Browning et al. (2013) model collective-household economies of scale in goods consumption by having each good be partly shared, instead of each good being public or private. We modify their model to achieve simple point identification and estimation of the economies of scale of consumption of each good, and we provide a new index of household level economies of scale. Our model has a linear form, permits households of varying composition, including children, and accommodates unobserved heterogeneity in both preferences and in the economies of scale of each good. We provide estimates using Canadian Surveys of Household Spending data.
We replicate the two foundational studies which proposed the two-tier stochastic frontier model, first in the cross-sectional setting and then for the fixed effects panel data model. We explore matters of software then and now, different mathematical formulations of the likelihood, and alternative current software tools. We also highlight several data issues that arose in both replications.
We investigate how school closures affect educational outcomes through parental responses. Using quasi-experimental variation in school-level closure days and linked administrative-survey data, we find that 10 additional closure days raise private tutoring expenditure by 4.1% and within-school test-score dispersion by 25%; over the average 53-day closure, low-income students lose 0.09 SD. To quantify substitution between schooling and parental investment and evaluate compensatory policy, we estimate a tournament model in which schooling and tutoring jointly produce test scores. Tutoring substitutes for in-person days, burdening low-income households disproportionately. Counterfactuals show a means-tested voucher fully offsets the resulting rise in inequality.
We replicate a study by K & auml;nzig (American Economic Review, 111 (2021), 1092-1125), who employs structural vector autoregressive techniques to examine the impact of changes in oil supply expectations on the price of oil and other macroeconomic aggregates. K & auml;nzig identifies an oil supply news shock by constructing a proxy from OPEC announcements about their production plans. As an alternative approach, we use non-Gaussianity and independence to identify structural shocks and find that one of them corresponds closely to K & auml;nzig's oil supply news shock, implying that the proxy is not necessarily needed to obtain a shock with the same characteristics.
We estimate the causal effects of the introduction of the minimum wage in Germany on the distributions of hourly wages, monthly earnings, and hours worked, combining rich large-scale data sources. We compare linear and non-linear versions of distribution regression difference-in-differences (DR-DiD) and also estimate bivariate DR-DiD. We show that the introduction of the minimum wage in 2015 led to shifts in low hourly wages around the minimum wage threshold including spillover effects up to 50%-70% above. We present evidence for working hours effects in different parts of the hours distribution, though the magnitudes are small. The minimum wage explains a sizeable share of the recent fall in wage and earnings inequality. We show that groups that were later more strongly affected by the minimum wage already experienced higher wage growth before the introduction, leading to an overestimation of minimum wage effects if not accounted for.
