumptions (sample size, distribution) before using statistics in real decisions.