Search results

This paper studies the event-history approach to microeconometric program evaluation. We present a mixed semi-Markov event-history model, discuss its application to program evaluation, and analyze its empirical content. The results of this paper provide fundamental insights into what can be learned from longitudinal microdata about, for example, the effects of training programs for the unemployed on their unemployment durations and subsequent job stability. They can guide the choice of particular models and methods for the empirical analysis of such effects.

To review and address current approaches and limitations to modeling change over time in social entrepreneurship research.

The article provides a narrative review of different practices used to assess change over time. It also shows how different research questions require different methodologies for assessing changes over time. Finally, it presents worked examples for modeling these changes.

Our review suggests that there is a lack of research in social entrepreneurship that takes into account the many different considerations for addressing how time influences outcomes.

This chapter introduces an analytic technique to social entrepreneurship that effectively models changes in predictors and outcomes even when data are non-normal or nested across time or levels of analysis.

On the theoretical level, this chapter examines the mechanisms through which cultural and financial capital affects educational outcomes in different institutional contexts. On the methodological level, the central question in this chapter is how to resolve concerns in comparative analyses of educational attainment, such as variations in enrolment rates and study program duration across institutional settings. On the empirical level, the chapter asks whether family background predicts educational attainment in similar ways in two diametrically opposed welfare states: the United States and Norway. Differences in dropout from higher education were compared using nationally representative longitudinal data from the United States and Norway and event history and multilevel modelling techniques. The chapter also makes use of the standardized sheaf coefficient to summarize central background variables for more direct comparison of effect sizes. The findings show that whereas parents’ education level has strikingly similar effects on students’ dropout probabilities in the two countries, the effect of parents’ income varies substantially according to the institutional context. The chapter concludes that in comparative analyses of inequality in education the value of different types of family resources must be understood in light of the concrete, practical constraints of the national institutional contexts.

A robust body of scholarship has attached unintended childbearing, cohabitation, and stepfamily living arrangements to a greater risk of union instability in the United States. These aspects of family life, which often co-occur, are overrepresented among disadvantaged populations, who also have an independently higher risk of union instability. Existing scholarship has modeled these family experiences as correlated events to better understand family and union instability, yet the authors assert a direct effort to test whether or how unintended childbearing differs across marital and stepfamily statuses makes important contributions to established research on relationship stability. Drawing on the 2006–2017 National Survey of Family Growth (NSFG), the authors test potential moderating effects to better understand the linkages between unintended childbearing and union dissolution among 7,864 recent, higher-order births to partnered mothers via discrete-time, event history logistic regression models. Findings confirm that unintended childbearing, cohabitation, and stepfamily status are all linked with a greater risk of dissolution. However, unintended childbearing is differentially linked to instability by marital status, with unintended childbearing being associated with a higher risk of dissolution for married couples relative to cohabiting couples. Unintended fertility does not seem to increase the risk of instability across stepfamily status. Findings provide more evidence in support of selection, rather than causation, in explaining the association between unintended childbearing and union instability among higher-order births. Results suggest that among higher-order births, unintended childbearing may reflect underlying relationship issues.

This paper examines the diffusion of a multinational bank’s quality initiative across functional and geographic boundaries. It demonstrates substantial regional differences in the volume and institutionalization of TQM activities, with slow development and little staying power in the U.S. and rapid expansion in Asia and Latin America. Event history analysis of quality team formation demonstrates that positive feedback occurs primarily within business divisions operating within national boundaries.

Starting in the 1960s, university systems around the world began to undergo a variety of drastic changes that would forever alter higher education. The spread of social movements were fueled by anti-war protests, demands for civil rights, and new forms of economic and political organization (Lipset, 1993). In terms of changes in universities, students demanded greater educational access and equal opportunities. A worldwide logic of inclusiveness increasingly affected national political and educational outcomes, including transformations in multiple dimensions of the status of women in the polity and in the educational system. This chapter focuses on the emergence and expansion of women's studies curricula in universities throughout the world, treating this unexpected development as a further manifestation of the globalization of a logic of inclusiveness.

As more and more longitudinal data become available, researchers turn toward dynamic tools that better utilize these data to contribute to the understanding of postsecondary education. Event history analysis (EHA) is one such approach, and its ability to study change over time has lent itself particularly well to the study of higher education. This chapter introduces the family of methods, providing detailed descriptions and guidance for researchers both new to and familiar with these techniques. An example of reform of higher education governance is used to illustrate the concepts and components relevant to EHA.

We investigate how household disadvantage affects the time use of 15–18 year olds using 2003–2006 data from the American Time Use Survey. Applying competing-risk hazard models, we distinguish between the incidence and duration of activities and incorporate the daily time constraint. We find that teens living in disadvantaged households spend less time in nonclassroom educational activities than other teens. Girls spend some of this time in work activities, suggesting that they are taking on adult roles. However, we find more evidence of substitution into unsupervised activities, suggesting that it may be less-structured environments that reduce educational investment.

We identify methodological weaknesses in a paper by Skocpol, Abend-Wein, Howard, and Lehmann (1993) on the origins of mothers’ pensions in the American states in the early twentieth century. These include a sub-optimal and potentially biased strategy for assessing the impact of state characteristics on the time to adoption of pensions, as well as the use of a backward stepwise regression procedure for selecting independent variables. To determine whether Skocpol et al.’s conclusions remain valid, we recreated most of their dataset and used methods that are more appropriate for the analysis of duration data, including the Cox and complementary cloglog event history procedures. While we find support for several of their claims, our findings allow for a more straightforward interpretation of the role of explanatory variables, and the temporal dependence of the adoption process.

This study examines the effects of a family's and individual children's characteristics on the probability of having a divorce. Current research shows a clear indication of increased divorce risks if an individual's parents or siblings have experienced a divorce. Explanations include both shared family characteristics (including genetic effects) and common characteristics of the individual children involved. This study analyzes the effects of shared family background characteristics on the divorce risk of individuals. By analyzing siblings within families and including individual children's characteristics in the analysis, it is possible to separate individual-level and family-level effects.

In addition to employing a multi-level structure of individual siblings nested within families, the data cited here are censored. For all individuals, the length of the marriage and the divorce status are known, but the divorce status is interpreted differently for individuals who have or have not experienced divorce. For divorced individuals, the final divorce status is known; for individuals who have not experienced divorce, the final marriage status is unknown or censored. The proper analysis model for such data is event history (also called survival) analysis. This study therefore employs a multi-level event history model.

Our results show that there is a similarity in the divorce risks of siblings from the same family, which is not explained away by the available child and family characteristics. This finding suggests that shared genetic and social heritage play an important role in the intergenerational transmission of divorce risks.