Paste your codes
One row per segment: Coder 1’s code, then Coder 2’s. Codes can be names or numbers. Copy two columns straight from a Google Doc table or a spreadsheet (tab-separated), or type them with a space or comma between (use a comma if a code name has spaces in it). Leave a cell empty when a coder gave that segment no code.
Notes
- One code per segment. Cohen’s κ assumes each coder picks exactly one code per segment. If you allow several, compute κ per code instead: a column of yes/no for each coder.
- Spelling counts. “Workaround” and “Work-around” are different codes here. Agree on code names from the codebook first.
- κ = (P(a) − P(e)) / (1 − P(e)): observed agreement corrected for the agreement you’d expect by chance, given how often each coder used each code.
- Bands (Landis & Koch, 1977): below 0 poor, .00–.20 slight, .21–.40 fair, .41–.60 moderate, .61–.80 substantial, .81–1.00 almost perfect.