cv.cm

Cronbach's alpha calculator

Paste item scores to check a scale's internal consistency. The data stay in this tab.

Reliability

Cronbach's alpha (α)
0.935
Standardized alpha
0.9346
Items (k)
5
Respondents (n)
10
Mean inter-item correlation
0.7408
Sum of item variances
5.2333
Variance of total score
20.7667

Internal consistency: excellent (α ≥ 0.9).

APA style: Cronbach's α = .93 (5 items, n = 10).

Item statistics

ItemMeanVarianceCorrected item-total rα if item deleted
Q13.51.1670.9690.891
Q23.81.0670.7710.93
Q33.70.90.7080.941 ↑
Q43.51.1670.8220.921
Q53.60.9330.8730.912

↑ marks items whose removal would raise alpha. Item-total correlations below about 0.3 are often reviewed.

How to use this tool

Check a scale's reliability in three steps.

  1. Copy your item scores

    Select the item columns in Excel, Sheets or SPSS: one row per respondent, with or without a header.

  2. Paste them

    Paste into the box. Alpha, standardized alpha and the item table update as you type.

  3. Review the items

    Look for low item-total correlations or a higher alpha if item deleted (↑), then copy the APA line.

FAQ

What is Cronbach's alpha?

A measure of internal consistency: how closely the items of a scale or questionnaire hang together. α = k ÷ (k − 1) × (1 − Σ item variances ÷ variance of the total score), with k the number of items.

What is a good Cronbach's alpha?

A common rule of thumb (George & Mallery, 2003): ≥ 0.9 excellent, ≥ 0.8 good, ≥ 0.7 acceptable, ≥ 0.6 questionable, ≥ 0.5 poor, below 0.5 unacceptable. Above about 0.95 the items may be redundant.

How do I paste my data?

One respondent per row and one item per column, as in Excel, Google Sheets or SPSS. Copy the cells and paste them; a header row with item names is optional. Rows with a missing score are left out.

What does alpha if item deleted mean?

The alpha the scale would have without that item. If it is higher than the current alpha (marked ↑), the item may not fit the scale or may be reverse-worded and not yet recoded.

Why is my alpha negative?

Usually because some items are reverse-worded: agreeing with them means the opposite of the others. Recode them (for a 1–5 scale, 6 minus the score) and paste the data again.