A dependency-light Python script (standard library only) that turns raw per-viewer ratings into a defensible subjective-test result: per-condition Mean Opinion Score, standard deviation, and the ITU-R BT.500 95% confidence interval (ε = 1.96 · S/√N, with a Student-t multiplier auto-selected for small N). It flags when N is below the ~15 practical floor, reports whether two conditions' confidence intervals overlap (i.e. whether the test can separate them), and runs on a CSV or a built-in sample d
Download free PDF
The handbook · 7 volumes
Fora Soft Video Engineering Handbook
This MOS confidence-interval calculator turns raw viewer ratings into MOS, standard deviation and the BT.500 confidence interval, and flags when your panel is too small to separate two conditions. Our seven-volume handbook covers the video stack; start with Volume 1 on quality metrics and how codecs create artifacts, then Volume 3 on QoE monitoring and Volume 6 on AI models. Written by Nikolay Sapunov, CEO at Fora Soft.
Running a subjective MOS test and unsure the panel is big enough?
Send us your test plan or ratings, and we will check the sample size and confidence intervals and say which differences the results can support. 250+ video products shipped since 2005.
You get a realistic estimate, technical recommendations and next steps. Free, no obligations.
