Tensions in Practice: Typical items in tension with typical encounters¶
Two jobs occupying one and three time units
Two invented jobs have lengths 1 and 3 and occupy four time units with no overlap or idle time. Choosing one of the two jobs uniformly gives average length 2. Choosing a moment uniformly from their occupied time is three times as likely to encounter the longer job; the average full job length encountered is 2.5. Both answers are correct for their stated sampling rule.
Describe the typical job
Give each job one equal opportunity to be included.
Describe occupied time
Give each occupied moment one equal opportunity to select its job.
Why these aims pull against each other
A convenient time encounter weights a job by its duration. Equal job inclusion needs a job-based frame and may require following jobs to completion.
Choose an arrangement to see what changes and what remains difficult.
Arrows express the declared relations, not measured effect sizes. Examples and quantities are illustrative.
What this choice protects
What it costs
When it fits
Compare the arrangements
Give each job equal weight
Enumerate the jobs and record each complete duration once.
- What it protects
- The mean describes a uniformly selected job.
- What it costs
- A complete job frame and follow-up take effort and may delay results.
- When it fits
- The question concerns job durations and the set can be followed without unaccounted loss.
Illustration note: The two-job arithmetic is exact and intentionally omits censoring or attrition.
Give each occupied moment equal weight
Select a moment uniformly from the declared four occupied units and identify the job containing it.
- What it protects
- The result describes which full job lengths dominate occupied-time encounters.
- What it costs
- Long jobs receive more weight, so the result cannot be read as the equal-job mean.
- When it fits
- The question concerns encounters or occupied time, or the weighting is explicitly accounted for.
Illustration note: The diagram uses known full durations to expose the sampling mechanism; a real snapshot may not yet reveal the eventual duration.
What this illustration does—and does not—establish
The source supplies the stated tension; the selected arrangements are bounded editorial illustrations. Costs and conditions remain part of the comparison.
- The numbers are invented; there are no arrivals, service recommendations or queue waiting-time calculations.
- Uniform occupied-time selection is assumed. Idle periods, unequal encounter timing or other selection mechanisms change the weights.
- The 2.5 is the expected full length of the encountered job, not its remaining duration.
Source entries
Inspection Paradox
This source passage supplies the contextual tension. The concrete arrangements and schematic examples are editorial illustrations, not measured findings.
Which Statistic Is the Question (scopal)
T2 — Which Statistic Is the Question (scopal). "Typical interval length" and "length of the interval I'm in" are *both correct* statistics of different populations; the paradox is a confusion about which question is being asked, not an error in either answer. The boundary is the definition of the estimand. The failure mode is treating the encounter-mean as a wrong answer to the enumeration question (or vice versa) when each is the right answer to its own — the superintendent and the parent both report true numbers. Diagnostic: pin down whether the quantity of interest is averaged over *items* or over *encounters* before calling any number biased.
The source operation
When the act of sampling intervals — or chunks, runs, or relationships — proceeds by *encountering* them rather than by *enumerating* them, longer intervals are systematically over-represented in the sample in direct proportion to their length. The bias is not statistical noise to be averaged away; it is a structural consequence of the sampling mechanism. Selecting intervals with probability proportional to size — which is exactly what "showing up at a random moment and asking which interval contains me" does — yields a sample whose distribution of lengths is the *length-weighted* version of the underlying distribution, not the underlying distribution itself.
Following starts takes time
T4 — Static Snapshot versus Inception Cohort (temporal). The canonical correction — "study a cohort followed from inception, not the cases currently ongoing" — trades the length-bias of a cross-section for the cost and delay of longitudinal follow-up. The competing consideration is that the cohort design is slower, more expensive, and itself prone to attrition.