A debutant disappears from the evaluation

A worked example using a hypothetical scenario to show how the reasoning applies.

The scenario

A hypothetical model drops every row without a previous-start figure, then describes its accuracy as applying to all runners. That claim exceeds its tested coverage. Report which runners were omitted and decide how the product should display an unavailable prediction rather than silently fabricating one.

What to take from it

Coverage is part of model performance; it should remain visible beside accuracy.

What to check next

• Record whether data is unavailable, not applicable or genuinely zero.
• Keep imputation rules with the model version.
• Compare evaluation coverage for complete and incomplete records.

Keep the conclusion specific

Separate the observation, the interpretation and the unresolved question. A worksheet is most useful when its conclusion stays within the evidence entered into it.

No missing racing fact is inferred for a real horse in this website.