Leonard Goff

Welcome! I am an assistant professor of economics at the University of Georgia. My research is primarily in applied econometrics and in labor economics, and I also have interests in environmental and public economics.

I recently obtained my PhD in economics from Columbia University, and previously studied physics and philosophy at the University of British Columbia and the University of Maryland.

You can reach me at leonard.goff@uga.edu.


Working Papers

  • Treatment Effects in Bunching Designs: The Impact of the Federal Overtime Rule on Hours
    • [Supplemental Material]
    • Abstract: The Fair Labor Standards Act (FLSA) mandates overtime premium pay for most U.S. workers, but a lack of changes to the rule has left limited opportunities to assess its impacts on the labor market. This paper uses bunching at 40 hours to estimate the effect of the FLSA overtime rule on hours of work, leveraging an extension of the ``bunching design'' identification strategy and a large sample of weekly paychecks. I develop a nonparametric approach to using bunching at a choice-set kink that partially identifies the average causal effect of the kink among bunchers, under weak assumptions on choice. The bounds are informative in the overtime context and suggest that directly affected hourly workers in the U.S. work an average of at least half an hour less per week as a result of the FLSA mandate. This also delivers new estimates of the wage elasticity of hours demand.
  • Identifying the buncher LATE

  • A Vector Monotonicity Assumption for Multiple Instruments
    • [Supplemental Material]
    • Abstract: When a researcher wishes to use multiple instrumental variables for a single binary treatment, the familiar LATE monotonicity assumption can become restrictive: it requires that all units share a common direction of response even when different instruments are shifted in opposing directions. What I call vector monotonicity, by contrast, simply restricts treatment status to be monotonic in each instrument separately. This is a natural assumption in many contexts, capturing the intuitive notion of "no defiers" for each instrument. I show that in a setting with a binary treatment and multiple discrete instruments, a class of causal parameters is point identified under vector monotonicity, including the average treatment effect among units that are responsive to any particular subset of the instruments. I propose a simple "2SLS-like" estimator for the family of identified treatment effect parameters. An empirical application revisits the labor market returns to college education.

Work in Progress

  • The Career Impact of First Jobs: Evidence and Labor Market Design Lessons from Randomized Choice Sets
  • Do Firms Fully Exploit Their Labor Market Power in Setting Wages? Evidence from Canada
  • Interactions Between Family and School Environments: Evidence on Dynamic Complementarities?
  • Identifying Compensating Variation from Subjective Reports


Outside of economics:

Curriculum Vitae

Teaching Materials

Statistics for Econometrics (Fall 2021; UGA ECON8070)

  • Class notes: [PDF]

    Senior Honors Thesis Workshop (Fall 2019; Columbia ECON GU4999)

    (Professor: Michael Best)

    Microeconometrics (Fall 2018; Columbia ECON GR6414)

  • Code

    Visit my Github

    Some software projects:

    Stay a while...

    This is a Javascript adaptation of an old game called "It's Hexed" by the Kohner toy company. See if you can find one of the 2,339 ways to fit all 12 shapes into the box without overlap! Double-click to rotate a piece. Powered by KonvaJS.

    If you're accessing this site on a phone, the game will probably work better here.