Define the records before counting
Define the metric and inspect unusually high or low values against source records. Separate data errors from genuine unusual work. Record service type, period and any known cost or collection uncertainty. A valid specialist or long-distance job may belong in a separate analytical group without being erased from totals.
A worked example
Fictional collections are $100, $120, $130, $150 and $1,000. Their mean is $300 and median $130. Both describe the five records, but the mean is strongly affected by the $1,000 job. Showing only “average job value $300” would obscure the typical range in this small cohort.
Resolve the gap in evidence
Present count, total, median and range when they help the decision. If segmenting, state the rule before comparing and preserve the all-record total. Correct confirmed errors with an audit note. Do not exclude refunds or negative contribution merely because they lower a result.
Check whether it worked
Review whether the decision changes with and without the unusual but valid case, labeling that as sensitivity analysis. Reconcile both views to the same underlying ledger. Avoid treating one extraordinary job as expected recurring demand or using its economics as a universal benchmark for ordinary work.
Put it to work
A record you can use
- Metric and unusual value
- Source verification
- Valid record or correction
- All-record and segmented summaries
- Decision sensitivity
Plain text. No email required. Store completed records in your approved business systems.
Next useful step
Need help applying this to your marketing? A strategy call starts with your business and the evidence you have.
Talk through your next step →For a general editorial question, email Chris. Please leave out customer details. Questions are private, and no response time is promised.