Obviously, a measure should be more reliable and valid. It is possible, however, to have a test or measure that meets one of these criteria and not the other. Think for a moment about how this might would occur. Can a test be reliable without being valid? Can a test be valid without being reliable? To answer these questions, imagine that you are measuring in a group of individuals with a “new” intelligence test. The test is based on a rather ridiculous theory of intelligence, which states with the larger your brain, the more intelligent you are. The theory also assumes that the larger your brain, the larger your head is. Thus, you are going to measure intelligence by measuring head circumference. You gather a sample of individuals and measure the circumference of each person's head. Is this a reliable measure? Many people immediately say no because head circumference seems like such a laughable way to measure intelligence. But remember, reliability is the measure of consistency, not truthfulness. Is this test going to consistency measure the same thing?

Yes, it is consistency measuring the head circumference, which is not likely to change over the time. Thus, your score at one time will be the same or very close to same as you later. The test is therefore very reliable. Is its valid measure of the intelligence? No, the test in no way measures the construct of the intelligence. Thus, we have established that a test can be reliable without being valid. However, because the test lacks validity, it is not good measure. Can the reverse be true? In other words, can we have a valid test (a test that truly measures what it claims to measure) that is not reliable? If a test truly measures intelligence, individuals will score about the same each time they took it because intelligence does not vary over much over time. Thus, if the test is valid, it must be reliable. Therefore, a test can be reliable but not valid, but if it is valid, it is by default reliable.