Understanding the Psychometric Testing of a Measuring Instrument in Business Research

Abstract

The purpose of this paper was to understand the issues involved in the psychometric testing of a measuring instrument in business research. The two most important testing tools for measuring instrument are validity and reliability. Validity refers to whether a measuring instrument is measuring what it purports to.Three types of validity were discussed in this paper: (]) transaction validity, which assesses how well the measuring instrument samples the content domain being measured; (2) criterion validity, which assesses how well the measuring instrument correlates with other measures of the co nstn1ct of interest; and (3) construct validity, which assesses how well the measuring instrument represents the construct of interest. How consistently does the measuring instrument measures whatever it does measure? This is the issue of reliability. Reliability is the degree to which the measuring instrument is dependable, consistent and replicable overtime, over the instn1ments and other groups of respondents. Three types of reliability were discussed in this paper:(]) reliability as stability is a measure of consistency over time and over similar samples. (2) reliability as equivalence : If equivalent forms of a measuring instrument yield similar results , then the measuring instrument can be said to demonstrate this form of reliability and (3) reliability as internal consistency which examines the inter-item correlations within a measurement device and indicates how well the items fit together conceptually.