Primary: (Applied) Econometrics, Labor Economics
Secondary: Economics of Digitization
We examine the impact of household access to the internet on job finding rates in Germany during a period (2006-2009) in which internet access increased rapidly, and job-seekers increased their use of the internet as a search tool. During this period, household access to the internet was almost completely dependent on connection to a particular technology (DSL). We therefore exploit the variation in connection rates across municipalities as an instrument for household access to the internet. OLS estimates which control for differences in individual and local area characteristics suggest a job-finding advantage of about five percentage points. The IV estimates are substantially larger, but much less precisely estimated. However, we cannot reject the hypothesis that, conditional on observables, residential computer access with internet was as good as randomly assigned with respect to the job-finding rate. The hypothesis that residential internet access helped job-seekers find work because of its effect on the job search process is supported by the finding that residential internet access greatly increased the use of the internet as a search method. We find some evidence that household access to the internet reduced the use of traditional job search methods, but this effect is outweighed by the increase in internet-based search methods.
Estimating Causal Effects in Binary Response Models with Binary Endogenous Explanatory Variables
By means of a simulation study, this paper compares different estimators used in the past to estimate a binary response model (BRM) with a binary endogenous explanatory variable (EEV). It also provides guidance on how the average structural function (ASF) can be used in such a setting to estimate average partial effects (APEs). The (relative) performance of five different linear parametric, non-linear parametric as well as non-linear semi-parametric estimators is compared in specific scenarios such as the prevalence of weak instruments or non-standard distributed disturbances. The simulation shows that the non-linear maximum likelihood recursive bivariate probit estimator dominates in a majority of scenarios, even if the corresponding parametric assumptions are not fulfilled. Moreover, while one of the non-linear semi-parametric special regressor estimators under investigation might be seen as a suitable alternative for estimating coefficients, it suffers from weaknesses in estimating partial effects. These insights are confirmed by an application to individual labor supply.
The Impacts of Working from Home on Individual Health and Well-Being with Philipp Grunau
Using a novel German linked-employer-employee dataset, we provide unique evidence about the consequences of working from home (WfH) on individual health and well-being. During the recent pandemic, this locational flexibility measure has been used extensively to promote health by hampering the spread of the virus and to secure jobs. However, its direct theoretical ambiguous effects on health and well-being as characterized by different potential channels have barely been empirically investigated to date despite WfH’s increasing popularity in the years before the pandemic. To address concerns about selection into WfH, our analysis relies on an identification strategy ruling out confounding effects by time-invariant unobservable variables. Moreover, we explain the remaining (intertemporal) variation in the individual WfH status by means of an instrumental variable strategy using variation in equipment with mobile devices among establishments. We find that subjective measures of individual health are partly affected by WfH, whereas no corresponding effects are present for an objective measure of individual health. In terms of individual well-being, we find that WfH leads to considerable improvement. By addressing the potential heterogeneity in our effect of interest, we find that men, middle-aged individuals and those commuting to different municipalities particularly benefit from WfH.
Beyond F-statistic – A General Approach for Weak Identification with Constantin Weiser
We propose a new method to detect weak identification in IV models. This method is based on the asymptotic normality of the distributions of the estimated endogenous variable structural equation coefficients in the presence of strong identification. Therefore, our method resulting in a specific test is more flexible than previous tests as it does not depend on a specific class of models, but is applicable to a variety of both linear and non-linear IV models or mixtures of them, which can be estimated by generalized method of moments (GMM). Moreover, our proposed test does not rely on assumptions of homoscedasticity or the absence of autocorrelation. For linear models estimated by 2SLS, our novel test yields the same qualitative conclusions as the usually applied test on excluded instruments at the reduced form. By adopting weak identification definitions of Stock and Yogo (2005), we provide critical values for our test by means of a comprehensive Monte Carlo simulation. This enables applied econometricians to make case-by-case decisions regarding weak identification in non-homoscedastic linear models by using pair bootstrapping procedures. Moreover, we show how our insights can be applied to assess weak identification in a specific non-linear IV model.
Work in Progress
- An Analysis of the Special Regressor Approach in Different Classes of Limited Dependent Variables
- Broadband and the Labor Market: The Internet’s Effect on the Individual Likelihood to Find a (new) Job
- The Medium-term Consequences of Working from Home on Wages and Employment with Philipp Grunau, Thorsten Schank and Richard Upward
- The Relationship between Broadband Access and Commuting with Philipp Grunau, Thorsten Schank and Richard Upward
- Determinants and Effects of Gig and Crowd Working – Insights from a Representative Household Survey