Looking for a Needle in a Haystack? A Structural Time Series Model of the Relationship Between Teenage Employment and Minimum Wages in the United States

The work of Card and Krueger has cast doubt on the nature of the relationship between the minimum wage and teenage employment. The earlier "consensus" finding of a small but statistically significant negative effect was based on time series data whereas Card and Krueger's findings are based mainly on cross section data. In this article, we re-examine the time series relationship between minimum wage and teenage employment. We find that previous models break down due to their inability to capture changes in the trend, cyclical and seasonal components of teenage employment. We propose a structural time series model in which these components are treated as stochastic components and which contains the traditional approach as a special case. The model when estimated up to 1979 accurately predicts what happens to teenage employment subsequently, when the minimum wage was frozen after 1981 and then increased quite substantially in the early 1990s. Moreover, we find that there is a significant, negative effect of the minimum wage on teenage employment and its size and significance have hardly changed during the 1980s and early 1990s. Finally, the model remains robust in an out-of-sample test for 1993-99 containing two further minimum wage hikes.