Aggregation and Weightage Issues Concerning Composite Index Development: Experience with Digital Divide of Asian Countries

Abstract

The term ‘digital divide’ refers to the gap between individuals, households, businesses and geographic areas with regard to both their opportunities to access Information and Communication Technologies (ICT) and to their use of the Internet. Several initiatives have been taken by various international bodies to address the multifarious dimensions of digital divide. However, there is a little consensus about the different measurement aspects of digital divide. The paper attempts to measure the composite Digital Divide Index of Asian countries using different techniques of weighting and aggregation. More specifically, four weighting techniques viz. Iyengar-Sudarshan Method, Benefit of Doubt Method, Principal Component Analysis and Unobserved Component Model and three techniques of aggregation viz. Linear Aggregation, Geometric Aggregation and Weighted Displaced Ideal Method are used. These different combination of weighting and aggregation techniques resulted to twelve types of composite indicators of digital divide. Based on the values of these indices, the countries are ranked. Spearman’s rank correlation coefficient is calculated to understand the parity between the ranks obtained through the different indices. Finally, Pareto ordering is used to find out the index which is most compatible with the other combinations. It is found that the index formed combining the Unobserved Component Model and Linear aggregation is most compatible than the other indices.