Questions to Ask When Analyzing Data

Anchors the work to a real decision owner and prevents aimless exploration.

Clarifies deliverables so scope, method, and timelines match the business need.

Surfaces selection, measurement, and survivorship biases that distort conclusions.

Avoids aggregation errors and mismatched denominators that mislead stakeholders.

Forces data quality triage before modeling, improving reliability of results.

Frames results relative to expectations or controls, not in isolation.

Prevents invalid inference by checking normality, independence, stationarity, etc.

Encourages counterfactual thinking and reduces false certainty in causal claims.

Tests robustness by varying inputs, features, or time slices.

Right-sizes complexity to interpretability and deployment costs.

Ensures generalization and guards against overfitting to historical noise.

Communicates uncertainty transparently for risk-aware decisions.

Focuses on downside risk and mitigation plans upfront.

Prioritizes simple narratives, visuals, and decision-ready artifacts.

Turns findings into a playbook with clear responsibilities.

Creates a learning loop that compounds value across projects.

Reduces legal and reputational risk by designing for responsible use.

Frames impact in dollars, hours, or risk reduction to prioritize execution.

Plans for maintenance, alerts, and retraining to preserve performance.

Forces ruthless synthesis so the recommendation is easy to approve.