DECLARE & DEFINE
Make the intervention explicit.
Record what changed, when it changed, where it was applied and which outcome it was expected to influence. Then choose the treated population, the comparison group or the pre-intervention period—Trace checks whether the available data can support the proposed design.
ASSUME & ESTIMATE
State the conditions, then measure.
Document the conditions required for the comparison to be meaningful, including possible spillovers, anticipatory behaviour and concurrent events. Where the design is eligible, Trace applies an appropriate causal comparison—interrupted time series and difference-in-differences evaluations.
CHALLENGE & REVIEW
No claim without approval.
Diagnostics test whether the evidence behaves as the design expects—warnings, uncertainty and failed checks remain attached to the estimate. Analyst approval is required before estimation, and final sign-off is required before the finding informs a client decision or model update.
From movement to explanation
Built to say “we do not know.”
Sales rose after a campaign. Complaints fell after a service change. One outlet improved while another did not. Timing alone does not establish cause—other promotions, seasonal patterns, market shocks or differences between locations may offer competing explanations. Trace makes those explanations part of the investigation instead of hiding them behind a headline number.
WHAT TRACE RETURNS
Evidence with its boundaries attached.
An estimate of the intervention’s effect, an uncertainty interval around it, the population and window examined, design-specific diagnostics, warnings when the comparison is fragile, the assumptions the interpretation depends on and an auditable approval record.
HONEST LIMITS
A valid result can be “not identifiable.”
Trace does not discover causality from any dataset placed in front of it. It does not turn correlation into proof, and it cannot rule out events that were never recorded. If the intervention cannot be separated credibly from other explanations, the investigation should stop—often a more valuable answer than false certainty.
CLOSE THE LEARNING LOOP
Let evidence teach, not rewrite.
Marres helps teams learn, allocate, simulate and respond. Trace completes the cycle by testing what happened after a decision became an intervention. Models may learn from the result, but they may not quietly rewrite themselves—the estimate, its limitations and the person who approved its use remain visible.
Make each decision teach the next one. Evaluate a campaign, pricing change, service intervention, operational policy or controlled rollout—and carry the learning forward without pretending uncertainty has disappeared.
Evaluate an intervention ↗