ABSTRACT
This unit provides an overview of the concept of error, defining both systematic and random error and explaining the relevance of each to understanding the limitations of research as well as categorizing the steps to reduce (but never eliminate) error. The specific ideas of reliability and validity are addressed, including a discussion of internal and external validity. Mechanisms for evaluating measurement validity are defined, including test-retest, item-total, and parallel-forms. Typologies of measurement validity are presented, with detailed descriptions of content, construct and criterion validity. Steps to evaluate validity are described, along with the process for evaluating the reliability of an index and the importance of indexes in minimizing random error.
