eScholarship Repository eScholarship Repository California Digital Library
eScholarship > IIR > IIRWPS > Paper iirwps-166-08

IRLE Papers

IRLE Website

Policies

Search IRLE

Submit a Paper

Notify me of new papers

institute_logo

UCIAS
Institute for Research on Labor and Employment
University of California, Berkeley

IRLE Papers  •  IRLE Website  •  Policies  •  Search IRLE  •  Submit a Paper

Do Minimum Wages Really Reduce Teen Employment? Accounting for Heterogeneity and Selectivity in State Panel Data
Sylvia Allegretto, University of California, Berkeley
Arindrajit Dube, University of California, Berkeley
Michael Reich, University of California, Berkeley

June 28 Revision.

Download the Paper (238 K, PDF file) - June 28, 2008 Tell a colleague about it.
Printing Tips: Select 'print as image' in the Acrobat print dialog if you have trouble printing.

ABSTRACT:
Traditional estimates of minimum wage effects on employment include controls for state unemployment rates and state and year fixed-effects. Using Current Population Survey data, we show that such estimates often are biased and that the estimates vary ith the source of identifying variation. Without sufficient controls for heterogeneous employment patterns that would occur without minimum wage policies, traditional estimates vary substantially both in sign and magnitude depending on time period and hence with the selectivity of states with minimum wage hikes. Estimates without sufficient controls also vary across demographic groups in a counterintuitive manner that suggests misspecification problems. To account for heterogeneous employment patterns and selectivity among states with minimum wages, we include controls for long-term growth differences among states by using a state-specific linear trend, and controls for heterogeneous responses to economic shocks by including Census division-specific time effects. In the 1990 to 2006 period, including these controls reduces the magnitude of the estimated employment elasticity from -0.168 (significant at the 1 percent level) to -0.024 (not significant). Although the division and state trend controls do not constitute a panacea, they do provide important tools to mitigate the bias that results from unobserved spatial heterogeneities in employment patterns that are correlated with the minimum wage. Since estimates in most previous national-level studies insufficiently address this issue, economists’ estimates of minimum wage effects must be revised accordingly.

SUGGESTED CITATION:
Sylvia Allegretto, Arindrajit Dube, and Michael Reich, "Do Minimum Wages Really Reduce Teen Employment? Accounting for Heterogeneity and Selectivity in State Panel Data" (June 28, 2008). Institute for Research on Labor and Employment. Institute for Research on Labor and Employment Working Paper Series. Paper iirwps-166-08.
http://repositories.cdlib.org/iir/iirwps/iirwps-166-08

 
bar
Open Archives Initiative eScholarship is a service of the California Digital Library bepress