1 Answer | Add Yours
Validity and reliability are issues that often come up in social sciences research. They are particularly important with regard to standardized tests and other tests of academic achievement. Both are important, but they are different things.
Reliability is a measure of how well the results of a test or experiment could be replicated. In the context of an academic test, this would refer to whether a group of people who all knew the same amount would all get very similar scores on the test. If your sample of test-takers all had the same knowledge and yet their scores varied widely, your test would not be reliable.
Validity has to do with how well your test or experiment actually measures what it is supposed to measure. This is a major concern with standardized tests like the SAT. They are supposed to measure how well-prepared a person is for college and how well that person will do in college. But many people argue that they actually only measure things like how well the person has been trained to take the test. If this is true, the SAT is not valid because it does not really test the attribute (college readiness) that it purports to measure.
We’ve answered 319,627 questions. We can answer yours, too.Ask a question