PSYC 3250 Lecture Notes - Lecture 9: Standard Deviation, Nomological Network, Thomson To7
8 Dec 2015
School
Department
Course
Professor
Document Summary
Some items are better than others at measuring the attribute in question. Part of test development is choosing the best items for your final test. A loosely structured group of statistics that can be computed for each item in a test. The exact choice and interpretation of the statistics that make up an item analysis are determined by the purpose and nature of the test and the test developer"s objectives. An item analysis can show why a test is reliable (or unreliable) Can suggest ways of improving the measurement characteristics of a test. In psychometrics, difficulty is defined in terms of the number of people who answer each test item correctly. E. g. if everyone chooses the correct answer, the item is defined as easy; if 1 person in 100 answers it correct, the item is defined as difficult. Item-difficulty index: percentage of examinees who answer the item correctly pvalue for item= number of people answering theitem correctly.
