Assessment Education Perspectives

Making Sense of Assessment Results – Defining Three Basic Measurement Concepts

Defining Three Basic Measurement Concepts - Making Sense of Assessment Results

Our mantra here at is just that – making sense of assessments and understanding and interpreting the data to help improve student learning. While data literacy is certainly important when it comes to statistical analysis and psychometrics, for teachers, assessment data can often become cumbersome to parse and connect back to instructional strategies.

Understanding a few key data measurement concepts can help teachers and educators improve their comfort level when it comes to communicating assessment data and how it translates into student learning.

  1. Measurement Scale. Measurement scales are most often used to pin point how well a student understands a body of content covered on a test. In general terms, the content from curriculum standards is assigned a level of difficulty on the scale. Students are then given a scale score based on the average difficulty of the questions that they answer. This can help teachers potentially group students based on similar instructional needs.
  1. Mean and Median. Both of these are also known as Measure of Central Tendency, the keyword here being ‘central’, as the mean and median are used to describe the center of a set of data. The mean is the method of communicating the average of set of numbers and the median is the middle number in a given set. Together, these pieces of information can help teachers identify trends and shape comparisons between groups, which can help inform grading and summaries of student performance towards targets.
  1. Standard Error of Measurement. Many factors can influence the way a student will ultimately perform on an assessment; confidence in the subject matter certainly, but also how they slept the night before, what they had for breakfast that morning, or even the weather. Give the same student the same test on different days and you’ll likely see that they will perform differently – better or worse – from the first test to the second. The variation in these two test scores is described as the Standard Error of Measurement.

Having a Standard Error of Measurement associated with a test score can help a teacher determine the level of confidence in that score. This helps teachers understand a student’s true understanding of subject matter despite an uncharacteristically low score on a particular test.

Understanding and interpreting assessment data – or data literacy as we like to call it – is an important step in assessment literacy. While there are some that think that students are over-tested, making good use of assessment data can help allay this thinking.