SIPRI’s New Long Data-set on Military Expenditure: The Successes and Methodological Pitfalls

SIPRI has collected data on military expenditure almost since its foundation in the 1960s, but various historical difficulties led to breaks in the consistency of the data series, so that until recently SIPRI’s consistent military expenditure database has only provided data from 1988 onwards. This paper describes recent efforts at SIPRI that have succeeded in extending these consistent series for most countries back to at least the 1960s, and in some cases to 1949. It describes the underlying difficulties involved in collecting military expenditure data and ensuring consistent series, the sources used in the reconstruction of the long data-set, the methodological choices made, and the results of the exercise. Overall, consistent constant price data series have been extended back as far as 1957 for half of the countries covered by the SIPRI database that existed at the time. Europe and the Americas generally have the best data coverage. One of the biggest problems with the extended data-set is the extensive use of estimates to splice together overlapping, but disagreeing series for the same country, adjusting the older series upwards or downwards by an appropriate ratio to give greater consistency with the later series. A number of case studies are investigated where parallel series exist for countries, suggesting that this approach may in some cases involve significant margins for error.