National accounts estimation using indicator ratios

We propose a new approach to national accounts compilation, which also serv es as a formalization of current compilation practices. When formalizing th e procedure, a distinction is made between (basic) data, national accounts identities and so-called indicator ratios. The latter are ratios of or perc entage relations between national accounts variables, such as the relation between output and value added. Indicator ratios are currently used in nati onal accounts compilation practices in order to make adjustments to the bas ic data or to fill in missing data. The latter use is particularly relevant when basic data are scarce, which is the case not only in many developing countries, but also in developed countries when annual accounts are compile d for recent periods. The (basic) data, indicator ratios and identities tog ether are used in a Bayesian approach to estimate the values of national ac counts variables and analytical indicator ratios based thereon. The amendme nt of the current practices consists in introducing reliability intervals o f basic data and indicator ratios, which allows for the use of a much large r number of indicator ratios in the compilation and checking of national ac counts data. The Bayesian compilation approach makes it possible-in contras t to current practices-to use indicator ratios both as priors and as analyt ical indicators.