Validity and Reliability of Online Buyer’s Anxiety Scale

This study was designed to test the validity and reliability of buyers’ anxiety scale of online buying. Data were collected from 250 respondents using self-reported anxiety questionnaires designed by researchers. The instruments tested consisted of two types of measurement scales, namely ASAOB-1 with five scales, from Never Experience with a score of 1 to Always with a score of 5. The second scale type named ASAOB-2 also uses a five-point scale to measure the level of anxiety, from Very Low (1) to Very High (5). The collected data were simulated using factor analysis to obtain the loading value as a measure of validity, while the reliability coefficient uses Cronbach’s Alpha. Simulations were carried out in stages using subjects as many as 25%, 50%, 75%, and finally 100% of the total respondents. The proportion of subjects used in the simulation is determined arbitrarily. Simulation results show that there are a number of items of which the level of validity decreases when the number of cases increases. In general, the numbers of validity show fluctuations, and they are not linear with the number of cases used for testing. The Alpha Cronbach’s coefficient is also not linear with the number of cases used in testing. From these findings, it is indicated that the indices of validity and reliability are not linearly related to the number of cases used.