Impact of Sibship Size,Birth Order and Sex Composition on School Enrolment in Urban Turkey*

This paper investigates, in a unified framework, the effects of sibship size, birth order and sibling sex composition on children's school enrolment in urban Turkey. We utilize an instrumental variable estimation method to address parents’ joint fertility and schooling decisions using twin births as instruments. We find no causal impact of sibship size on school enrolment. However, there is evidence for a parabolic impact of birth order where middle‐born children fare worse. Sex composition of siblings matters only for female children. Our finding that birth order and sibling sex composition matter more for poorer households suggests that scarce financial resources play an important role in bringing about the sibling composition effects.     

How interethnic marriages affect the educational attainment of children: Evidence from a natural experiment

The allocation of Moluccan immigrants across towns and villages at arrival in the Netherlands and the subsequent formation of interethnic marriages resemble a natural experiment. The exogenous variation in marriage formation allows us to estimate the causal effect of interethnic marriages on the educational attainment of children from such marriages. We find that children from Moluccan fathers and native mothers have a higher educational attainment than children from ethnic homogeneous Moluccan couples or children from a Moluccan mother and a native father.     

THE EFFECT OF PARENTAL EMPLOYMENT ON CHILD SCHOOLING

This paper presents a model that provides conditions under which a causal interpretation can be given to the association between childhood parental employment and subsequent educational attainments of children. The key parameter comes from theconditional demand function for children's future earning capacity. Its identification rests on having data on siblings and assumptions about the timing of parents' knowledge of their children's endowments. In addition to sibling differences, the useof a fixed‐effects instrumental‐variables estimator identifies the parameter under weaker conditions. Empirical analysis informed by the model reveals a negative and significant effect on the child's educational attainment of the months of the mother's full‐time employment when the child was aged 0–5. The effect of the mother's part‐time employment is smaller and less well determined, but again negative. These results suggest that the substitution effect of the mother's employment dominates the income effects. Stronger adverse effects are found for children of less‐educated mothers. Copyright © 2012 John Wiley & Sons, Ltd.     

R&D, Investment, and Industry Dynamics

We present a model of industry evolution where the dynamics are driven by a process of endogenous innovations followed by subsequent embodiments in physical capital. Traditionally, the only distinction between R&D and physical investment was one of labeling: the first process accumulates an intangible stock, knowledge, while the second accumulates physical capital. Both stocks affect output in a symmetric fashion. We argue that the story is not that simple, and that there is more to it than differences in the object of accumulation. Our model stresses the causal relationship between past R&D expenditures and current investments in machinery and equipment. This causality pattern, which is supported by the data, also explains the observed higher volatility of physical investment relative to that of R&D expenditures.     

Family planning,gender differences and infant mortality: evidence from Uttar Pradesh,India

This paper modeled the proximate determinants of infant survival using the National Family Health Survey data on 11,500 women from the most populous Indian state Uttar Pradesh in the period 1982–1992. A methodological framework was developed for analyzing the inter-relationships between high fertility and infant mortality, gender differences in mortality, and for modeling the effects of health care and family planning variables. Probit models were estimated by maximum likelihood taking into account simultaneity of regressors and unobserved household differences. The proximate determinants of infant survival included maternal education and age at first birth, birth interval, the number of children before family planning was first used, maternal tetanus vaccination, and child's vaccinations. Indicator variables for a boy (girl) born at a birth order higher than the “ideal” number showed that unwanted births exacerbated female mortality.     

A Geo-Additive Bayesian Discrete-Time Survival Model and its Application to Spatial Analysis of Childhood Mortality in Malawi

We describe a flexible geo-additive Bayesian survival model that controls, simultaneously, for spatial dependence and possible nonlinear or time-varying effects of other variables. Inference is fully Bayesian and is based on recently developed Markov Chain Monte Carlo techniques. In illustrating the model we introduce a spatial dimension in modelling under-five mortality among Malawian children using data from Malawi Demographic and Health Survey of 2000. The results show that district-level socioeconomic characteristics are important determinants of childhood mortality. More importantly, a separate spatial process produces district clustering of childhood mortality indicating the importance of spatial effects. The visual nature of the maps presented in this paper highlights relationships that would, otherwise, be overlooked in standard methods.     

Nonlinear continuous time modeling approaches in panel research

Stochastic differential equations (SDE) are used as dynamical models for cross-sectional discrete time measurements (panel data). Thus causal effects are formulated on a fundamental infinitesimal time scale. Cumulated causal effects over the measurement interval can be expressed in terms of fundamental effects which are independent of the chosen sampling intervals (e.g. weekly, monthly, annually). The nonlinear continuous–discrete filter is the key tool in deriving a recursive sequence of time and measurement updates. Several approximation methods including the extended Kalman filter (EKF), higher order nonlinear filters (HNF), the local linearization filter (LLF), the unscented Kalman filter (UKF), the Gauss–Hermite filter (GHF) and generalizations (GGHF), as well as simulated filters (functional integral filter FIF) are compared.     

Family size and child outcomes: Is there really no trade-off?

We study the impact of family size on intermediate and long-term outcomes using twin births as an exogenous source of variation in family size in an unusually rich dataset. Similar to recent studies, we find no evidence of a causal effect on long-term outcomes and show that not taking selection effects into account will likely overstate the effects. We do, however, find a small but significant negative impact of family size on grades in compulsory and secondary school among children who are likely to be vulnerable to further restrictions on parental investments.     

The Effects of UI Benefits on Unemployment and Subsequent Outcomes: Evidence from a Kinked Benefit Rule

This paper analyses the effects of unemployment insurance benefits on unemployment exits and subsequent labour market outcomes. We exploit a piecewise linear relationship between the previous wage and benefits in Finland to identify the causal effects of the benefit level by using a regression kink design. Although we only find weak evidence of an effect on the time to the next job, higher benefits decrease the time spent in part-time unemployment and thus result in more full-time unemployment. The re-employment probability and post-unemployment wage are also negatively affected. The results for the duration of the first post-unemployment job are not conclusive, but in total both employment and earnings in the two years following the beginning of the unemployment spell decrease with higher benefits.     

Using the Lee–Carter Method to Forecast Mortality for Populations with Limited Data*

The Lee–Carter method for modeling and forecasting mortality has been shown to work quite well given long time series of data. Here we consider how it can be used when there are few observations at uneven intervals. Assuming that the underlying model is correct and that the mortality index follows a random walk with drift, we find the method can be used with sparse data. The central forecast depends mainly on the first and last observation, and so can be generated with just two observations, preferably not too close in time. With three data points, uncertainty can also be estimated, although such estimates of uncertainty are themselves highly uncertain and improve with additional observations. We apply the methods to China and South Korea, which have 3 and 20 data points, respectively, at uneven intervals.     

A Tutorial on Multilevel Survival Analysis: Methods,Models and Applications

Data that have a multilevel structure occur frequently across a range of disciplines, including epidemiology, health services research, public health, education and sociology. We describe three families of regression models for the analysis of multilevel survival data. First, Cox proportional hazards models with mixed effects incorporate cluster‐specific random effects that modify the baseline hazard function. Second, piecewise exponential survival models partition the duration of follow‐up into mutually exclusive intervals and fit a model that assumes that the hazard function is constant within each interval. This is equivalent to a Poisson regression model that incorporates the duration of exposure within each interval. By incorporating cluster‐specific random effects, generalised linear mixed models can be used to analyse these data. Third, after partitioning the duration of follow‐up into mutually exclusive intervals, one can use discrete time survival models that use a complementary log–log generalised linear model to model the occurrence of the outcome of interest within each interval. Random effects can be incorporated to account for within‐cluster homogeneity in outcomes. We illustrate the application of these methods using data consisting of patients hospitalised with a heart attack. We illustrate the application of these methods using three statistical programming languages (R, SAS and Stata).     

High‐involvement HRM,job satisfaction and productivity: A two wave longitudinal study of a Spanish retail company

The strategic human resource management literature lacks longitudinal studies, and the causal associations between human resource management (HRM) and organisational performance (OP) remain underexplored. We tested cross‐lagged relationships between high‐involvement work systems (HIWS), job satisfaction, and store productivity based on a large longitudinal dataset from the retail sector comprising two waves of data. The first wave (2011) included 6,016 employee responses from 104 stores, and the second wave (2015) included 5,842 employee responses from 94 stores. The quantitative study suggested counterintuitive negative associations. A subsequent qualitative study indicated that the association may have been conditioned by the recessionary action taken by the company in response to financial difficulties. The longitudinal research design, the compilation of data during difficult economic situations, and in a relatively unexplored sector such as the retail industry help to shed some light on the universalism of the HRM‐OP relationship and its boundary conditions.     

Open space, residential property values, and spatial context

We use hedonic analysis of home transaction data from the Minneapolis–St. Paul metropolitan area to estimate the effects of proximity to open space on sales price. We allow the effects of proximity to vary with demographic and location-specific characteristics and include fixed effects to control for observed and unobserved neighborhood characteristics. We find that the value of proximity to open space is higher in neighborhoods that are dense, near the central business district, high-income, high-crime, or home to many children. Using the metropolitan area's average value may substantially overestimate or underestimate the value of open space in particular neighborhoods.     

IDENTIFYING CAUSAL MECHANISMS (PRIMARILY) BASED ON INVERSE PROBABILITY WEIGHTING

This paper demonstrates the identification of causal mechanisms of a binary treatment under selection on observables, (primarily) based on inverse probability weighting; i.e. we consider the average indirect effect of the treatment, which operates through an intermediate variable (or mediator) that is situated on the causal path between the treatment and the outcome, as well as the (unmediated) direct effect. Even under random treatment assignment, subsequent selection into the mediator is generally non‐random such that causal mechanisms are only identified when controlling for confounders of the mediator and the outcome. To tackle this issue, units are weighted by the inverse of their conditional treatment propensity given the mediator and observed confounders. We show that the form and applicability of weighting depend on whether some confounders are themselves influenced by the treatment or not. A simulation study gives the intuition for these results and an empirical application to the direct and indirect health effects (through employment) of the US Job Corps program is also provided. Copyright © 2013 John Wiley & Sons, Ltd.     

The entrepreneur's role stressors and proclivity for a venture withdrawal

We test a causal model of entrepreneurs’ role stressors—role conflict, role ambiguity, and role overload—and their relationships with exhaustion and reduced perceptions of compensation for one's efforts which over time lead to the development of a proclivity for venture withdrawal. Using structural equation modelling and a 2-year longitudinal data set, we find empirical support for the proposed causal model. Overall, the empirical results support the indirect influence of role stressors and highlight the direct effects of enhanced exhaustion and reduced perceptions of compensation for one's efforts on a proclivity for a new venture withdrawal. The paper concludes by proposing implications for theory and further research.     

Adjustments and their Consequences—Collapsibility Analysis using Graphical Models

We review probabilistic and graphical rules for detecting situations in which a dependence of one variable on another is altered by adjusting for a third variable (i.e., non‐collapsibility or non‐invariance under adjustment), whether that dependence is causal or purely predictive. We focus on distinguishing situations in which adjustment will reduce, increase, or leave unchanged the degree of bias in an association that is taken to represent a causal effect of one variable on the other. We then consider situations in which adjustment may partially remove or introduce a bias in estimating causal effects, and some additional special cases useful for case‐control studies, cohort studies with loss, and trials with non‐compliance (non‐adherence).     

We the living: the effects of living and deceased donor stories on charitable bequest giving intentions

Choosing messages to encourage charitable bequest giving may be particularly challenging given sensitivity to personal mortality reminders. Previous research suggests that people often react to mortality reminders with avoidance, including distancing themselves from those associated with death. We compare the effects of otherwise similar living and deceased bequest donor stories on subsequent intentions to leave a charitable bequest. Although both story types significantly increased subsequent intentions to leave a charitable bequest, living donor stories consistently outperformed otherwise identical deceased donor stories. Fundraisers may do well to emphasize stories of living planned bequest donors and de‐emphasize death and the deceased in charitable bequest fundraising messaging. Copyright © 2016 John Wiley & Sons, Ltd.     

A Bootstrap Method for Identifying and Evaluating a Structural Vector Autoregression*

Graph‐theoretic methods of causal search based on the ideas of Pearl (2000), Spirtes et al. (2000), and others have been applied by a number of researchers to economic data, particularly by Swanson and Granger (1997) to the problem of finding a data‐based contemporaneous causal order for the structural vector autoregression, rather than, as is typically done, assuming a weakly justified Choleski order. Demiralp and Hoover (2003) provided Monte Carlo evidence that such methods were effective, provided that signal strengths were sufficiently high. Unfortunately, in applications to actual data, such Monte Carlo simulations are of limited value, as the causal structure of the true data‐generating process is necessarily unknown. In this paper, we present a bootstrap procedure that can be applied to actual data (i.e. without knowledge of the true causal structure). We show with an applied example and a simulation study that the procedure is an effective tool for assessing our confidence in causal orders identified by graph‐theoretic search algorithms.     

Climbing the drug staircase: a Bayesian analysis of the initiation of hard drug use

Since empirical studies have shown that cannabis users are much more likely to initiate hard drug use, a causal linkage has been suggested (‘gateway hypothesis’). However, individual differences in proneness and accessibility to drugs provide alternative non‐causal explanations for the observed drug use pattern. We propose a Bayesian estimation and predictive framework to analyze the effects and relative importance of previous cannabis use, proneness and accessibility factors on hard drug initiation and to explore possible policy implications. We employ a novel model specification, motivated by four gateway transmission channels, to analyze data from a recent Norwegian survey of young adults. Copyright © 2010 John Wiley & Sons, Ltd.     

THE MULTIDIMENSIONAL EFFECTS OF RELIGION ON SOCIOECONOMIC DEVELOPMENT: A REVIEW OF THE EMPIRICAL LITERATURE

Religion plays a fundamental role in most people's lives with profound implications for socioeconomic development. This survey provides a comprehensive and systematic overview of the causal mechanisms between religion and development discussed and tested in the economics literature, and reviews quantitative empirical evidence on the actual effects of religion on economic and social dimensions of development. We start by disaggregating the concept of religion into four religious dimensions and propose a framework to conceptualize causal mechanisms. Numerous mechanisms are possible but only a few uncontested findings exist. Religion is ambivalent vis‐à‐vis development: although religious ideas can foster certain forms of human capital acquisition and labor market participation, scholars have found a negative relationship between religious dimensions and both income and gender equality as well as innovation activities. Religious identity is also a source of labor market discrimination and has ambivalent effects on economic growth and social cohesion. Methodological challenges refer to the availability of fine‐grained data, especially for developing countries, the use of concepts and definitions, and the lack of causal inference.