#statistics.

Act as a Statistician for Manufacturing. Teach our quality team how to use SPC. 1. Explain Control Charts (X-bar and R charts). 2. Define 'Common Cause' vs. 'Special Cause' variation. 3. Set up rules for when a process is 'Out of Control' (e.g., Western Electric Rules). 4. Guide us through calculating Cp and Cpk (Process Capability) for a critical dimension with a tolerance of [Insert Tolerance].

You are a biostatistician and data scientist. I have run a [type of analysis: regression/ANOVA/t-test/chi-square/etc.] and need help interpreting the results. Think step by step: 1) State what statistical test was run and what it is designed to test, 2) Interpret the key output metrics (coefficient/p-value/F-statistic/etc.) in plain English — what does each number mean?, 3) Is the result statistically significant? Is it practically significant? (Distinguish between these.), 4) What are the key assumptions of this test and should I check if they are violated in my data?, 5) What can I conclude from this analysis? What should I NOT conclude (common misinterpretation)?, 6) What follow-up analysis would strengthen or challenge this finding? Results: [paste your output]. Context: [describe your research question and dataset].

You are a statistician and experimentation platform expert. Design a rigorous A/B test for the following change: [describe the change, e.g., "a new checkout flow"]. Step 1: Hypothesis formulation — write the null and alternative hypothesis formally. Step 2: Metric selection — define the primary metric (must be measurable, attributable, and sensitive) and guardrail metrics. Step 3: Sample size calculation — given baseline conversion rate [X%], desired minimum detectable effect [Y%], significance level [α = 0.05], and power [1-β = 0.80], calculate the required sample size per variant. Show the formula. Step 4: Test duration — given [Z daily visitors], how long should the test run? Account for weekly seasonality. Step 5: Segmentation plan — should this be run on all users or a segment? What are the risks of each? Step 6: Analysis plan — when and how to analyze (avoid peeking), how to handle outliers and novelty effects, when to call the test. Step 7: Decision criteria — what result justifies shipping vs rolling back?