Classical Test Theory

This theory provides a formula for calculating the amount of error contained in a test. It is often assumed that tests automatically provide a true score that demonstrates an accurate assessment of a person’s knowledge. This is not true as all tests contain some amount of error. The following formula provides a way of determining if an assessment tool is reliable and how much error is contained within.

Observed score= true score + error

As a teacher I will be creating assessment tools and testing the students. This formula will allow me to see the error contained in my testing instruments. This will also allow me to reduce the amount of error in order to assess the students more effectively. By creating effective testing tools I will be able to see what information will need to be reviewed and where students are excelling and struggling.



If I create a test and then use this formula I will be able to assess the error of the instrument. This will allow me to reduce the error by pin pointing the error in the tool. I may need more specific directions, more challenging questions, changed wording on questions, a more thorough review of material, etc. in order to make the test more accurate.

If I was to give a test and notice a high rate of error I should change the test and provide students with the opportunity to take the test again. The less error that is contained within the test the more accurately the assessment of student knowledge will be.