Item Analysis - A Primer On Psychology

Item is a statement in the form of a question. Item analysis is one of the most important aspects of test construction.

Item analysis is a general term for a set of methods used to evaluate test items.

Items can be analyzed qualitatively in terms of their content and form and quantitatively in terms of their statistical properties. 

Importance of item Analysis:

The items represents the test. All the things of a test depend on items. The importance of item analysis is given below:

1. There can be little doubt that item analysis is a vitally important operation in the development of a new test and one that should invariably be carried out unless special circumstances.
2. Both the validity and reliability of any test depend ultimately on the characteristics of its items. High reliability and validity can be built into a test in advance through item analysis.
3. Tests can be improved through the selection, substitution or revision of items.
4. Item analysis makes it possible to shorten a test and at the same time to increase its validity and reliability.

Methods of computing item analysis:

There are two basic methods of item such as Item difficulty and item discrimination. These two are described in the following:

1. Item Difficulty index: For testing purposes, the difficulty of an item is defined in terms of the percentage or proportion of persons who answer it correctly. The easier the item, the larger this percentage will be.

It is customary to arrange items in order of difficulty so that test-takers begin with relatively easy items and proceed to items of increasing difficulty.

In the process of test construction, a major reason for measuring item difficulty is to choose items of suitable difficulty level.

Items that are too easy or too difficult do not affect the variability of test scores, they contribute nothing to the reliability or validity of the test. The closer the difficulty of an item approaches 1.00 or 0, the less differential information about test-takers it contributes, conversely the closer the difficulty level approaches .50 the more differentiations the items can make.

Items within a test tend to be inter-correlated, the more homogeneous the test, the higher these intercorrelations will be. Moreover, the higher the item inter-correlations, the wider should be the spread of item difficulty.

Up and LP designate the numbers of examinees in the upper and lower groups, .respectively, who pass the item, whereas U is the total number of examinees in the upper (or lower) group. The value of p is referred to as an item easiness index (or item difficulty index). To illustrate the computation of these indexes, assume that 50 people take a test. Then the upper and lower groups can be formed from the top 14 and bottom 14 examinees on a total test score. If 12 of the examinees in the upper group and 7 of those in the lower group pass item A, the p = (12 + 7)/28 = .68

2. Item Discrimination index: Item discrimination refers to the degree to which an item differentiates correctly among test-takers in the behavior that the test is designed to measure.

The extreme group method is used to calculate item discrimination. The upper group is made up of 25%-33% who are the best performers and bottom is 25%-33% who are poorest performers respectively. The most appropriate percentage is to use the top and bottom 27% of the distribution.

The higher the discrimination, the more the item discriminates.

Up and LP designate the numbers of examinees in the upper and lower groups, .respectively, who pass the item, whereas U is the total number of examinees in the upper (or lower) group. The value of D is referred to as an item discrimination index. And D = (12 — 7)/14 = .36.

Reference:

Anastasi, A. (1982). Psychological testing. New York: Macmillan.

Share this:

• X
• Facebook

Like Loading...