What is the meaning of the concepts of standardisation, reliability and validity applicable to psychometric testing?
_____________________________________
Standardisation
- to enable an employee’s scores on a test to be meaningfully interpreted, the test is to be standardised on a population similar to that on which it has been designed to be used (e.g. in respect of 15 FQ+P, people with a wide range of technical, managerial, professional, sales and administrative/clerical roles)
- such standardisation ensures that the scores obtained in a test can be meaningfully interpreted by referring them to a relevant distribution of scores
Reliability
- in essence, reliability refers to the requirement that a test must consistently measure a construct
- reliability is generally assessed using one of two different methods, namely –
- assessing the stability of the test’s scores over a time period: referred to as temporal stability – it involves determining the extent to which a group of people obtain similar scores on a test when it is administered at two different points in time
- internal consistency – this method of assessing a test’s reliability involves determining the extent to which, if people score one way on one item (i.e. respond to one item in an introverted way) they will respond in the same way to other items in the test that measure the same construct (i.e. respond in an introverted manner to other test items)
Validity
- this refers to the requirement that the test should measure what it claims to measure
- in this regard, there are two approaches, namely:
- construct validity – by utilising this requirement, the test is required to demonstrate that it correlates with other major tests which measure related constructs but does not correlate with tests that measure different constructs
- criterion validity – the validity of a test in terms of this method involves demonstrating that the test meaningfully predicts some real-world criteria (e.g. a valid test of extroversion might be expected to predict success in sales roles, while a valid test of consciousness might be expected to predict success in administrative roles)
