This paper analyzes the relationship between aggregate wages and individual wages when there is time series variation in employment and in the dispersion of wages. A new and easily implementable framework for the empirical analysis of aggregation biases is developed. Aggregate real wages are shown to contain three important bias terms: one associated with the dispersion of individual wages, a second reflecting the distribution of working hours, and a third deriving from compositional changes in the (selected) sample of workers. Noting the importance of these issues for recent experience in Britain, data on real wages and participation for British male workers over the period 1978-1996 are studied. A close correspondence between the estimated biases and the patterns of differences shown by aggregate wages is established. This is shown to have important implications for the interpretation of real wage growth over this period.