Life expectancy, like most statistics, is an estimate which is subject to a margin of error. The accuracy of the results can be indicated by calculating a confidence interval which provides a range of values within which the true underlying life expectancy would lie (with 95 per cent probability).
The 95 per cent confidence intervals for life expectancy at birth are given in Table 6, Table 7 and Table 8, and are illustrated in Figure 1, Figure 2, Figure 3 and Figure 4 for Urban/Rural Classification, Deprivation Decile and Community Health Partnership areas within Scotland.
There is no simple ‘rule of thumb’ for the size of confidence intervals. But they largely depend on the size of the population, so confidence intervals for areas with small populations tend to be wider. It is also worth noting that life expectancy results in these areas can be affected by the random variation in the number of annual deaths. This means that the results can be erratic and vary from year to year.
More information about the methods used to calculate the standard errors and confidence intervals used in this report can be found in the Office for National Statistics methodology paper Life expectancy at birth: methodological options for small populations.