Chapter 04

Statistical Tests for AI Quality

Choose the statistical test based on the data shape: paired vs independent, numeric vs categorical, ordinal vs binary. State the null hypothesis before running the eval. Report effect size and practical risk, not only p-values. Control false discoveries when trying many…

Apply this chapter

  • Choose the statistical test based on the data shape: paired vs independent, numeric vs categorical, ordinal vs binary.
  • State the null hypothesis before running the eval.
  • Report effect size and practical risk, not only p-values.
  • Control false discoveries when trying many prompts, models, policies, or slices.

Continue the conversation

Apply this to your context.

Save your product context once, then open a focused conversation that combines it with this concept.

8 focused briefs

Concepts in this chapter

  1. 020
    Comparing Versions with t-testsA t-test can help Confidence Engineers decide whether a difference in average scores is likely to be real or just sampling noise.
  2. 021
    Null Hypothesis: What Are We Actually Testing?The null hypothesis is the boring default: assume the new AI system is not really better until the evidence is strong enough to challenge that…
  3. 022
    Chi-Squared Tests for Categorical AI QualityChi-squared tests help compare counts, categories, and failure distributions when quality is not a smooth 0-10 score.
  4. 023
    P-Values: Evidence, Not PermissionP-values can support a comparison, but they do not decide whether a product is safe, useful, or worth shipping.
  5. 024
    Statistical Significance vs. Practical SignificanceA difference can be statistically credible and still too small to matter. Confidence Engineers need to explain both sides.
  6. 025
    Power Analysis and Minimum Detectable EffectBefore asking whether a change won, builders should decide what size of win would actually matter.
  7. 026
    Multiple Comparisons and False DiscoveriesThe more slices, variants, and metrics you inspect, the more likely one lucky result will look real.
  8. 027
    F-Scores, Precision, Recall, and AI QualityF-scores help Confidence Engineers reason about the tradeoff between catching the right things and avoiding false alarms.

Shared across the Knowledge Edition

Adapt every concept to your world.

Describe your product, role, users, risks, constraints, or current quality problem. This stays in this browser until you choose to send it to ChatGPT.

Saved only in this browser.0 / 2400