Psychometric test has been developed to measure mental characteristics of a person so it literally means measurement of the mind (S. Hammond, 1993). It is a psychological test which is made up from a collection of items (Paul Kline, 1998). These items are questions or statements which are usually answered with ‘Yes’ or ‘No’ or with the Likert scale (strongly disagree or strongly agree).
According to Sean Hammond (1993) there are problems that psychologist confront during research which is measurement. Due to lack of direct access to the mental characteristics, psychometric has developed a detailed set of procedures and models for statistics estimation. In essence, these procedures rely on the presences of indicators (which may be viewed as the items or questions).
Enormous work has been made by psychometrists in attempt to overcome the difficulties of measuring psychological variables. There are three essential criteria for a good psychometric test which are reliability, validity and standardisation. Test standardisation ensures that the conditions are as similar as possible for all individuals who are given the test. Standardisation also ensures that no matter who gives the test and scores it, the results should be the same. Reliability is a test that must measure the same thing in the same way every time someone takes it. There are two types of test reliability: Internal consistency reliability and Test–retest reliability.
The reliability analysis depends on the individual items which make up the test. Hypothetically, the researcher makes a test reliable with as small a number of items as possible. In order to regulate the relative contribution of each item into the overall test, reliability analysis is carried out. There are different ways in which this analysis would be conducted which are Cronbach’s Alpha and Standardized Alpha