Descriptive Measures
Introduction
In statistics, after organizing data using tables and graphs, the next essential step is to
describe the characteristics of the data. Descriptive measures help us answer questions like:
• What is the “typical” value?
• How much variation exists in the data?
• Are there extreme values?
• How can we summarize a dataset in a meaningful way?
To address these questions, Chapter 3 introduces numerical measures of center,
spread, position, and standardized values. These measures allow us to understand
patterns and compare datasets more effectively.
Chapter Outline
3.1 Measures of Center
3.2 Measures of Variation
3.3 The Five-Number Summary: Boxplots
3.4 Descriptive Measures for Population: Use of Samples
Objectives
After completing this module, students will be able to:
1. Explain and compute measures of center such as the mean, median, and mode.
2. Identify and compute measures of variation including range, variance, standard
deviation, and IQR.
3. Construct and interpret the five-number summary and boxplots.
4. Distinguish between population parameters and sample statistics.
5. Compute and interpret z-scores to identify the relative standing of data values.
Try This!
“Which Class Did Better?”
A teacher recorded quiz scores from two classes:
• Class A: 78, 85, 90, 92, 88
• Class B: 70, 95, 100, 65, 90
Answer the following:
1. Which class has the higher typical score?
___________________________________________________________________
2. Which class shows greater variability?
___________________________________________________________________
3. Are there any unusually high or low scores?
___________________________________________________________________
4. Which measure of center (mean or median) is more appropriate for each class?.
___________________________________________________________________
Think Ahead!
1) Choosing the Center:
• Why might the median be preferred over the mean for skewed data?
______________________________________________________________
______________________________________________________________
• When is the mean more informative?
______________________________________________________________
______________________________________________________________
2) Understanding Variation:
• Why is standard deviation useful even if the range exists?
______________________________________________________________
3) Outliers:
• How do outliers affect the mean?
______________________________________________________________
______________________________________________________________
• Why are resistant measures important?
______________________________________________________________
______________________________________________________________
Read and Ponder
1. Measures of Center
• Mean: average of all values; sensitive to outliers.
• Median: middle value; resistant to outliers; better for skewed data.
• Mode: most frequent value; used for categorical data.
2. Measures of Variation
• Range = max – min
• Variance: average squared deviation from mean
• Standard deviation (s): square root of variance; primary measure of spread
• IQR = Q3 – Q1: resistant measure; used for outlier detection
3. Five-Number Summary & Boxplots
Includes: min, Q1, median, Q3, max.
Boxplots help compare distributions and detect potential outliers.
4. Population vs. Sample Measures
• Population: μ, σ
• Sample: x̄, s
• Samples are used to estimate population parameters.
5. Z-scores
̅
𝒙− 𝒙
𝒛=
𝒔
Indicates how far a value is from the mean in standard deviations.
Practice Problem
Student Stress Scores
A guidance counselor wants to analyze student stress scores from two grade levels.
Before comparing groups, she first examines the distribution of scores.
Grade 10 Stress Grade 10 Stress Grade 12 Stress Grade 12 Stress
Scores Scores Scores Scores
62 67 78 81
58 69 82 76
55 71 75 87
70 64 80 84
65 59 85 89
68 73 88 74
72 66 79 86
60 57 77 91
75 61 90 78
63 74 83 82
Questions:
A. What is the five-number summary for each group?
B. Which group seems more consistent in stress level?
C. Are there any potential outliers detected using IQR?
D. Based on the boxplots, which measures of center/spread should be used?
Step-by-Step in JAMOVI
1) Input data into JAMOVI
2) Explore the Data
Go to Analyses → Exploration → Descriptives
• Move Stress Score to Variables and Grade level to Split by
• Under Statistics, tick the following boxes:
o Central Tendency: Mean, Median, and Mode
o Percentile Values: Percentiles ten input 25, 50, 75 on the box next to it and
Cut points for then input 2 for equal groups
o Dispersion: Std. deviation, Variance, Range, Minimum, Maximum, and IQR
• Under Plots, tick the boxes for Box plot and Label outliers
A. What is the five-number summary for each group?
Minimum: 55 for Grade 10 and 74 for Grade 12
Maximum: 75 for Grade 10 and 91 for Grade 12
Q1(25th Percentile): 60.75 for Grade 10 and 78 for Grade 12
Q3(75th Percentile): 70.25 for Grade 10 and 86.25 for Grade 12
Median: 65.5 for Grade 10 and 82 for Grade 12
B. Which group seems more consistent in stress level?
Grade 10 students seems more consistent in stress level due to its smaller spread of
scores compared to the Grade 12 students.
C. Are there any potential outliers detected using IQR?
Detecting Outliers using IQR:
Below: Q1-1.5(IQR)
Above: Q3+1.5(IQR)
For Grade 10 Students:
Lower Fence: 60.75 – 1.5(9.5) = 46.5| Minimum=55 ≥ 46.5
Upper Fence: 70.25 + 1.5(9.5) = 84.5| Maximum=75 ≤ 84.5
There are no potential outliers detected for the stress scores in Grade 10 students.
For Grade 12:
Lower Fence: 78 – 1.5(8.25) = 65.625| Minimum=74 ≥ 65.625
Upper Fence: 86.25 + 1.5(8.25) = 98.625| Maximum=91 ≤ 98.625
There are no potential outliers detected for the stress scores in Grade 12 students.
D. Based on the boxplots, which measures of center/spread should be used?
Both box plots for Grade 10 and Grade 12 students appear to be symmetric
which implies that there are no outliers present, therefore, the mean should be used as
the measure of center and the standard deviation for the measure of spread.
Conclusion
Descriptive measures allow us to summarize large sets of data with just a few
key statistics. They help identify the center, variation, distribution shape, and unusual
values. These tools provide the foundation for deeper statistical analysis, including
hypothesis testing and inference.
See If You Can Do This
1) Compute the mean, median, and mode for the dataset:
45, 52, 52, 60, 71, 80
2) Determine the five-number summary for:
10, 12, 18, 22, 30, 45, 50
3) A student received a test score of 88, with a class mean of 80 and
standard deviation of 4.
• What is the z-score?
• Interpret it.
Reference:
Weiss, N., 2012. Elementary Statistics 8th edition.