All tools

Content validity index (CVI) calculator

The content validity index, proposed by Lynn (1986) and popularized by Polit and Beck (2006), is widely used in nursing, health and psychology research. Each judge rates the relevance of each item from 1 to 4, and the index is the proportion of judges who gave it a 3 or 4. Paste the ratings from Excel: one row per item and one column per judge.

The calculation runs in your browser. We don’t store what you type.

How it’s calculated

Each item’s I-CVI: the number of judges who rated it 3 or 4, divided by the total number of judges.

The instrument’s S-CVI/Ave: the mean of all the item I-CVIs.

The instrument’s S-CVI/UA: the proportion of items where every judge gave a 3 or 4.

The modified kappa (k*) by Polit, Beck and Owen (2007) adjusts the I-CVI for the chance that judges agree at random.

How to read the result

  • With 3 to 5 judges, each item needs I-CVI = 1.00 (full agreement). With 6 or more, the minimum is 0.78.
  • For the instrument, an S-CVI/Ave of 0.90 or more is recommended. The S-CVI/UA is stricter, and 0.80 or more is considered good.
  • Read the modified kappa like this: above 0.74 excellent, 0.60 to 0.74 good, 0.40 to 0.59 fair and below 0.40 poor.
  • Revise the items below the minimum using the judges’ comments before your pilot test.
Next stepCronbach’s alpha calculatorAfter expert judgment comes the pilot test: calculate reliability with Cronbach’s alpha.Step-by-step guideAiken's V, Lawshe, CVC or binomial test: which one to use to validate your instrumentAiken's V vs Lawshe's CVR vs Hernández-Nieto's CVC vs the binomial test: how judges answer, the formula, an example and the cut-off for each.

Frequently asked questions

What is the difference between CVI and CVC?
The CVI counts the proportion of judges who rated the item relevant (3 or 4 on a 1 to 4 scale). Hernández-Nieto’s CVC uses the mean rating across the whole scale and subtracts the chance error. Use the one your university asks for.
What scale should judges use?
The original 4-point scale: 1 = not relevant, 2 = somewhat relevant, 3 = quite relevant, 4 = highly relevant. Four points are used so there is no neutral midpoint.
Should I report S-CVI/Ave or S-CVI/UA?
Polit and Beck recommend reporting the S-CVI/Ave. Many studies report both. Make clear which one you use, because with many judges the UA is much lower.
Do I rate clarity and relevance separately?
Yes. If your judges rated several criteria, calculate one index per criterion.

Know what you want to ask?

Build the survey in SurvIQ, share it by link, WhatsApp or QR code, and watch results come in live. The Free plan is free forever.

Create a free survey

More tools

Kendall’s W calculatorAgreement among expert judges: W, chi-square and p-value.Binomial test for expert judgmentValidate each item with judges who answer yes or no: agreement and exact p-value.Cohen’s and Fleiss’ kappa calculatorMeasures agreement between raters or judges, beyond what chance would produce.Normality test (Shapiro-Wilk and Kolmogorov-Smirnov)Check whether your data is normally distributed before choosing a statistical test.Student’s t-test calculatorCompares the means of two groups or a before and after, with Levene’s test and Cohen’s d.Mann-Whitney U test calculatorCompares two independent groups when the data aren’t normal or are ordinal.