Response to Replication of Examining Inequality in the Time Cost of Waiting

Holt and Vinopal (2023) provides evidence of an income-based gap in time spent waiting for services on the typical day in the United States. The gap was estimated at the extensive margin, unconditional intensive margin, and intensive margin conditional on some waiting time. The analysis was complemented with a heterogeneity assessment that found the income-based gap in the length of waiting spells conditional on some waiting was observed across race categories except Black Americans. Unfortunately, Hall and Thiele identified an error in the code regarding missing household income data that led to a larger analytic sample than was warranted. In addition, Hall and Thiele claim some sensitivity in the hypothesis tests of some results to an expanded definition of the dependent variable and standard error estimation choice. However, correcting our original coding errors regarding missing income, adding weights when omitted, and adding controls when omitted does not meaningfully alter the estimated coefficients or their precision. Hall and Thiele's claims that our race results are not robust is misleading, as they seem driven by interpretation of simplified and space-constrained writing in the abstract, rather than lack of reproduction or sensitivity of the empirical results. To the extent we observe some sensitivity, it involves Hall and Thiele's move to an expansive definition of waiting time to include more leisure and entertainment services, a change that substantially alters the interpretation of results and goes beyond a simple test of robustness.