The real minimum wage and unemployment by educational attainment, age, ethnicity and race

There have been a large number of studies attempting to quantify the effect of a minimum wage on unemployment.  Earlier studies tended to emphasize the correlation of teenage employment with the minimum wage using various types of time series or panel data.  The conclusions of these studies while far from uniform tend to indicate that the elasticity of teenage employment relative to the minimum wage is somewhere in the -0.1 to -0.3 range.  Several investigations have chosen to use a case study approach where a specific, low-wage industry is examined before and after a change in the minimum wage.  Card and Krueger’s paper on the fast food industry in the adjoining states of New Jersey and Pennsylvania is one of the best known studies of this type.  It is notable in that they found a positive relationship between a rising minimum wage and employment.

This research uses modern time series analysis to examine the effects of the minimum wage on several subcategories of the population.  A VAR framework consisting of three variables--the real national minimum wage, labor force participation and unemployment--is constructed.  Each series is tested for stationarity and the system is tested for cointegrating vectors.  Finally, impulse response functions are used to simulate the effect of an increase in the minimum wage on unemployment and labor force participation.  Monthly data from the Current Population survey are used to create these series for several categories of workers depending on age, education, race and ethnicity. This approach allows the model to predict the effect of the minimum wage on each of these different categories of workers.