Reliability means that an experiment or test reports the same results after a repeated number of trials. Independent researchers must be able to replicate experiments using the same controls as the original researchers, making the research generalizable.
Clinical assessments are meaningful only in so far as they are reliable and valid, yet academic medical center rarely demonstrate the reliability of their assessments. When reported reliability is usually based on measurement obtained at on point in time. On the other hand, reliability is an essential component of validity and assessment validation and revision is a never-ending cycle. For ongoing assessments over extended time frames, real-time reliability computations may alert users to possible changes in the learning environment that are revealed by variations in reliability over time.
According to Greogory 2011, Reliability refers to the attribute of consistency in measurement. If a measure is reliable, it yields consistent results. There are four ways to estimate the reliability of a measure:
• Inter-observer: Is concluded when different testers rate the same information and yield consistent results.
• Test-retest: Is proven when the same instrument is measured at two different times, without intermediate intervention, and yield the same results.
• Parallel-forms: Exists when two different instruments designed to test the same material yield the same results.
• Split-half reliability: Occurs when test items are divided in half and yield the same results.
এতে সদস্যতা:
মন্তব্যগুলি পোস্ট করুন (Atom)
কোন মন্তব্য নেই:
একটি মন্তব্য পোস্ট করুন