Enter the number of raters who assigned each case to each category. Each row must sum to the number of raters.
Paste tab-separated or comma-separated data. Each row = one case. Each column = one category count.
Drag & drop your file here, or click to browse. Supports .xlsx, .xls, .csv. Make sure your data matches the selected format above.
Click to upload or drag & drop
Excel (.xlsx, .xls) or CSV (.csv)
Kappa is a chance-adjusted measure of inter-rater agreement. Unlike simple percent agreement, it accounts for agreement expected by chance alone. Values range from -1 (complete disagreement) to +1 (perfect agreement).
Assumes raters are not forced to assign a certain number of cases to each category. Uses uniform chance agreement (1/k). Recommended when raters have free choice.
Assumes raters are forced to assign a certain distribution of cases. Uses observed marginal distribution for chance agreement. Use when category quotas are fixed.
| Kappa Value | Strength of Agreement |
|---|---|
| < 0.00 | Poor (less than chance) |
| 0.00 โ 0.20 | Slight |
| 0.21 โ 0.40 | Fair |
| 0.41 โ 0.60 | Moderate |
| 0.61 โ 0.80 | Substantial |
| 0.81 โ 1.00 | Almost Perfect |
References: Fleiss (1971), Randolph (2005), Gwet (2010), Brennan & Prediger (1981), Landis & Koch (1977)