Reliability A test must be reliable, that is, it must have the ability to consistently yield the same results when it is repeatedly administered to the same individuals under the same conditions. For example, if an individual record his/her responses on various items of a questionnaire and thus provides a certain type of information, he/she should provide approximately the same type of responses when the questionnaire is administered to him/her on the second occasion. If an achievement test is administered to learners and then re-administered after .a gap of fifteen days without any special coaching in that subject, within these fifteen days, the learners must show a similar range of scores on the administration of the test. The repeated measure of an attribute, characteristic, or trait by a tool may provide different results. They may be due either to a real change in the individual's behavior or to the unreliability or inconsistency of the tool itself. It varies from sample to sample. It does not give the same or fixed result in varied situations. It is affected by the variance of scores. It is the correlation of scores on the testing tool itself. The results in terms of two sets of measures obtained by the use of the tool are correlated to measure the level of reliability. If the variation in the results is due to a real change in behavior, the reliability of the tool is not to be doubted. However, if the variation is due to the tool itself, then the tool is to be discarded. There are various procedures to assess the reliability of a test. These include (i) the test-retest method, (ii) the alternate or parallel-form method, (iii) the split-half method, and (iv) the rational equivalence method.