UPI Study › Courses › Educational Psychology › Free lessons › Lesson 8.6 Free with a free account
The Bell Curve and Standard Deviation: What the Numbers Tell Us
Educational Psychology · Chapter 8: Assessment, Testing, and Making Sense of ResultsSection 8.6 · lesson 75 of 1009 min · free with a free account
Free preview
Create a free account to keep watching
It takes a minute and costs nothing. Your free account unlocks all of Chapter 1 and 3 more lessons of Educational Psychology.
Lesson complete
Earn the 3 college credits for Educational Psychology
Enrolling adds a quiz after each lesson, the graded work and the official transcript. Recommended for credit by NCCRS.
Next lesson: Compared to Others vs. Compared to a Standard: Norm vs. Criterion →← From Scores to Insights: How to Summarize Assessment ResultsNext lesson: Compared to Others vs. Compared to a Standard: Norm vs. Criterion →
In this lesson
The empirical rule, z-scores, and when not to assume a normal distribution.
- Describe the normal distribution and its two parameters
- Apply the empirical rule to interpret a score
- Calculate and interpret a z-score
- Recognize when educational data are not normal
Transcript
Everything said in the video, section by section (1,222 words). Read along, or search it.
Assessment, Testing, and Making Sense of Results
The Bell Curve and Standard Deviation
Three numbers do most of the work in educational measurement. Sixty-eight, ninety-five, and ninety-nine point seven. Learn what they mean and most score reports become readable. This section starts with the normal distribution itself. Then standard deviation, which is what makes a score a location. Then the empirical rule, which is where those three numbers come from. Then z-scores, which let you compare across completely different tests. And finally a warning about when none of this applies. That warning matters more than it might sound. The bell curve is a model of some data, not a law about all data. Applying it where it does not fit produces confident nonsense.
The Shape
Why So Many Measurements Look the Same
Many naturally occurring measurements share a characteristic shape. Height and weight, for instance. Also reaction time. And scores on carefully constructed psychological tests. That pattern is called the normal distribution. It is also known as the Gaussian distribution. Plotted as a frequency histogram, it forms a symmetrical bell. Most scores cluster near the center, which is the mean. And progressively fewer scores appear as you move toward the extremes. Those extremes are called the tails. Two parameters define the distribution completely. The mean, which is the arithmetic average. In a perfectly normal distribution, it equals the median and the mode. And the standard deviation, measuring how spread out the scores are.
Why It Matters
Tests Are Built to Produce This Shape
Why is this distribution so foundational to educational measurement? Partly because many standardized tests are built to produce it. Deliberately constructed, through item selection and through norming. That construction buys three specific advantages. It allows the use of parametric statistics. It enables calculation of percentile ranks from standard scores. And it makes intuitive predictions about proportions possible. You can say what share of students fall in any given range. But educators should be cautious here, and the caution is important. Not all educational outcomes follow a normal distribution. And assuming normality where it does not exist leads to erroneous interpretations. The shape was engineered into these tests. It was not discovered in students.
Standard Deviation
How Far From the Middle Is Normal?
Standard deviation quantifies the average distance of scores from the mean. That is the whole definition, and it is worth sitting with. A small standard deviation means something specific. Scores cluster tightly around the mean. A large standard deviation means the opposite. Scores are widely spread out across the range. Notice what that single number does for you. It turns a score into a location. Without it, you know where the middle of the group is. But you do not know whether one score is close to it, or far from it. The mean alone cannot tell you that.
Empirical Rule
Sixty-Eight, Ninety-Five, Ninety-Nine Point Seven
For a normal distribution, three proportions always hold. Approximately sixty-eight percent of scores fall within one standard deviation. One standard deviation of the mean, in either direction. Approximately ninety-five percent fall within two standard deviations. And approximately ninety-nine point seven percent fall within three. That is known as the empirical rule. You will also see it called the sixty-eight, ninety-five, ninety-nine point seven rule. Which is a mouthful, and also a complete description. So why memorize three numbers? Because they let you interpret a score immediately. Relative to the group, without a table and without software.
Worked
A Reading Test With Mean 100 and SD 15
Consider a standardized reading test to see this working. It has a mean of one hundred, and a standard deviation of fifteen. A student scores one hundred and fifteen. That is one standard deviation above the mean. Which means scoring better than approximately eighty-four percent of the norm group. Now take a student who scores seventy. That is two standard deviations below the mean. That student scored better than only about two point five percent of the group. A result like that would typically trigger concern. And further evaluation. Understanding standard deviation is what lets you make that call. It separates typical variation from a genuine outlier requiring intervention.
Z-Scores
One Number That Works on Every Scale
The z-score generalizes all of this into one number. It expresses how many standard deviations a raw score sits from the mean. Above or below, depending on the sign. The formula is straightforward. Take the raw score, subtract the mean, then divide by the standard deviation. A z-score of zero means the student scored exactly at the mean. A z-score of plus one point five means one and a half deviations above it. And here is why this transformation is worth doing. Z-scores allow direct comparison across tests with different scales. Take a z of plus one on a vocabulary test. And a z of plus one on a math test. Those two represent identical relative performance. Even if the raw scores differ dramatically from each other.
The Ladder
From Z-Score to Instructional Decision
Z-scores map onto instructional decisions along a ladder. A z of minus three or lower is the zero point one percentile. That is extremely below average, and calls for immediate intervention. From minus two to minus three sits around the second to third percentile. That is well below average, and suggests a specialist referral. From minus one to minus two is below average, and warrants close monitoring. From minus one to plus one is the average range. That spans the sixteenth to the eighty-fourth percentile. Typical instruction is the appropriate response there. From plus one to plus two is above average, suggesting enrichment options. And plus two or higher is exceptionally above average. That is the ninety-eighth percentile and above, prompting gifted evaluation.
Worked Example
A Score of 78, Turned Into a Decision
Here is that ladder used on a real evaluation. A school psychologist administers a standardized intelligence test. The reported score is seventy-eight. The scale has a mean of one hundred and a standard deviation of fifteen. The special education team applies z-score logic. Seventy-eight minus one hundred is minus twenty-two. Divided by fifteen, that gives minus one point four seven. So the student sits one point four seven deviations below the mean. That is roughly the seventh percentile. Then comes the word that matters most in this example. Combined with other evaluation data, this contributes to a picture. A comprehensive picture informing eligibility discussions for services. The z-score located the score. It did not make the decision.
Not A Law
The Normal Curve Is a Model
Now the caution, which is the most important slide in this section. The normal curve is a model. It is not a law. It is a mathematical model describing many assessment outcomes. But it does not describe all of them. Classroom grades, for example, are often deliberately skewed. Most students pass, which is the point of teaching them. Mastery learning outcomes are J-shaped by design. Skewness is simply the asymmetry of a distribution. Positive skew means a long right tail. So use normal distribution logic only when data are approximately normal. And always inspect the distribution visually first. Before making any statistical inference from it.
How To
Using Z-Scores in Practice
To finish, the practical routine for using z-scores. They give you a universal language across different tests and scales. First, compute. Subtract the group mean from the student score. Then divide that difference by the standard deviation. Second, read the sign, which does a lot of work. A positive z indicates above-average performance. A negative z indicates below-average performance. Third, convert it for the conversation you are about to have. Use a standard normal table, or software, to get a percentile rank. That third step matters more than it looks. Z-scores and percentile ranks are complementary tools. The z-score is what you reason with. The percentile is what you say out loud.
About Educational Psychology at UPI Study
Educational Psychology (Psychology 120) is a self-paced online course of 100 video lessons in 11 chapters, from memory, conditioning and child development to motivation, individual differences, assessment, instruction and educational technology. It carries a NCCRS credit recommendation for 3 semester credits.
Every lesson transcript is free on pages like this one, and the videos are free with a free UPI Study account. Enrolling adds a practice quiz after each lesson, the graded work and final exam that earn the credit, lifetime access, and an official transcript on completion. UPI Study has helped over 130,000 students with college credits. ACE and NCCRS have over 2,100 cooperating colleges that will consider accepting credits; the final decision is with the universities.
Enroll now → Course details Download the syllabus All Psychology and social science courses Every course with PRO →
Why take it here
Why students take Educational Psychology with UPI Study
Where the credit goes
Universities that work with NCCRS
Educational Psychology carries a NCCRS credit recommendation. These universities work with NCCRS; some are UPI Study's signed partners. ACE and NCCRS have over 2,100 cooperating colleges that will consider accepting credits; the final decision is with the universities.
Thomas Edison State UniversitySigned partner
University of the PeopleSigned partner
Charter Oak State CollegeSigned partner
Strayer UniversitySigned partner
Columbia Southern UniversitySigned partner
Indiana TechSigned partner
Penn StateWorks with NCCRS
Southern New Hampshire UniversityWorks with NCCRS
SUNYWorks with NCCRS
+many more cooperating universitiesFind my college →Find my college → Not listed? Ask Athena in the corner of this page, or book a 15-minute call.
FAQ
Questions students ask us
About The Bell Curve and Standard Deviation: What the Numbers Tell Us
What is a normal distribution?
What is the 68-95-99.7 rule?
How do you calculate a z-score?
Are classroom grades normally distributed?
About the Educational Psychology course
How many college credits is Educational Psychology?
How much does Educational Psychology cost and what is included?
Which universities accept UPI Study credits?
How long does Educational Psychology take?
How are the exams done?
How do my credits reach my college?
Ready for the full course? Earn 3 credits in Educational Psychology.
100 video lessons, a quiz after each one, and the graded work that earns the credit. Recommended for credit by NCCRS.
3 credits · NCCRSEnroll →