A valid language test for university entry, for example, should include tasks that are representative of at least some aspects of what. For example, a valid driving test should include a practical driving component and not just a theoretical test of the rules of driving. If such a ruler existed it would be an interesting conversation piece, but as a measuring instrument it would be a miserable failure. Validity refers to whether a test measures what it aims to measure. Before you decide that your imaginary uncle is a tightwad, I should tell you that the ruler is made of an extremely rare wood with an interesting property – the wood shrinks and expands randomly – not according to humidity or temperature or day of the week, but randomly. Imagine that you have a rich uncle who has just returned from a cruise to an exotic country, and he has brought you as a souvenir a small ruler – not a pygmy king, but a piece of wood with markings on it. These two properties, reliability and validity, are the focus of this chapter. The major focus is on a logical understanding of the concepts, as well as an applied understanding through the use of various statistical approaches.Įvery measuring instrument, whether it is a yard-stick or an inventory of depression, must have two properties: the instrument must yield consistent measurement, i.e., must be reliable, and the instrument must in fact measure the variable it is said to measure, i.e., must be valid. ![]() These two properties are defined and the various subtypes of each discussed. ![]() ![]() AIM This chapter introduces the concepts of reliability and of validity as the two basic properties that every measuring instrument must have.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |