January 16, 2012
Reliability and Validity
Evaluating human services is a task that can be very complex. People can have different interpretations of the same event. Another concern is that people are not always honest. Therefore, human services will gain from effective, high quality evaluations of data collection methods. This requires that the data collection methods supply accurate and dependable information. This paper will define and describe 2 concepts of measurement known as reliability and validity,-provide examples and supporting facts as to how these concepts apply to data collection in human services, and evaluate the importance of the validity and reliability of data collection methods and instruments. Funding for many non-profit human services organizations are dependent on the precise results of research and statistics gathered through various processes of data collection. Reliability and validity are two criterions that are used to judge the functions of research designs and measurements. These criterions are something that should be looked at before, during, and after research to show the relevance and significance of human services. Using the example of a weight scale is the perfect way to confer the idea of reliability and validity. If an individual of 150lbs. weighs themselves several times and gets several different readings, the scale being used can be considered unreliable. Now if that scale also reads 125 each time, it is rather reliable but invalid. However, the consistent, accurate reading of 150lbs. each time indicates that this scale is not only reliable, but also valid. When thinking about validity, it is important to evaluate if the research is doing what it is supposed to do. According to Rosenthal and Rosnow (2008), “The measure in question might be a psychological test of some kind, a group of judges who rate things, a functional MRI scanner for monitoring...