Impact on Interquartile range

An SAT Math micro-topic under Center, spread, and shape of distributions (Problem solving and data analysis). Free to read — no account needed.

The interquartile range measures the spread of the middle half of a dataset: IQR=Q3−Q1\text{IQR} = Q_3 - Q_1.
On a box plot it is the width of the box, from the first quartile to the third.
iqr_boxplot.png
When you add or replace a value, the quartiles can shift.
Suppose a new data point replaces the highest value in the set; the median, Q1Q_1, and Q3Q_3 may all move to new positions.
Where exactly they land depends on the other values in the data.
The important point is that Q1Q_1 and Q3Q_3 need not move by the same amount.
Q1Q_1 might rise by 11 while Q3Q_3 rises by 55, because each quartile is set by a different part of the data.
Since the two ends move differently, the gap between them — the IQR — changes.
So never assume a change leaves the IQR fixed; check both quartiles.
Find Q1Q_1 and Q3Q_3 before and after the change, then compare Q3−Q1Q_3 - Q_1.
Only if both quartiles shift by the same amount, or neither moves, does the IQR stay the same.

Worked examples

A dataset has Q1=3Q_1 = 3 and Q3=9Q_3 = 9. What is its interquartile range?
The IQR is Q3−Q1Q_3 - Q_1.
So the IQR is 9−3=69 - 3 = 6.
After a new value is added, Q1Q_1 rises from 33 to 44 but Q3Q_3 stays at 99. Does the IQR change?
The new IQR is 9−4=59 - 4 = 5, compared with the old 9−3=69 - 3 = 6.
So yes, the IQR changes, dropping from 66 to 55.
A change shifts both Q1Q_1 and Q3Q_3 up by exactly 22. Does the IQR change?
If both quartiles move by the same amount, their difference is unchanged.
So the IQR stays the same.

Is this one of the topics costing you points?

Take the free 10-question diagnostic for a predicted SAT score and a breakdown of which domains are costing you points.

Predict your SAT score →

More in Center, spread, and shape of distributions