Markus Gangl

Assessing Bias in the Estimation of Causal Effects: Rosenbaum Bounds on Matching Estimators and Instrumental Variables Estimation with Imperfect Instruments

Propensity score matching provides an estimate of the effect of a “treatment” variable on an outcome variable that is largely free of bias arising from an association between treatment status and observable variables. However, matching methods are not robust against “hidden bias” arising from unobserved variables that simultaneously affect assignment to treatment and the outcome variable. One strategy for addressing this problem is the Rosenbaum bounds approach, which allows the analyst to determine how strongly an unmeasured confounding variable must affect selection into treatment in order to undermine the conclusions about causal effects from a matching analysis. Instrumental variables (IV) estimation provides an alternative strategy for the estimation of causal effects, but the method typically reduces the precision of the estimate and has an additional source of uncertainty that derives from the untestable nature of the assumptions of the IV approach. A method of assessing this additional uncertainty is proposed so that the total uncertainty of the IV approach can be comparedwith the Rosenbaum bounds approach to uncertainty using matching methods. Because the approaches rely on different information and different assumptions, they provide complementary information about causal relationships. The approach is illustrated via an analysis of the impact of unemployment insurance on the timing of reemployment, the postunemployment wage, and the probability of relocation, using data from several panels of the Survey of Income and Program Participation (SIPP).

Motherhood, Labor Force Behavior, and Women's Careers: An Empirical Assessment of the Wage Penalty for Motherhood in Britain, Germany, and the United States

Using harmonized longitudinal data from the British Household Panel Survey (BHPS), the German Socio-Economic Panel (GSOEP), and the National Longitudinal Survey of Youth (NLSY), we trace career prospects after motherhood for five cohorts of American, British, and West German women around the 1960s. We establish wage penalties for motherhood between 9% and 18% per child, with wage losses among American and British mothers being lower than those experienced by mothers in Germany. Labor market mechanisms generating the observed wage penalty for motherhood differ markedly across countries, however. For British and American women, work interruptions and subsequent mobility into mother-friendly jobs fully account for mothers’ wage losses. In contrast, respective penalties are considerably smaller in Germany, yet we observe a substantial residual wage penalty that is unaccounted for by mothers’ observable labor market behavior. We interpret this finding as indicating a comparatively more pronounced role for statistical discrimination against mothers in the German labor market.

Welfare States and the Scar Effects of Unemployment: A Comparative Analysis of the United States and West Germany1

The article examines whether, through supporting workers’ search for adequate reemployment, the decommodification achieved by welfare state transfers reduces the longer‐run scar effects of unemployment. Drawing on employment history data from the Survey of Income and Program Participation and the German Socio‐Economic Panel, the analysis establishes positive effects of unemployment benefits on workers’ post‐unemployment jobs: workers’ risks of incurring severe earnings losses, of experiencing occupational mobility, and of entering unstable job arrangements are considerably reduced in both the United States and West Germany. As workers face constrained choices in labor markets, however, this institutional protection of workers’ economic status comes at the economic cost of prolonged unemployment. Simulation analyses suggest that higher benefit coverage alone might account for up to 20% of the smaller cumulative disadvantages associated with unemployment for German workers.

Income Inequality, Permanent Incomes, and Income Dynamics Comparing Europe to the United States

As income mobility over time serves to offset income inequality existing at any point in time, cross-national differences in social stratification are preferably assessed from data on average incomes over an extended period of time. Hence, this article uses longitudinal income data from the Panel Study of Income Dynamics and the European Community Household Panel to reassess the received empirical evidence. Even discounting the impact of income mobility, however, the United States continues to exhibit the highest level of permanent income inequality in this particular sample of industrial countries. In addition, older workers and individuals at the bottom of the income distribution have faced significantly worse income prospects than common in many European countries.

The structure of labour market entry in Europe: a typological analysis

This chapter focuses on different patterns of labour market entry across Europe. Different approaches to the school to work transition process are examined. The value of different structures is considered. Occupational and organisational structures are compared. Statistics are used to compare structures in various European Union member states.

Unemployment Dynamics in the United States and West Germany

1 Dynamics of unemployment, jobs and careers: a cross-national perspective.- 2 Dynamic perspectives on labor markets and unemployment.- 2.1 Perspectives on unemployment dynamics.- 2.2 A matching framework to explain unemployment flows.- 2.3 Institutions, restructuring, and unemployment dynamics.- 2.4 Summary.- 3 Statistical methodology.- 3.1 Data.- 3.2 Statistical analysis of event history data.- 3.3 Institutional inference and cross-national analysis.- 4 Dynamics of employment and unemployment in the United States and West Germany.- 4.1 The structure of unemployment.- 4.2 Labor market flows.- 4.3 Labor reallocation and turnover.- 4.4 Unemployment dynamics.- 4.5 Summary.- 5 Unemployment incidence: labor turnover in the United States and West Germany.- 5.1 Job losses and inflows into unemployment.- 5.2 A structural model of turnover dynamics.- 5.3 Unemployment risks and turnover components.- 5.4 Institutions and economic restructuring.- 5.5 Summary.- 6 Unemployment duration and reemployment rates: a supply-side perspective.- 6.1 Outflows from unemployment: jobs, training or withdrawal?.- 6.2 Interdependencies between exit routes: responses to low reemployment prospects?.- 6.3 Benefit effects revisited: Trade-offs between unemployment duration and reemployment outcomes.- 6.4 Summary.- 7 Opportunity, choice and reemployment rates: two-sided search and vacancy levels.- 7.1 Job competition: which jobs for the unemployed?.- 7.2 Sectoral effects on reemployment processes.- 7.3 Reemployment rates and the structure of opportunity.- 7.4 Structural sources of job opportunities.- 7.5 Summary.- 8 Summary and conclusions.- References.

The making of a good woman: : Extended parental leave entitlements and mothers’ work commitment in germany

The authors investigate the relationship between family policy and women’s attachment to the labor market, focusing specifically on policy feedback on women’s subjective work commitment. They utilize a quasi-experimental design to identify normative policy effects from changes in mothers’ work commitment in conjunction with two policy changes that significantly extended the length of statutory parental leave entitlements in Germany. Using unique survey data from the German Socio-Economic Panel and difference-in-differences, triple-differenced, and instrumental variables estimators for panel data, they obtain consistent empirical evidence that increasing generosity of leave entitlements led to a decline in mothers’ work commitment in both East and West Germany. They also probe potential mediating mechanisms and find strong evidence for role exposure and norm setting effects. Finally, they demonstrate that policy-induced shifts in mothers’ preferences have contributed to retarding women’s labor force participation after childbirth in Germany, especially as far as mothers’ return to full-time employment is concerned.

Nichtparametrische Schätzung kausaler Effekte mittels Matchingverfahren

Matchingverfahren umfassen eine Klasse nichtparametrischer Verfahren zur statistischen Abschatzung kausaler Effekte mittels Beobachtungsdaten. In diesen Verfahren erfolgt die Drittvariablenkontrolle durch Konstruktion statistischer Vergleichsgruppen, die in Bezug auf relevante Hintergrundfaktoren weitgehend identisch sind. In der praktischen Anwendung dominiert das Propensity score matching, das eine einfache Vergleichsgruppenbildung innerhalb eines eindimensionalen Merkmalsraums ermoglicht. Die empirische Analyse erfolgt dabei in drei Schritten: zunachst ist ein Zuweisungsmodell zu entwickeln, das die Verteilung des Kausalfaktors in Abhangigkeit von theoretisch relevanten Kovariaten beschreibt. Uber die aus dem Zuweisungsmodell vorhergesagten Propensity scores wird anschliesend durch den Einsatz verschiedener Matchingalgorithmen die Balancierung der Hintergrundkovariaten in den Vergleichsgruppen der Untersuchung angestrebt. Ist diese erreicht, erfolgt die eigentliche Schatzung der interessierenden kausalen Effekte durch den nichtparametrischen Vergleich der Ereignisverteilungen in den Experimental-und Kontrollstichproben. Auf die Annahme eines vollstandigen Erklarungsmodells fur die abhangige Variable der Analyse wird dabei verzichtet. Matchingverfahren stellen insgesamt eine Alternative zu gangigen Regressionsmodellen dar, die kausale Effekte unter vergleichsweise sparsamen statistischen Annahmen abschatzen. Ahnlich wie in konventionellen Regressionsanalysen hangt die Validitat der Effektschatzungen jedoch entscheidend davon ab, ob der kausal wirksame Faktor und die Ergebnisgrose unter Kontrolle der verfugbaren Kovariaten aus theoretischer Sicht als unabhangig betrachtet werden konnen.

Sozialhilfebezug und Arbeitsmarktverhalten

Zusammenfassung Die neuere dynamische Armutsforschung zeigt, daß dauerhafter Sozialhilfebezug vergleichsweise selten ist. Die Sozialhilfe wird in vielen Fällen wieder verlassen, nicht zuletzt auch über den Arbeitsmarkt. Die vorliegende Analyse setzt an diesen Resultaten der dynamischen Armutsforschung an und arbeitet die Charakteristika und Bedingungsfaktoren von Abgängen aus der Sozialhilfe in den Arbeitsmarkt heraus. Auf der Basis eines Modells von Matchingprozessen im Arbeitsmarkt wird gezeigt, daß das Zustandekommen von Arbeitsmarktübergängen im wesentlichen von den individuellen Arbeitsmarktressourcen und Erwerbspotentialen der Hilfebezieher bestimmt wird. Effekte transferinduzierter Fehlanreize, kumulativer Bezugserfahrungen oder der konjunkturellen Entwicklung von Opportunitätsstrukturen im Arbeitsmarkt sind dagegen nicht nachweisbar. Es wird zudem deutlich, daß Armutsanalysen sehr differenziert angelegt sein müssen, um einerseits den heterogenen Lebens- und Problemlagen von Sozialhilfebeziehern gerecht zu werden und andererseits die unterschiedlichen sozialen Prozesse abzubilden, die Bezugsverläufe in der Sozialhilfe strukturieren.

Ansprüche an den Wohlfahrtsstaat in den alten und neuen Bundesländern

Der Begriff des Wohlfahrtsstaates bezeichnet ein Bundel staatlicher Institutionen, die in die primare, uber den Marktmechanismus erzeugte Verteilung okonomischer und sozialer Ressourcen und Lebenschancen eingreifen. Wohlfahrtsstaatliche Politik verfolgt durch diese Eingriffe die Ziele der Schaffung materieller Sicherheit im Lebenslauf der Burger und der Realisierung von Gleichheit und Gerechtigkeit innerhalb der Gesellschaft (allgemein Flora et al. 1977). Den Kernbereich wohlfahrtsstaatlichen Handelns bilden dabei zweifelsohne Instrumente zur Einkommenssicherung der Gesellschaftsmitglieder, sei es uber die Sozialversicherung oder explizite staatliche Transfers wie Sozialhilfe, Kinder- oder Wohngeld; daneben sollten sozialpolitische Regulierungen, die staatliche Bereitstellung sozialer Dienste oder auch die aktive Arbeitsmarktpolitik jedoch nicht vergessen werden.