Reference Population Note¶
Documentation artifact — instantiates Conditioned Probability Frame Specification
A short written note pinning exactly which population a rate is computed over, and where that denominator stops being valid, so the number can't drift onto a different base.
Most conditional-probability misuse is denominator drift: a rate estimated over one population gets quietly applied to another. Reference Population Note is the documentation artifact that fixes the denominator in writing. It answers, in a sentence or two, exactly who is counted in the bottom of the fraction — which cases are in, which are excluded, over what window — and states where that base stops being valid. Its defining move is that it is about the denominator specifically, as a single stated population, not the event, not the calculation, not a comparison: it pins one number's base so the number can't wander onto another.
Example¶
A labor ministry publishes a headline "unemployment rate: 4.1%." That figure is a probability-like rate, and its denominator is doing quiet, heavy lifting. The Reference Population Note attached to it reads: "Numerator: persons actively seeking work in the past four weeks and available to start. Denominator: the civilian labor force — employed plus actively-seeking — aged 16+. Excludes: discouraged workers who stopped looking, full-time students, retirees, and the institutionalized. Not valid as a measure of 'share of adults without a job,' which uses a different base."
The last line is the point. A commentator who wants to say "4.1% of adults can't find work" is stopped by the note, because that claim uses a denominator (all adults) the rate was never computed over. Without the note, the 4.1% floats free and gets re-based by whoever quotes it; with it, the base travels with the number and the invalid re-use is flagged before it happens.
How it works¶
- State the denominator explicitly. Name the population in the bottom of the fraction: who is included, over what time window, under what sampling rule.
- List the exclusions. Say who is not counted, because the excluded cases are exactly where a reader's intuitive denominator diverges from the real one.
- Mark the assumption boundary. Note the conditions under which the population definition holds — the selection rule, the eligibility cutoff, the counting convention.
- Mark the reuse boundary. Name at least one tempting re-use the number does not support, so the drift is pre-empted rather than discovered.
Tuning parameters¶
- Specificity of the population statement — a one-line label versus a full inclusion/exclusion spec. Detail prevents drift but lengthens every report that carries the note.
- Exclusion emphasis — how prominently the excluded cases are flagged. Foregrounding exclusions is honest but can make a clean headline look hedged.
- Number of reuse warnings — none, one, or an enumerated list of invalid re-bases. More warnings pre-empt more misuse but risk reading as defensive boilerplate that gets skipped.
- Attachment tightness — a footnote near the number versus a separate methodology appendix. Tight attachment survives quoting; a distant appendix is thorough but easily severed.
When it helps, and when it misleads¶
Its strength is that it defends the denominator, the single most drift-prone part of a conditional claim, in the cheapest possible medium: prose a reader can absorb without any statistical machinery. It is what keeps "4.1%" or "1 in 8" from being silently re-based when it's quoted downstream — a written instance of the reference-class problem, the fact that the same case belongs to many populations[1] and its probability differs in each.
Its failure mode is that a note documents the denominator without anyone honoring it: prose is advisory, and a determined misquoter can simply ignore the exclusions. The classic misuse is a note so buried or so verbose that it's never read, letting the headline rate travel naked despite the paperwork existing. The guarding discipline is to keep the note short, attach it as close to the number as the medium allows, and lead with the one reuse boundary that matters most rather than an exhaustive list nobody finishes.
How it implements the components¶
denominator_population— this component is the note's subject: the explicit statement of the population the rate is computed over.assumption_boundary— it records the selection and eligibility assumptions the denominator rests on.reuse_boundary— it names where the number stops being valid, blocking re-basing onto a different population.
It does NOT implement frame_compatibility_check — adjudicating whether two rates may be compared is the frame compatibility review's job; the note describes one denominator, it does not referee a comparison. Nor does it implement base_rate_reference or a subgroup breakdown — laying strata side by side belongs to the stratified rate table.
Related¶
- Instantiates: Conditioned Probability Frame Specification — this mechanism keeps the denominator visible for a single rate.
- Sibling mechanisms: Conditional Probability Annotation · Frame Compatibility Review · Given-That Clause · Likelihood-Ratio Frame · Probability Tree · Scenario Condition Card · Stratified Rate Table · Two-by-Two Probability Table
Editorial Notes¶
Form Classification¶
Form family: Representation, Specification & Plan
Rationale: Reference Population Note operates as a static representation, map, specification, schema, or prospective plan that externalizes information because it a short written note pinning exactly which population a rate is computed over, and where that denominator stops being valid, so the number can't drift onto a different base.
Independent corroboration: The frozen evidence defines Reference Population Note as 'A short written note pinning exactly which population a rate is computed over, and where that denominator stops being valid, so the number can't drift onto a different base', so its operative form is Representation, Specification & Plan.
Review outcome: Independent reviewer agreement; high confidence.
Origin Attribution¶
Primary origin: Statistics & Experimental Design
Origin pattern: Single lineage
Present-day reach: Universal
Rationale: Explicitly defining the denominator and target population is core statistical inference practice.
Review resolution: Both blind reviewers agree that statistics_experimental_design is the primary origin. Explicit reconciliation of alternate origin disagreement, origin mode disagreement, domain reach disagreement adopts reviewer_a's classification because explicitly defining the denominator and target population is core statistical inference practice. The resulting lineage records alternates=none, origin_mode=single_lineage, and domain_reach=universal; these describe formative provenance separately from later applicability.
Encyclopedia synthesis: The exact catalogued form synthesizes established practice rather than reproducing a single standard historical label.
Review outcome: Reconciled after independent review; high confidence.
Notes¶
The nearest twin is the Stratified Rate Table: both are denominator-conscious artifacts. The note pins one denominator and forbids re-basing it; the table deliberately splits the denominator into subgroups so their rates can be read against each other. Reach for the note to protect a single figure, the table to compare several.
References¶
[1] Hájek, A. "The Reference Class Problem Is Your Problem Too". Synthese 156(3), 563–585 (2007). Defines the reference-class problem: the same case can belong to multiple classifications and receive different probabilities under each. registry ↩