Repeated Cross-section Data Research Articles

Do fertility preferences in early adulthood predict later average fertility outcomes of the same cohort?: Pritchett (1994) revisited with cohort data

Pritchett (1994) influentially examined the relationship between survey-reported ideal fertility and period total fertility rates. Pritchett’s analyses found that country-period by country-period differences in fertility preferences could statistically account for the majority of the variation in period total fertility rates. This result was impactful because it suggested that preferences, rather than constraints such as contraceptive access, explain fertility outcomes. However, because Pritchett’s analysis documented a correlation between two period measures, it cannot say whether a cohort of women achieves their fertility preferences, on average, over a life course. In the three decades since Pritchett’s paper, a longer span of repeated cross-section data has been collected that allows us to revisit this question with data that tracks cohorts of women as they age. In this paper, we update this evidence by examining the relationship between ideal fertility in early adulthood and completed fertility for the same cohort of women in later adulthood. We find that the prior result replicates: The relationship between fertility preferences and completed cohort fertility is, if anything, even stronger in our data.

Spatial Internet Spillovers in Manufacturing

Does local internet diffusion spur manufacturing performance in developing countries? To answer this question, we conduct instrumental variable estimations, using repeated cross-section data on 44,073 manufacturing firms from 109 developing and transition economies, and find large positive spillover effects of local email incidence on manufacturing firms sales and sales per worker. This evidence is driven by the local dissemination of email technology within industries rather than across industries. However, further analysis stresses that inter-industry spillovers are actually U-shaped, that is, negative at low email incidence rates but turning positive once incidence reaches approximately 50% of the local universe of firms. This suggests that local internet spillovers across industries are subject to network effects. Last, these threshold effects seem related to the presence of outward-oriented firms, which are known to exhibit higher digital absorptive capacity. Overall, this paper shows that local industrialisation paces may strongly diverge between poorly and highly digitalised environments.

Effect of Arsenic on Health: Evidence from Indian Districts

It is well established that consuming groundwater contaminated with arsenic can lead to diseases of the heart, blood vessels, peripheral nervous systems and skin diseases such as pigmentation change. In this article, I focus on two health outcomes—skin diseases and still births—using district-level data from India, a country with widespread arsenic contamination. Arsenic may come into human contact via direct and/or indirect channel. I intend to examine these two channels of arsenic transmission. To analyse the two-fold objectives of this study, I have used repeated cross-section data from the two health rounds of National Sample Survey Organization (60th and 71st round survey). I find a positive and statistically significant relation between skin diseases and drinking water from arsenic contaminated tube well. Similar results are found for still birth in arsenic affected areas, even after controlling for state- and district-level factors. Using odds ratio, I also find positive effect of rice consumption on skin manifestations, robust to state-fixed effects, but not district-fixed effects. Individuals are more adversely affected in terms of skin lesions and adverse pregnancy outcomes. Drinking arsenic contaminated water is a more dominant pathway than consumption of food containing arsenic, particularly rice and wheat. JEL Codes: I10, I12, Q25, Q53, Q54

The Relationship Between Subjective Wellbeing and Subjective Wellbeing Inequality: An Important Role for Skewness

We argue that the relationship between individual satisfaction with life (SWL) and SWL inequality is more complex than described by earlier research. Our measures of SWL inequality include indices designed specifically for ordinal data as well as often used (but inappropriate) measures suited to cardinal data. Using inequality indices derived by Cowell and Flachaire designed for use with ordinal data, our analysis shows that skewness of the SWL distribution, rather than inequality per se, matters for individual SWL outcomes. The empirical analysis is based on repeated cross-section data obtained from the World Values Survey. Our results are consistent with there being negative externalities for an individual’s SWL arising from people who are low in the SWL distribution, with positive externalities arising from people who are high in the SWL distribution.

Heat exposure and child nutrition: Evidence from West Africa

Extreme heat shocks are increasingly linked to poor economic and health outcomes. This paper constructs hour-degree bins of temperature exposure to assess the effects of extreme heat on early child nutrition, a health outcome correlated with educational attainment and income in adulthood. Linking 15 rounds of repeated cross-section data from five West African countries to geo-coded weather data, we find that extreme heat exposure increases the prevalence of both chronic and acute malnutrition. We find that a 2 °C rise in temperature will increase the prevalence of stunting by 7.4 percentage points, reversing the progress made on improving nutrition during our study period.

Migrant remittances and consumption expenditure under rain-fed agricultural income: micro-level evidence from Ghana

ABSTRACT Using a repeated cross-section data set from Ghana for 1991/1992, 1998/1999, 2005/2006, 2012/2013 and 2016/17, and a Two-Stage Least Squares estimator, this paper investigates the effect of agricultural income on remittances and consumption expenditure. It is found that households in Ghana use remittances to protect themselves from decline in agricultural income due to rainfall failure. The results suggest that a 100 Ghana Cedis decrease in agricultural income leads to a 30 Ghana Cedis increase in remittances. The results further posit that rainfall-induced agricultural income changes affect total consumption and food expenditures of rural households. A 100 Ghana Cedis decrease in agricultural income due to rainfall failure leads to a 60 Ghana Cedis fall in total consumption expenditure, and 36 Ghana Cedis fall in food expenditure of rural households. Very poor households in rural areas are found to be more vulnerable to such rainfall-driven agricultural income changes.

Assessing the impact of recent Venezuelan immigration on housing rents in Colombia

ABSTRACT The economic and social crisis faced by Venezuela since 2013 has led to a massive migration of its population to neighbouring countries, with Colombia being the nation that has been the most impacted. This paper estimates the impact of Venezuelan immigration on housing rents in Colombia’s main cities. Using a repeated cross-section data of Colombian households between 2013 and 2019, along with an instrumental variables approach, this study finds that a 1% increase in the proportion of Venezuelan immigrants to residents in the main cities in Colombia raises housing rents, on average, by about 1.25%.

Modelling Non-Linear Age-Period-Cohort Effects and Covariates, With an Application to English Obesity 2001–2014

Abstract We develop an age-period-cohort model for repeated cross-section data with individual covariates, which identifies the non-linear effects of age, period and cohort. This is done for both continuous and binary dependent variables. The age, period and cohort effects in the model are represented by a parametrization with freely varying parameters that separates the identified non-linear effects and the unidentifiable linear effects. We develop a test of the parametrization against a more general ‘time-saturated’ model. The method is applied to analyse the obesity epidemic in England using survey data. The main non-linear effects we find in English obesity data are age-related among women and cohort-related among men.

Rural electrification and changes in employment structure in Cambodia

Abstract This study analyzes the effects of electrification on the employment structure in Cambodia, which is still in its early stages of electrification and structural change. We examine the movement out of agriculture through three categories of nonagricultural employment: self-employment, wage employment, and unpaid work. To mitigate the problem of non-random placement of electricity, the inverse probability of treatment weighting regression adjustment (IPWRA) method is used to conduct two estimations, one with individual-level repeated cross-section data and the other with district-level panel data, taking advantage of a large and representative sample from the Cambodia General Population Census in 1998 and 2008. Our study finds that the labor movement away from agriculture is dominated by an increase in nonagricultural self-employment activities. Access to electricity increases the probability of nonagricultural self-employment for both men and women by 10–11 percentage points over a decade. We also confirm the existence of small external effects of electrification in rural Cambodia, possibly due to low electrification rates among rural households.

Doubly robust difference-in-differences estimators

This article proposes doubly robust estimators for the average treatment effect on the treated (ATT) in difference-in-differences (DID) research designs. In contrast to alternative DID estimators, the proposed estimators are consistent if either (but not necessarily both) a propensity score or outcome regression working models are correctly specified. We also derive the semiparametric efficiency bound for the ATT in DID designs when either panel or repeated cross-section data are available, and show that our proposed estimators attain the semiparametric efficiency bound when the working models are correctly specified. Furthermore, we quantify the potential efficiency gains of having access to panel data instead of repeated cross-section data. Finally, by paying particular attention to the estimation method used to estimate the nuisance parameters, we show that one can sometimes construct doubly robust DID estimators for the ATT that are also doubly robust for inference. Simulation studies and an empirical application illustrate the desirable finite-sample performance of the proposed estimators. Open-source software for implementing the proposed policy evaluation tools is available.

The demand for child care subsidies under rationing

The resources of the Child Care and Development Fund (CCDF) are insufficient to meet the increasing demand for child care subsidies caused by the 1996 welfare reform in the U.S. Since these subsidies are not an entitlement, there is rationing, i.e. not all eligible families who demand a subsidy receive one. In the presence of rationing, a combination of demand- and supply-side factors plays a role in determining subsidy utilization. Accordingly, this paper models the demand for child care subsidies under rationing as a partially strategic game among applicant mothers and local agencies, in which mothers are considering their probability of being rationed out of the subsidy when they decide whether or not to apply. I estimate the model using a Maximum Likelihood approach with repeated cross-section data from the National Survey of America’s Families. For exclusion restriction to help identify the model, I use the variation across states in the amount of pre-determined child care funding, scaled by the number of young children in each state. The results enable us to simulate the effect of different subsidy policies and to estimate the latent demand for subsidies. The latter includes families discouraged from applying who would demand a subsidy in the case of no rationing. Policy simulations suggest a latent demand 16% larger than observed demand in the sample. Even when completely eliminating rationing, a large fraction of potential beneficiaries would continue to opt out of the subsidies. Hence it is it is more affordable than might be expected to reduce the chronic underfunding of these subsidies.

Heat Exposure and Children's Nutrition: Evidence from West Africa

Growing evidence indicates extreme weather affects a variety of economic indicators. However, there is no evidence connecting temperature shocks to children’s nutritional status, an important predictor of economic outcomes in adulthood. Linking 15 rounds of repeated cross-section data from five West African countries to geo-coded weather data, we find that extreme heat exposure increases the prevalence of both chronic and acute malnutrition. Our results indicate that a 2°C rise in temperature will increase the prevalence of stunting by 3.9 percentage points in our study sample, reversing more than half of the progress made on improving nutrition during our study period.

Going with the Flow? The Effect of Economic Fluctuation on People’s Solidarity with Unemployed People

Rising levels of unemployment in European welfare states have revived questions on the social protection of the unemployed and the people’s solidarity with this claimant group. Does people’s solidarity with the unemployed—in terms of the welfare benefits they would grant this group—decrease when the economy fares ill and unemployment is on the rise, or does solidarity increase as many more people are at risk of losing their jobs? And, do changes in economic conditions and unemployment affect the solidarity of all social groups alike, or are there differences with people’s socio-economic position? In this study, we address these questions using repeated cross-section data from the Netherlands in the period 1975–2010. Our multilevel analyses show that in times of higher unemployment people’s solidarity with the unemployed is higher, while independently from that, in times of economic downturn solidarity is lower. These macro-level effects vary only little across social groups, yet we do find that the unemployment rate affects people’s solidarity more positively during economic good times. This indicates that people’s solidarity with the unemployed depends, among others, on the specific macro-economic constellation of economic welfare and unemployment.

The impact of the action plan for promoting employment and combating unemployment on employment informality in Algeria

ABSTRACTThis paper examines whether the Action Plan for Promoting Employment and Combating Unemployment, a labor market intermediation program adopted by the Algerian government in 2008, reduced the informality of employment in Algeria. Using repeated cross-section data from the Household Survey on Employment for the period from 1997 to 2013, and a difference-in-difference methodology, we estimate whether the Action Plan has reduced the probability that workers are employed informally in enterprises of more than 5 workers – the type of enterprise that is most likely to be directly affected by the Action Plan. Our results show that the Action Plan has in fact contributed to reducing employment informality in such enterprises, but with heterogeneous effects. More precisely, it reduced informality for employees of establishments of 10 workers or more but had no significant effects on informality for those working in enterprises of 5 to 9 workers. Furthermore, when we restrict our estimates to new entrants only, we do not find statistically significant effects.

Transporte y calidad de vida urbana. Estudio de caso sobre el Metroplús de Medellín, Colombia

This paper aims to establish the impact of the bus rapid transit system of Medellin, Colombia, on the urban quality of life (UQL), measured as the contribution of the amenities available in each neighborhood to the welfare of its residents. To this end, repeated cross-section data from the Encuesta de Calidad de Vida de Medellin for 2010 and 2014 and information on the neighborhood amenities are used. As a whole, the research considered 4,091 observations in 2010 and 4,219 in 2014. Through the estimation of a quasi-experimental hedonic model, the amenities with significant coefficients were identified to calculate a UQL index. The findings suggest that the implementation of the Metroplus had a positive and significant effect on changes in the UQL during the period 2010-2014. The magnitude of the effect shows differences in the results across the urban area.

The Wall’s Impact in the Occupied West Bank: A Bayesian Approach to Poverty Dynamics Using Repeated Cross-Sections

In 2002, the Israeli government decided to build a wall inside the occupied West Bank. The wall had a marked effect on the access to land and water resources as well as to the Israeli labour market. It is difficult to include the effect of the wall in an econometric model explaining poverty dynamics as the wall was built in the richer region of the West Bank. So a diff-in-diff strategy is needed. Using a Bayesian approach, we treat our two-period repeated cross-section data set as an incomplete data problem, explaining the income-to-needs ratio as a function of time invariant exogenous variables. This allows us to provide inference results on poverty dynamics. We then build a conditional regression model including a wall variable and state dependence to see how the wall modified the initial results on poverty dynamics. We find that the wall has increased the probability of poverty persistence by 58 percentage points and the probability of poverty entry by 18 percentage points.

The economic response of rural areas to local supply shock: evidence from the Occupied West Bank

ABSTRACTAs the Second Intifada broke out at the end of 2000, Israel severely restricted entry for Palestinians to its labor market, forcing a great section of commuters to return to their local labor markets. This paper examines the economic effect of the return commuting on non-commuters in rural areas of the Occupied West Bank. Utilizing place-of-work, repeated cross-section data, the results show that returned commuting has negative repercussions. Specifically, wages decrease for workers with the same skill type (low skilled). The results also provide evidence that favors the crowd-out effect hypothesis. The estimated probability of unemployment increases for non-commuters with disproportionate effect for job seekers relative to those reportedly employed. Consistent with this result, increases in return commuting prolong unemployment duration for the low skilled. The outcome of this paper helps understand how rural labor markets may respond to labor supply shocks.

Doubly Robust Difference-in-Differences Estimators

This article proposes doubly robust estimators for the average treatment effect on the treated (ATT) in difference-in-differences (DID) research designs. In contrast to alternative DID estimators, the proposed estimators are consistent if either (but not necessarily both) a propensity score or outcome regression working models are correctly specified. We also derive the semiparametric efficiency bound for the ATT in DID designs when either panel or repeated cross-section data are available, and show that our proposed estimators attain the semiparametric efficiency bound when the working models are correctly specified. Furthermore, we quantify the potential efficiency gains of having access to panel data instead of repeated cross-section data. Finally, by paying particular attention to the estimation method used to estimate the nuisance parameters, we show that one can sometimes construct doubly robust DID estimators for the ATT that are also doubly robust for inference. Simulation studies and an empirical application illustrate the desirable finite-sample performance of the proposed estimators. Open-source software for implementing the proposed policy evaluation tools is available.

The Vaccination Kuznets Curve: Do vaccination rates rise and fall with income?

This paper presents a new stylized fact about the relationship between income and childhood vaccination. It shows vaccination rates first rise but then fall as income increases. This pattern is observed in WHO country-level panel data, and in US county-level panel and individual-level repeated cross-section data. This data pattern suggests that both low and high-income parents are less likely to follow the standard vaccination schedule, and that such behavior is reflected in the vaccination rate at the population level. I provide several alternative explanations as to why we observe this data pattern, including avoidance measures, medical care, and social segregation.

Estimation of unobserved dynamics of individual partisanship: a Bayesian approach

Political party preference is a crucial element in the analysis of economics and political science. However, it is often difficult to investigate the dynamic properties of the individual partisanship due to inaccessibility to panel data. This study proposes a Bayesian approach for estimating Markov dynamics of individual-level partisanship with repeated cross-section data in which the history of respondents’ choice of favored party cannot be observed. The proposed approach identifies individual heterogeneities that affect transitional patterns of partisanship, and replicates the dynamic patterns of individual partisan mobility. Using the proposed method with American survey data, the study shows that age, education and race significantly influence partisan dynamics among Americans over a three-decade period from 1972.