Skip to content

Veranstaltungsformat: Hybrid

Big Data and the analysis thereof is considered of increasing importance, not only for big (tech) companies.

Big Data (BD) and the analysis thereof (i.e., Big Data Analytics, BDA) is considered of increasing importance, not only for big (tech) companies but also for small/medium-sized companies and, in particular, for new ventures. Despite or precisely due to its generally presumed relevance, the question arises whether applying BDA leads to better firm performance. Based on a large, representative sample of 3,700 German start-ups, we specifically study the adoption of BDA among start-ups and analyze its economic effects using various short- and longer-term performance measures. We show that start-ups adopting BDA significantly differ from non-adopters regarding their founders' age, education, team composition, and experience. Accounting for these differences, we then investigate the effect of adopting BDA on the new ventures' operating costs, sales, profits, survival rate, and (employee) growth. Our findings show that using BDA does not lead to a competitive advantage in terms of the classical short-term performance measures but is rather associated with greater sales/profit uncertainty, higher (personnel) costs, and a higher probability of failure. Yet, the increased risk of adopting BDA is at the same time compensated by a prospect for higher excess performance -- BDA-adopting start-ups perform significantly better than their peers at the 90%-quantile -- as well as by better expected longer-term performance, as measured by the start-ups' growth and by their ability to secure Venture Capital (VC). Our findings support the concept of a few Schumpeterian Entrepreneurs who adopt technology at the frontier of innovation and found high-risk start-ups with the prospect of high rewards.

A proposal for an occupation-specific end-of-life and late-life perspective on retirees.

Retirement marks a significant life transition, signaling the end of one's active work engagement and the beginning of a new phase of life. In the best-case scenario post-retirement life is characterized by increased time spend with friends and family, and a purpose in life that is perceived as meaningful. The reduced work load should be associated with improved health, because sources of physical and psychological stress should have far less impact. However, reality paints a different picture: The research on retirement shows a lot variation in retirement experiences, financial well-being, mental and physical health, social engagement, and overall life satisfaction.
The importance of pre-retirement occupations on individuals' lives cannot be overstated. However, the impact of occupations on people’s lives does not end with their retirement. Hence, I will propose a new perspective on employment and occupations by focusing on the retirees’ late life and end of life. In my presentation I will provide the theoretical foundations, why occupations (should) have a lasting impact. I will present a data source with which such analyses could be done and discuss outcome variables of interest. Examples for occupation-specific outcomes of interest are: years of life remaining after retirement, years in good health after retirement, years spend in loneliness, wealth, poverty, depression, political attitudes, decrease in cognitive capabilities, social networks, free-time activities, volunteering, housing, life satisfaction, etc.
From a policy perspective, understanding how different occupations influence post-retirement lives can inform retirement planning initiatives and social safety nets as well as occupation-specific training and safety regulations. On an individual level, insights gained from such research can assist individuals in making informed decisions about their vocational aspirations, careers, planned changes of occupations, retirement age, and financial preparations.

The literature on alternative methods for accounting for sample-independent variability is reviewed, a typology of sources of sample-independent variation is developed, and an empirical investigation is conducted estimating the relative and absolute importance of the different types of sample-independent variation.

Empirical economics papers report standard errors to take into account uncertainty associated with sampling variation but rarely consider non-sampling variation from researcher choices about measurement of key variables, functional form choice, identification strategy, and data set. In this paper, we review the literature on alternative methods for taking account of non-sampling variability, develop a typology of sources of non-sampling variation, and conduct an empirical exercise in which we estimate the relative and absolute importance of different types of non-sampling variation. The empirical exercise proceeds in the context of the literature that seeks to estimate the causal effect of college quality on educational and labor market outcomes.

This paper analyzes the open-economy spillover effects of labor market reforms under incomplete insurance. Using microeconomic data, we document a boost in the tradable sector in the aftermath of the German Hartz IV reform. In our model, this phenomenon can be explained by an increase in household savings due to higher precautionary savings in response to the reduction in the generosity of unemployment insurance (Hartz IV). Besides reducing unemployment in the reforming country, lower unemployment benefits generate long-run negative consumption spillovers in a monetary union, which we call the dark shadow of labor market reforms. Our model can match various German trends post Hartz IV reform, such as: i) a lasting increase in net foreign asset position, ii) short-term expansion of the tradable sector relative to the non-tradable sector, and iii) continued depreciation of the real exchange rate. By contrast, simulations of German wage moderation result in qualitatively different open-economy effects that are not in line with the empirical patterns for Germany.

Exploiting prospective data on a cohort born in 1958 we estimate the gender wage gap over the life-course between age 23 and 63, departing from the literature in two ways.

Most studies estimating the gender wage gap rely on linear regression of log hourly earnings.  Estimates often condition on potentially endogenous regressors such as labour market experience and family formation.  Exploiting prospective data on a cohort born in 1958 we estimate the gender wage gap over the life-course between age 23 and 63, departing from the literature in two ways.  First, we use matching estimators which are rarely used in the literature.  Like regression analyses matching relies on observed data to recover the effect of gender on earnings, but by explicitly considering the issue of common support it is more transparent in its treatment of men as counterfactuals for women.  We examine the importance of the common support issue for the size of the gender wage gap.  Second, we condition on pre-labour market variables to avoid conditioning on endogenous choice variables, such as family formation, which are made, in part, with knowledge regarding one’s potential earnings.  We argue our data are well-suited to the task because they contain a wide array of prospective data collected at birth, then at ages 7, 11 and 16, which might conceivably confound estimates of the GWG.  In contrast to findings in the literature in which the regression-adjusted GWG is considerably smaller than the raw gap, we find differences in log hourly mean earnings between men and women are of roughly similar size and, in some cases, wider than raw gaps conditioning on pre-labour market variables.  This is the case whether we use matching or linear estimation techniques. However, the PSM estimated GWG is above the raw gap when cohort members are in their 40s, 50s and 60s.  The implication is that women have pre-labour market traits which reduce their earnings later in life relative to men.  The gap follows an inverted-u shape over the life-course, reaching its maximum of around. .45 log points at age 42, after which it begins to decline, though it remains large among cohort members in their 60s.

Joint work with: Francesca Foliano, Heather Joshi, Bozena Wielgoszewska and David Wilkinson

In this study, we examine how the same vacating opportunity translates differently for male and female full-time workers.

In this study, we examine how the same vacating opportunity translates differently for male and female full-time workers. By utilizing matched employer-employee data from Germany, our empirical approach leverages 30,000 unforeseen worker deaths spanning from 1980 to 2016 which enables us to explore how firms react to exogenous vacancies. We find that when a position becomes vacant, female replacements have starting wages that are 20 log points lower compared to their male counterparts. Even after considering the pre-hire wage of replacement workers, half of this gap persists. The gender disparity in opportunities cannot be attributed to workload redistribution among other coworkers. Over time, the gap tends to widen on average and remains stable even for those who remain employed full-time in the subsequent five years after being hired.​

We study the role of labor market beliefs in the gender pay gap. We find that, on average, women expect to receive lower salaries than men and also expect to receive fewer offers when employed. 

We study the role of labor market beliefs in the gender pay gap. We find that, on average, women expect to receive lower salaries than men and also expect to receive fewer offers when employed. Gender differences in expectations explain a sizable fraction of the residual gap in reservation wages. We estimate a partial equilibrium job search model that incorporates worker heterogeneity in beliefs about the wage offer distribution, arrival rates, and separation rate. Counterfactual exercises show that labor market beliefs play an important role in the gender wage gap, but matter little for the gender differences in welfare. Eliminating gender differences in the actual offer distribution, by contrast, decreases the gender gap in pay and welfare.

Numerous governments provide income-contingent childcare subsidies.

Numerous governments provide income-contingent childcare subsidies. In this paper, we estimate the dynamic marginal efficiency cost of redistribution (MECR) associated with a large-scale program of this kind in Germany, and compare them with the MECR associated with the benchmark redistributive tool, the income tax. To do so, we integrate methods from public finance theory into a dynamic structural heterogeneous-household model of childcare demand and maternal labor supply. We also incorporate social mobility concerns into the MECR and find the MECR of the childcare subsidies to be significantly lower at the margin, suggesting that childcare subsidies are the more efficient redistributive tool.

This lecture is about how artificial intelligence can be used to reduce friction in markets.

We explore how Artificial Intelligence can be leveraged to help frictional markets to clear. We design a collaborative-filtering machine-learning job recommender system that uses job seekers' click history to generate relevant personalised job recommendations. We deploy it at scale on the largest online job board in Sweden, and design a clustered two-sided randomised experiment to evaluate its impact on job search and labour-market outcomes. Combining platform data with unemployment and employment registers, we find that treated job seekers are more likely to click and apply to recommended jobs, and have 0.7 percent higher employment within the 6 months following first exposure to recommendations. At the job-worker pair level, we document that recommending a vacancy to a job seeker increases the probability to work at this workplace by 10 percent. We propose a decomposition exercise of the net employment effects into three channels. The most important channel corresponds to the increase in the number of applications due to recommendations (first channel), partly offset by the lower conversion into employment of marginal applications (second channel). Congestion effects (third channel) are not a significant contributor to the overall effect. We also find larger employment effects when recommended vacancies are less popular, and for recommendations that broaden search further away in geographical and occupational distance.

We study how online job search advice affects the job search strategies and labor market outcomes of unemployed workers.

We study how online job search advice affects the job search strategies and labor market outcomes of unemployed workers. In a large-scale field experiment, we provide job seekers with vacancy information and occupational recommendations on an online dashboard. A two-stage randomized design with regionally varying treatment intensities allows us to account for treatment spillovers. Our results show that online advice is highly effective when the share of treated workers is relatively low: in regions where less than less than 50% of job seekers are exposed to treatment, working hours and earnings of treated job seekers increase significantly in the year after the intervention. At the same time, we find substantial negative spillovers on other treated job seekers for higher treatment intensities, resulting from increased competition between treated job seekers who apply for similar vacancies.

Use of cookies and other technologies

We want to tailor our online services to your needs. For this purpose, we use so-called cookies.
You can decide for yourself which cookies you allow.
Your consent can be changed at any time under Cookie settings in our privacy policy. For more information, see our privacy policy.

Web analytics tool Matomo