On the usability of RAS in manpower forecasting: An evaluation based on Indian data

Abstract

Projection of changes in the occupational structure is vital for ensuring accurate manpower forecasts. Yet this is seldom attempted in a rigorous way. One of the main difficulties which a manpower planner faces—especially in a developing economy—is the paucity of reliable time series data on the occupational pattern of employment. Given this constraint, it is maintained that it is futile to consider experimentation with sophisticated statistical forecasting techniques whose data requirements may be difficult to fulfil. The RAS, on the other hand, is a relatively simple technique which has been extensively used in adjusting matrices in diverse fields with only a given initial matrix and the row and column totals for another year. This is the first detailed application of the RAS to Indian occupational data. Our results confirm the potential usefulness of the RAS as a basis for approximating temporal changes in the occupational structure. Specifically, it is demonstrated here that as compared with the errors in occupational forecasts which would result from the assumption of an unchanging occupational structure, those associated with the RAS are markedly lower. The paper concludes by pointing out that, when detailed data become available, more flexible forms of the RAS which allow for the possibility of departures from biproportionality may be utilised.