Skip to main content

Estimation and inference of distributional partial effects: Theory and application (Shen, 2019)

Review Guidelines

Absence of conflict of interest.

Citation

Shen, S. (2019). Estimation and inference of distributional partial effects: Theory and application. Journal of Business & Economic Statistics, 37(1), 54–66.

Highlights

  • The study’s objective was to examine the impact of an increase in the state-level minimum wage on household earnings. 

  • The study is a nonexperimental comparison group analysis. The study used outcome data from the Current Population Survey (CPS) and a statistical model to compare the household earnings of households at the minimum wage to households making more than the minimum wage two years after a minimum wage increase.  

  • The study found that a small increase in the minimum wage was associated with higher household earnings for households earning the minimum wage, but not for all households earning more than the minimum wage. 

  • The quality of causal evidence presented in this report is low because the author did not ensure that the groups being compared were similar before the intervention. This means we are not confident that the estimated effects are attributable to the minimum wage increase; other factors are likely to have contributed. 

Intervention Examined

Minimum Wage Increases

Features of the Intervention

The study examines the effects of an increase in the state-level minimum wage (that exceeds the federal minimum wage) on the earnings of U.S. households. The average minimum wage increase in the period studied, from 1981 to 2008, was about 7.5 percent.  

Features of the Study

The study is a nonexperimental comparison group analysis. The study included 292,698 U.S. households from 1981 to 2008 with no more than two adults, and with a head of household who was between ages 18 to 64. The study compared the effects of minimum wage increases on 32,696 minimum wage–earning households (the treatment group) and 260,002 households that earned more than the minimum wage (the comparison group) in this period. Minimum-wage households were defined as those that rely substantially on income from a minimum wage earner; specifically, households with an earner making less than 120 percent of minimum wage in which these minimum wage earnings accounted for at least 20 percent of the total household income. The study used data from the CPS describing household earnings and information collected from other sources describing minimum wage laws in the United States. The author used a statistical model to compare the household earnings two years after minimum wage hikes between these two groups.   

Findings

The study found that a small increase in the minimum wage was associated with improved household earnings for households earning the minimum wage, but not for all households earning more than the minimum wage. A larger increase in the minimum wage (of at least 7.5 percent) was not associated with improved household earnings for any households. 

Considerations for Interpreting the Findings

The author does not present information about the pre-intervention characteristics or pre-intervention trends in household earnings for treatment and comparison group members. These preexisting differences between the groups—and not the minimum wage increases—could explain the observed differences in outcomes. 

Causal Evidence Rating

The quality of causal evidence presented in this report is low because the author did not ensure that the groups being compared were similar before the intervention. This means we are not confident that the estimated effects are attributable to the minimum wage increase; other factors are likely to have contributed. 

Reviewed by CLEAR

May 2021

Topic Area