Evaluating Social Policy by Experimental and Nonexperimental Methods

Although it is important to establish causal relationships in social policy evaluation, the effects are difficult to observe due to sample selection. To evaluate the performance of estimators designed to handle sample selection bias, we analyse data from a Norwegian rehabilitation project with a randomised experimental design. The data permit us to compare the performance of different nonexperimental estimators with the experimental results. In our case study we find that nonexperimental evaluation based on sample selection estimators with selection terms that fail to meet conventional levels of statistical significance is highly unreliable. The difference in difference estimator and propensity score matching estimators perform better in our context.
JEL classification : C 51; J 24; H 43; I 12     

The negative consequences of school bullying on academic performance and mitigation through female teacher participation: evidence from Ghana

Exploiting data from Ghanaian schools’ eighth grade students collected in 2011, we estimate the causal effects of school bullying on academic achievement and gender-based mitigating approaches by using propensity score matching (PSM) and doubly robust (DR) estimator approach. We find that students victimized by bullying score at least 0.22 standard deviation lower than their peers in a standardized mathematics examination. Meanwhile, we document that the effect of bullying is significantly attenuated in the presence of female teachers in the classroom. These results hold through a set of robustness checks including placebo regressions and matching quality test. We explain the results through gender difference in teaching paradigm and conclude that a feminine management approach in class is required to reduce the effect of bullying.     

Impact of innovation policies on small,medium and large Brazilian firms

This study comprises a comparative examination of the effects of innovation support programmes’ spend on innovative activities in small, medium and large Brazilian firms. The econometric methodology propensity score matching is used to assess the impacts of tax and financial incentives based on. Results show that innovation support programmes stimulate expenditure on innovative activities, especially financial incentives for the acquisition of machinery and equipment.     

Remittances and household expenditure behaviour: Evidence from Senegal1

We use different econometric techniques, from propensity score matching to multinomial treatment methods, to assess the impact of internal and external remittances on several household budget shares in Senegal. When only considering the average impact of remittances on the household expenditure behaviour, we find an overall productive use of remittances. However, the impact of remittances disappears when the marginal spending behaviour is considered, i.e., households do not show a different consumption pattern with respect to their remittance status. The marginal spending behaviour therefore suggests that, in the decision on how to allocate expenditure, remittances are treated just as any other source of income.     

Imports and TFP at the firm level: the role of absorptive capacity

This paper estimates the effect of the decision to import intermediate goods and capital equipment on Total Factor Productivity (TFP) at the firm level on a panel of Spanish firms (1991–2002). We use two alternative approaches. In the first, we estimate TFP and apply a diff‐in‐diff estimator with a control group constructed by propensity‐score matching. In the second, direct method, we estimate TFP with imported inputs as a state variable in one stage. Both approaches show that the effect of a firm's decision to source intermediates and capital equipment abroad on its TFP depends critically on its capacity to absorb technology, measured by the proportion of skilled labour.     

不同融资约束背景下政府研发补助效应研究

运用倾向得分匹配法检验了政府研发补贴对企业自身研发投入的影响,以及不同融资约束背景下政府研发补贴诱导效应的差异。实证结果显示,政府研发补贴对企业自身研发投入具有诱导作用;在强融资约束背景下,政府研发投入补助能够更有效地刺激企业加大自身研发力度,诱导效应更强。     

Is inflation targeting or the fixed exchange rate more effective for attracting FDI into developing countries?

This article investigates which monetary policy regime – inflation targeting or the fixed exchange rate – is more effective for attracting FDI inflows into developing countries. Using propensity score matching and the difference-in-differences estimator, we find no evidence that adopting an inflation targeting regime would be more effective than adopting a fixed exchange rate, and vice versa, in encouraging FDI inflows.     

The implications of the US renewable fuel standard programme for farm structure

We investigate the impact of the 2005 Renewable Fuel Standard (RFS) on farm structure, particularly farm size. We rely on the salience of a new ethanol plant in a farmers’ local neighbourhood to identify the impact of the RFS mandate on these spatially advantaged farms. To control for the nonrandom selection of ethanol production facilities, we utilize a propensity score matching estimator, and to remove impact of farm-level or market shifting unobservables resulting from shifts in commodity prices we employ a difference-in-difference (DD) matching approach. We estimate the treatment effect of an ethanol production facility on farm size prior to the RFS mandate and after the RFS programme. The effect of the RFS policy on farm size is obtained as the difference between these two DD matching estimators. Overall, our results suggest that the RFS programme raised the probability of farm size increase by roughly 12–18%, on average, for farms located within a 30-mile radius of new ethanol plants. In addition, the programme contributed to a net increase in farm size of 25–32%, on average, for those spatially advantaged farms.     

The impact of foreign takeovers: comparative evidence from foreign and domestic acquisitions in Germany

This study provides the first evidence of foreign takeover effects on the performance of acquired firms in Germany that considers a general takeover effect through the comparison with domestic takeovers. A propensity score matching approach combined with a difference-in-differences (DiD) estimator were performed with new high-quality panel data for manufacturing enterprises, provided by German official statistics. The results indicate a negative impact of foreign takeovers on employment and no productivity improvements for the period 2007–2009. This evidence contradicts existing empirical evidence for Germany which suggests significant productivity improvements and no changes in terms of employment. These findings are of particular interest to Germany as one of the most important FDI inflow destinations worldwide. They contribute to the foreign ownership performance premium literature as well as improving the understanding of foreign acquisition consequences, a subject of utmost topicality.     

Demographic responses to a political transformation: Evidence of women’s empowerment from Nepal

During the 2006 Democratic Movement in Nepal, the parliament unanimously decided to strip the over two century-old Shah monarchy of absolute power. We study the short-run effects of the arrival of democracy on different measures of women’s empowerment by exploiting exogenous variation in the government through abolition of the monarchy. This paper employs a propensity score matching estimator to evaluate the linkage between change in political regime and opinions related to women’s empowerment from 2006 Nepal Demographic and Health Surveys (NDHS). Results show that women’s say in decision making increased significantly, and opinions on violence against women strengthened. We further scrutinize the treatment effect estimates with Rosenbaum bounds and observe if they are sensitive to possible hidden selection bias. We also test for heterogeneity of the treatment effect across gender and find that males report higher probability of mutual household decision-making among couples than females.     

Innovation,complementarity, and exporting. Evidence from German manufacturing firms

This paper assesses whether there might be complementarities between different types of innovation activities (product, process and organizational) and how these effects may be linked to the likelihood that a firm will export. Complementarity is addressed through the properties of supermodular functions, and firm heterogeneity by export destination is explored. A new econometric strategy to test for pairwise complementarity in a function with three independent variables and a binary dependent variable is proposed. Exogenous and endogenous innovation variables are considered by using bootstrapping for hypothesis testing, propensity score matching and treatment effects models. The empirical analysis shows that complementarity relationships between innovation strategies are more likely to exist when firms export to multiple foreign markets.     

Participation in school-sponsored sports and academic spillovers: new evidence from the early childhood longitudinal survey

The link between participation in school-sponsored sports and academic performance has been studied extensively in the literature. Whilst previous studies tend to show positive academic spillovers, it remains unclear whether these positive associations are primarily driven by selection into sports. We investigate this issue using data on middle school children drawn from the Early Childhood Longitudinal Study, Kindergarten Class of 1998–1999. Due to the lack of credible instrumental variables for sports participation, we establish bounds for the relationship between school sports and academics using a combination of the propensity score matching method and an approach that uses selection on observed factors as a guide to selection on unobserved factors. We find that the association between participation in school-sponsored sports and academic performance as measured by standardised test scores in reading, math and science ranges from null to negative. Overall, our results suggest that failure to account for selection may result in a misleading positive correlation between sports participation and academic performance.     

How not to measure sustainable value (and how one might)

Sustainability is a complex multidimensional concept that entails economic, environmental, and social aspects. The sustainable value (SV) method developed by F. Figge and T. Hahn [Ecol. Econ. 48(2004) 173-187] is one of the most promising attempts to measure sustainability performance of firms. SV measures corporate contributions to sustainability by valuing resource use based on the opportunity cost, which must be estimated. This paper critically examines Figge and Hahn's estimator for opportunity cost, and shows that the proposed estimator rests on a number of strong, unrealistic assumptions. Evidence from Monte Carlo simulations conducted by authors shows that the proposed estimator performs very poorly even under ideal conditions. Having identified shortcomings in the SV method, we review some econometric approaches with a proven statistical foundation, which might be usefully applied in the present context.     

Democratization and Real Exchange Rates,

In this article, we combine two so far separate strands of the economic literature and argue that democratization leads to a real exchange rate appreciation. We test this hypothesis empirically for a sample of countries observed from 1980 to 2007 by combining a difference‐in‐difference approach with propensity score matching estimators. Our empirical results reveal a strong and significant finding: democratization causes real exchange rates to appreciate. Consequently, the ongoing process of democratization observed in many parts of the world is likely to reduce exchange rate distortions.     

To engage or not to engage in corporate social responsibility: Empirical evidence from global banking sector

Whether or not banks should engage in corporate social responsibility (CSR) activities is controversial because of the concomitant high cost even if banks could enjoy the benefits of a higher income as a result of their good reputation. Faced with this dilemma, bank managers are hesitant to engage in CSR. This study pursues this issue by examining whether or not banks engaging in CSR can bring profits and reduce non-performing loans. We apply three novel estimation methods to obtain the unbiased and full-blown CSR effect. The first two methods are matching methods, namely, conventional propensity score matching method and nearest-neighbor variance bias-corrected matching method (nn-VBC). The third method is Heckman's two-step method in switching regression. Regardless of the methods used, CSR banks overwhelmingly outperform non-CSR banks in terms of return on assets and return on equity. Our study offers policy suggestions for both government regulators and bank managers.     

Is the model “loans‐plus‐savings” better for microfinance in Eastern Europe and Central Asia? A propensity score matching comparison

Microfinance institutions are gradually evolving into multiservice organizations offering not only loans but also savings, and other financial and nonfinancial services. We contribute to the literature aimed at identifying how combining credit with savings affects outreach and sustainability in microfinance institutions (MFIs). We apply the propensity score matching method as well as its augmented dose–response version to compare the performance of loans‐plus‐savings MFIs with that of lending‐only in a sample of 710 observations from Eastern Europe and Central Asia. Owing to our unique capital structure data, we control for the use of subsidized capital, which related work ignores while existing evidence points to tradeoffs between subsidies and savings. We find that financial performance and breadth of outreach are positively associated with savings mobilization, while the evidence on depth of outreach points to a possible mission drift.     

THE ESTIMATED EFFECT OF CATHOLIC SCHOOLING ON EDUCATIONAL OUTCOMES USING PROPENSITY SCORE MATCHING

This paper examines the effect of attending a Catholic high school on educational outcomes. The statistical analysis is based on data obtained from the US National Educational Longitudinal Study. Using propensity score matching methods to control for selection bias, we find that Catholic schooling improves maths test scores, with stronger effects for males than for females, but appears to have little effect (if any) on reading scores. Catholic schooling also raises high school graduation rates and substantially increases the likelihood of enrolment in a 4‐year college. Use of the difference‐in‐difference method suggests that the effect of Catholic schooling on changes in maths scores is more muted, though still statistically significant.     

DOES TRADE ADJUSTMENT ASSISTANCE MAKE A DIFFERENCE?

The U.S. Trade Adjustment Assistance (TAA) program provides workers who have lost their jobs due to increased trade with income support and training, job search, and relocation benefits. This paper uses data collected by the Department of Labor on TAA beneficiaries to provide the most recent econometric evaluation of the effectiveness of the TAA program. Summary statistics suggest that the TAA program successfully targets displaced workers who have a greater difficulty finding new employment. However, using propensity score matching techniques we find that while the required training component of the program improves the employment outcomes of beneficiaries, on average the TAA program has no discernible impact on the employment outcomes of the participants. (JEL F16)     

An evaluation of government- sponsored vocational training programmes for the unemployed in urban Russia

This is the first study on the effects of active labour marketprograms such as training in Russia. We use the data from theofficial unemployment register combined with information fromthe follow-up survey in a large industrial city in the year2000. The method of propensity score matching was applied tolearn whether participation in the training programmes increasedthe monthly salaries of participants. The findings suggest thatindividuals tend to benefit from the participation in the trainingprogrammes. However, one year later, this effect disappeared.     

Estimating the causal effect of fertility on economic wellbeing: data requirements, identifying assumptions and estimation methods

This article aims to answer to what extent fertility has a causal effect on households’ economic wellbeing—an issue that has received considerable interest in development studies and policy analysis. However, only recently has this literature begun to give importance to adequate modelling for estimation of causal effects. We discuss several strategies for causal inference, stressing that their validity must be judged on the assumptions we can plausibly formulate in a given application, which in turn depends on the richness of available data. We contrast methods relying on the unconfoundedness assumption, which include regressions and propensity score matching, with instrumental variable methods. This discussion has a general importance, representing a set of guidelines that are useful for choosing an appropriate strategy of analysis. The discussion is valid for both cross-sectional or panel data.