Measuring spread: standard deviation and the five-number summary
Two ways of describing how spread out a data set is. One uses every value, the other uses five positions. Both appear on Exam 3.
A short walkthrough explaining what you need to know and how to solve this question type lands here once it's recorded.
ALEKS randomizes the numbers each attempt, but the question shape stays the same. Here are three example versions you might see.
Distances to the nearest airport for 14 families, already sorted:
11, 12, 13, 14, 18, 22, 23, 27, 27, 37, 37, 38, 39, 42
What is the interquartile range?
Same fourteen values: 11, 12, 13, 14, 18, 22, 23, 27, 27, 37, 37, 38, 39, 42.
What is the median?
For the six values 49, 52, 50, 54, 55, 52 the squared differences from the mean total 26.
What is the sample standard deviation, to two decimal places?
Red blood cell counts measured on six days:
49 52 50 54 55 52
Find the sample standard deviation, to two decimal places.
The mean
The squared differences
Divide by n minus 1, then root
Now the five-number summary
For fourteen sorted distances: 11, 12, 13, 14, 18, 22, 23, 27, 27, 37, 37, 38, 39, 42.
Minimum 11, maximum 42. With fourteen values the median sits between the 7th and 8th: (23 + 27) ÷ 2 = 25. The lower half is the first seven, so Q1 is its middle value, 14. The upper half is the last seven, so Q3 is 37.
The interquartile range is 37 − 14 = 23: the spread of the middle half of the data.