What went wrong with irelands recent post-censal population estimates

Abstract

The preliminary results of the 1979 Census (Ireland, 1979) indicated that the population was nearly 3.0 per cent greater than had been expected on the basis of the annual estimates of the population which were issued by the Central Statistics Office (CSO) for the years 1972 to 1978. The errors of closure for the years preceding each of the postwar censuses since 1951 are given in Table 1 from which it will be seen that the percentage error in 1978 was over twice as great as the previous largest error in 1950 and over five times as great as the average error for the years from 1950 to 1970.1international comparisons of errors of closure are given by Shryock et al. (1971, p. 106) and these show that the errors ranged from 1.1 per cent for West Germany in 1950 and 0.17 per cent for England and Wales in 1951 to 0.06 per cent for Australia in 1961. These figures and those shown in Table 1 indicate that there has been a significant deterioration in the relia-bility of Ireland's recent postcensal population estimates. Since reliable annual population estimates are needed by policy makers and planners, amongst others, to assist them in the preparation and evaluation of their programmes, it is important to know what went wrong with the recent estimates so that those who use them are alerted to possible sources of error in future estimates.