1.7 Calculate and interpret dispersion for ungrouped data | Athabasca University MATH 215: Introduction to Statistics

Athabasca University MATH 215: Introduction to Statistics

Descriptive Statistics

Range, variance, and standard deviation for individual data values

In earlier lessons you learned how to summarize a data set using a single "typical" value, such as the mean. But two data sets can have the exact same mean while looking very different when you list out their values. One set might have numbers tightly bunched together, while another might swing widely from very small to very large. Dispersion (also called spread or variability) tells us how much the data values differ from each other and from the mean. This lesson focuses on ungrouped data, meaning raw, individual data values that have not been organized into frequency classes or intervals. You will learn three tools for measuring dispersion by hand: the range, the variance, and the standard deviation, and you will learn how to explain what each number means in the context of a real situation.

What you will learn

Define dispersion and distinguish it from measures of central tendency such as the mean.
Calculate the range, sample variance, and sample standard deviation for an ungrouped data set by hand.
State and check the conditions needed before applying each dispersion formula.
Interpret the numerical value of each dispersion measure in the context of the original data.
Identify common calculation errors and correct them using proper algebraic steps.

Reviewing the Building Blocks: Mean and Deviation

Before measuring spread, we need two ideas from arithmetic. First, recall the mean of a data set, written

\bar{x}

, which is found by adding all the values and dividing by how many values there are. Second, a deviation is the signed distance between one data value and the mean, calculated as

x - \bar{x}

. If a value is above the mean, its deviation is positive; if it is below the mean, its deviation is negative.

A key algebra fact you will use throughout this lesson is that the sum of all deviations from the mean always equals zero, because the positive and negative distances cancel out exactly. This is why we cannot simply average the deviations to measure spread — we need a way to stop the positive and negative signs from cancelling. The course-level solution is to square each deviation before averaging, which is exactly what variance does.

Throughout this lesson we work with a data set of

n

individual values, and every formula below is built for calculating dispersion directly from that list of values.

x - \bar{x}

The mean $\bar{x}$ is the arithmetic average of the data values.
A deviation is $x - \bar{x}$ , the signed distance from a value to the mean.
The sum of all deviations from the mean is always zero.
Squaring deviations prevents positive and negative values from cancelling when we measure spread.

The Range: The Simplest Measure of Spread

The range is the easiest dispersion measure to compute. It only requires the largest and smallest values in the data set. The condition for using the range is simply that the data must be measured on a numeric scale where subtraction makes sense (for example, test scores or measurements), and the data set must contain at least two distinct values.

The range gives a rough sense of spread but ignores everything about the values in between the maximum and minimum. Two data sets can have the same range yet very different patterns of spread among the middle values. Because of this limitation, the range is normally reported alongside variance and standard deviation rather than by itself.

\text{Range} = x_{\max} - x_{\min}

Condition: data must be numeric and have at least two distinct values.
The range only uses the maximum and minimum; it ignores the middle values.
Report the range together with variance or standard deviation for a fuller picture.

Variance: Averaging the Squared Deviations

Variance measures the average squared distance of the data values from the mean. Squaring each deviation removes the negative signs (since a negative number squared becomes positive), which solves the cancellation problem we saw earlier. Squaring also has the side effect of giving larger deviations extra weight, so variance is sensitive to values that are far from the mean.

The condition for calculating variance from a data set is that you have a numeric list of at least two observations, since the formula divides by

n-1

, which must not be zero. The value

n-1

is called the degrees of freedom; using

n-1

instead of

n

corrects for the fact that measuring spread from a limited list of values tends to underestimate the true variability, giving a slightly larger and more accurate result.

The variance formula sums the squared deviations of every data value from the mean, then divides by

n-1

. Because the deviations are squared, the resulting variance is expressed in squared units of the original data (for example, if the data are measured in kilograms, the variance is in kilograms squared). This makes variance harder to interpret directly, which is why we usually take one more step to find the standard deviation.

s^2 = \frac{\sum (x - \bar{x})^2}{n-1}

Variance averages the squared deviations from the mean, removing sign cancellation.
Condition: at least two numeric observations, since the divisor is $n-1$ .
Dividing by $n-1$ (degrees of freedom) gives a more accurate estimate of variability than dividing by $n$ .
Variance is expressed in squared units of the original data, which limits direct interpretation.

Standard Deviation: Returning to Original Units

The standard deviation is simply the square root of the variance. Taking the square root converts the measure back into the same units as the original data, which makes it much easier to interpret in context. For example, if data values are measured in dollars, the standard deviation is also in dollars, while the variance would be in dollars squared.

The condition for computing the standard deviation is the same as for variance: a numeric list of at least two observations. In practice, you always calculate the variance first and then take its square root; there is no separate formula that skips this step.

A larger standard deviation means the data values are, on average, farther from the mean, indicating more spread or variability. A smaller standard deviation means the values cluster more tightly around the mean. Standard deviation is the most commonly reported dispersion measure in introductory statistics because it combines meaningful units with sensitivity to every data value, not just the extremes.

s = \sqrt{s^2}

Standard deviation is the square root of variance, restoring the original units.
Condition: same as variance, requiring at least two numeric values.
Larger standard deviation indicates more spread; smaller indicates values cluster near the mean.
Standard deviation is the most widely interpreted dispersion measure because of its natural units.

Summary of Dispersion Measures

Measure	Formula	Units	What it Tells You
Range	$x_{\max}-x_{\min}$	Same as data	Total spread between extreme values only
Variance	$s^2=\frac{\sum(x-\bar{x})^2}{n-1}$	Squared data units	Average squared distance from the mean
Standard Deviation	$s=\sqrt{s^2}$	Same as data	Typical distance of a value from the mean

Worked example

Dispersion of Daily Study Times

A student records the number of minutes spent studying statistics on 6 randomly chosen days: 40, 55, 30, 65, 50, 60. Find the range, the variance, and the standard deviation of this data set, and interpret each result in context.

Check conditions and identify quantities
The data are numeric (minutes) and there are $n = 6$ distinct observations, satisfying the condition of at least two numeric values for computing range, variance, and standard deviation. The variable is study time in minutes, and the number of observations is $n=6$ .
$n = 6$
Calculate the range
Identify the maximum value, $65$ , and the minimum value, $30$ , then subtract.
$\text{Range} = 65 - 30 = 35$
Calculate the mean
Add all six values and divide by $n=6$ to find the mean study time, which will serve as the reference point for measuring deviations.
$\bar{x} = \frac{40+55+30+65+50+60}{6} = \frac{300}{6} = 50.000000$
Find each deviation and square it
Subtract the mean from every data value to get the deviation, then square each deviation to remove negative signs: for 40 the deviation is $40-50=-10$ squared to $100.000000$ ; for 55 it is $5$ squared to $25.000000$ ; for 30 it is $-20$ squared to $400.000000$ ; for 65 it is $15$ squared to $225.000000$ ; for 50 it is $0$ squared to $0.000000$ ; for 60 it is $10$ squared to $100.000000$ .
$(x-\bar{x})^2: 100.000000,\ 25.000000,\ 400.000000,\ 225.000000,\ 0.000000,\ 100.000000$
Sum the squared deviations
Add all six squared deviations together to get the numerator of the variance formula.
$\sum (x-\bar{x})^2 = 100+25+400+225+0+100 = 850.000000$
Divide by degrees of freedom to get variance
Divide the sum of squared deviations by $n-1 = 5$ to obtain the variance.
$s^2 = \frac{850.000000}{5} = 170.000000$
Take the square root to get standard deviation
Take the square root of the variance to return to the original units of minutes.
$s = \sqrt{170.000000} \approx 13.038405$
Round the final answers
Round the final standard deviation to two decimal places for reporting, since the original data were whole minutes; the variance and range are already exact.
$s \approx 13.04 \text{ minutes}$

Answer: Range = 35 minutes; variance

s^2 = 170.000000

squared minutes; standard deviation

s \approx 13.04

minutes.

Check: Reasonableness check: the standard deviation of about 13.04 minutes is smaller than the range of 35 minutes and roughly one quarter to one third of it, which is typical for a small data set; also, most of the individual deviations (10, 5, 20, 15, 0, 10) are reasonably close to 13.04, confirming the calculation is consistent with the spread visible in the raw data. In context, this tells us that on a typical day, the student's study time differs from the average of 50 minutes by about 13 minutes, showing moderate but not extreme variability in daily study habits.

Common mistakes and how to avoid them

Dividing the sum of squared deviations by

n

instead of

n-1

.

Correction: Always use

n-1

(degrees of freedom) when calculating variance from a data set, since dividing by

n-1

gives a more accurate measure of spread for this course's formulas.

Reporting the variance as the final answer when the question asks for standard deviation, or forgetting to take the square root.

Correction: Remember that standard deviation always requires one extra step after variance: take the square root of

s^2

to return to the original units.

Averaging the raw deviations

x-\bar{x}

directly, expecting a nonzero result to measure spread.

Correction: Recognize that raw deviations always sum to zero by definition of the mean; square the deviations first so positive and negative distances do not cancel.

Confusing the range with the full picture of spread, assuming two data sets with equal ranges must have equal variability.

Correction: Always calculate variance or standard deviation as well, since the range ignores every value except the maximum and minimum.

Forgetting units or reporting variance and standard deviation with the same unit label.

Correction: State variance in squared units (for example, minutes squared) and standard deviation in the original unit (for example, minutes), since squaring changes the unit.

Lesson summary

Dispersion measures how spread out data values are, complementing measures of central tendency like the mean.
The range is the simplest measure, found by subtracting the minimum value from the maximum value, but it ignores all middle values.
Variance $s^2$ averages the squared deviations from the mean, dividing by $n-1$ degrees of freedom for a more accurate result.
Standard deviation $s$ is the square root of the variance, restoring the original units and making interpretation easier.
A larger standard deviation means data values typically fall farther from the mean, indicating greater variability in context.
Always check that data are numeric with at least two values before applying these formulas, and keep several decimal places until the final rounding step.

Check your understanding

Question 1

A data set of 5 delivery times (in minutes) has a mean of 20 minutes. If the squared deviations are 4, 9, 1, 16, and 0, what is the variance?

$6.000000$
$7.500000$
$5.000000$
$30.000000$

Show answer and explanation

7.500000

Sum the squared deviations:

4+9+1+16+0=30

. Since

n=5

, divide by

n-1=4

:

30/4 = 7.500000

. Dividing by

n=5

instead (giving

6.000000

) uses the wrong divisor for this course's formula.

Question 2

Why do we square the deviations before averaging them when computing variance?

Squaring prevents positive and negative deviations from cancelling to zero
Squaring makes the calculation easier to do by hand
Squaring converts the data back into original units
Squaring removes the need to calculate the mean first

Show answer and explanation

Squaring prevents positive and negative deviations from cancelling to zero

The sum of raw deviations from the mean is always zero because positive and negative distances cancel exactly. Squaring each deviation makes every term positive, so the sum reflects total spread instead of cancelling out.

Question 3

A data set has a range of 50 and a standard deviation of 2. What is the most reasonable interpretation?

The data values are extremely tightly clustered around the mean, with the range driven by one or two extreme values
The standard deviation must be incorrect since it is smaller than the range
The variance equals 50 as well
This combination is impossible for any real data set

Show answer and explanation

The data values are extremely tightly clustered around the mean, with the range driven by one or two extreme values

A small standard deviation relative to a large range suggests most values cluster closely near the mean, while a small number of extreme values stretch the range wide. This is a valid and common pattern, not an error.

Question 4

What units should be reported for the variance of exam scores measured in points?

Points squared
Points
No units are needed for variance
Percent

Show answer and explanation

Points squared

Variance is calculated from squared deviations, so its units are the square of the original data units. Exam scores in points give a variance expressed in points squared, while the standard deviation would be reported in points.

Key terms

Dispersion: A general term for how spread out or variable a set of data values is, distinct from the data's central or typical value.
Deviation: The signed distance between one data value and the mean, calculated as $x - \bar{x}$ .
Range: The difference between the maximum and minimum values in a data set.
Variance: The average of the squared deviations from the mean, divided by $n-1$ degrees of freedom, denoted $s^2$ .
Standard Deviation: The square root of the variance, denoted $s$ , expressed in the same units as the original data.
Degrees of Freedom: The divisor $n-1$ used in the variance formula, which adjusts the calculation to give a more accurate estimate of spread.

Continue through MATH 215

View the complete Athabasca University MATH 215: Introduction to Statistics learning path

About this lesson

Published by DoAssignment. This AI-assisted lesson follows Athabasca University MATH 215: Introduction to Statistics, study topic 1.7. It is a study resource, not an official curriculum publication.

Official curriculum reference

Report a correction or ask a question

1.7 · Calculate and interpret dispersion for ungrouped data

Athabasca University MATH 215: Introduction to Statistics

Range, variance, and standard deviation for individual data values

What you will learn

Reviewing the Building Blocks: Mean and Deviation

The Range: The Simplest Measure of Spread

Variance: Averaging the Squared Deviations

Standard Deviation: Returning to Original Units

Summary of Dispersion Measures

Dispersion of Daily Study Times

Common mistakes and how to avoid them

Lesson summary

Check your understanding

Question 1

Question 2

Question 3

Question 4

Key terms

Continue through MATH 215

About this lesson