ABSTRACT
Reliability concerns the consistency of test scores and the extent to which measurements are repeatable when different persons make the measurements, on different occasions, and using different instruments that are intended to measure the same construct. Measures of reliability indicate the amount of measurement error in a set of scores. Interrater or interscorer reliability refers to the consistency of test scores when they are determined by different examiners. Altemate-form reliability refers to the consistency of test scores for two forms of the same test. Altemate-form reliability is useful if a person must be tested twice and a learning or practice effect is expected. Understanding the various types of reliability and their respective purposes can help the test developer design the reliability research for the test. Traditionally, when the data are interval or ratio and score distributions are approximately normal, one of the most common statistics used for calculating reliability is the Pearson product-moment correlation coefficient.
