Outliers, invalid values and the population
A value can be statistically unusual and still correct. A value inside normal-looking limits can still be a recording error.
An IQR flag means unusual relative to the observed distribution. The dictionary determines validity; source evidence determines accuracy. Age 220 is unresolved invalid data. A verified 47-year-old student is an unusual valid member of the cohort. Age 21 could still be a typo for 31.
Flag invalid age as missing while preserving the student's usable programme and score. Correct a value only with evidence. Retain valid influential values, choose robust summaries when appropriate and report sensitivity as a comparison, not as a replacement for the intended-population result.
In W3 p. 43, all 100 students include 10 withdrawals. Five verified older students include four withdrawals. Removing them leaves 6/95=6.32%, versus 10/100=10%. Nobody's outcome improved; numerator, denominator and represented population changed. Lead with 10% if the target is all enrolled students, and show subgroup rates with their small sample sizes.
Source: W3 PDF pp. 4-55. The 14-row registry example below comes from the Week 3 lab code you previously pasted in this conversation; it is separate from the lecture's smaller examples.
The lecture's robust summaries are tested by changing one extreme value. The lab also makes the quartile convention explicit.
The lecture's fences and whiskers become record-level checks. Programme summaries and two equal-mean/SD classes show why the whole shape matters.
The lecture distinguishes copies, corrections and repeated events. The evidence packet supports removing R13, retaining R14 over R02, and flagging an invalid age value.
An IQR flag describes unusualness, while the dictionary and source establish different evidence. Deleting verified older students changes the population behind a rate.
Practice problems
Supplementary study questions on the lecture concepts — not verbatim exam questions. Each answer counts toward spaced review.
1. Conceptual understanding
Definitions and distinctions.
How should a verified 47-year-old and age 220 be treated?
Does an age inside IQR review limits guarantee accuracy?
2. Application
Apply the concept to a case or calculation.
The dictionary allows ages 16–100, but a row says 220. What is supported without a verified replacement?
A source verifies age 52 for an enrolled student outside the IQR fences. What should happen?
3. Interpretation and limitations
Evaluate assumptions and justify conclusions.
Deleting valid older students lowers a withdrawal percentage. What changed directly?
Which mistake could pass a reasonable age range and an IQR check?
Explain it in writing
Self-checked, not marked. Write a few sentences, then compare with the example answer. Your writing is saved as you type.
Show an example answer
It is a plausible guess, not verified evidence. The intended age could be something else. Flag it and consult the source while keeping the raw value.
Check: did you answer the question, use evidence or working, and avoid claiming more than the evidence supports?
Show an example answer
The rate for all enrolled students. You can additionally show age-group rates with counts, but excluding verified older students changes the target population.
Check: did you answer the question, use evidence or working, and avoid claiming more than the evidence supports?