Search results

Research on strategic choices available to the firm are often modeled as a limited number of possible decision outcomes and leads to a discrete limited dependent variable. A limited dependent variable can also arise when values of a continuous dependent variable are partially or wholly unobserved. This chapter discusses the methodological issues associated with such phenomena and the appropriate statistical methods developed to allow for consistent and efficient estimation of models that involve a limited dependent variable. The chapter also provides a road map for selecting the appropriate statistical technique and it offers guidelines for consistent interpretation and reporting of the statistical results.

This chapter examines the impact of price fluctuations in foreign stock markets on the stock prices of domestic banks in Korea, Malaysia, Singapore, and Thailand. Some studies have argued that the 2007–2009 global financial crisis (GFC) affected domestic banks less in East Asia, even though the supporting evidence is rather limited. Employing a multinomial logit model, we estimate how changes in the United States and Japanese stock markets affected the banking sectors in the sampled countries before the 1997 Asian financial crisis, and before and during the more recent GFC. We interpret the number of banks in a given country that experienced a large price shock on the same day (or “coexceedance”) as shocks to the domestic banking sector. The results suggest that fluctuations in foreign stock market indices exerted a larger impact on the prices of East Asian banking stocks during the 2000s than during the 1990s. In addition, although the shocks brought about by the deterioration of foreign stock markets were significant before the GFC, both increases and decreases in foreign stock prices significantly affected the banking sectors of the respective countries during the crisis. Lastly, we conclude that increasing foreign capital flows and foreign assets and liabilities greatly influenced domestic banking systems in East Asia during the 2000s.

As a field, we should put more emphasis on interpreting the magnitude of coefficient estimates rather than only assessing statistical significance. To support this claim, I demonstrate how focusing only on statistical significance can lead to incorrect and incomplete conclusions in many common applications of the linear regression model. Moreover, I demonstrate why interpreting coefficient estimates in common non-linear estimators (e.g., probit, logit, Poisson, and negative binomial estimators) requires additional care compared to the linear regression model.

This chapter enquires whether family migration experience affects the probability of high school graduation of children once unobserved heterogeneity is properly accounted for. Bivariate dynamic random effects probit models for cluster data are estimated to control for the potential endogeneity of education and migration outcomes of elder members of a family in a regression for the education and migration of younger children. Correlation of unobservables across migration and education decisions as well as within groups of individuals such as the family are explicitly modeled. Results show that children from households headed by a migrant are less likely to graduate from high school than children from households headed by a non-migrant. However, as the number of migrants in the family increase, a larger number of migrants in the family is associated with a higher probability of graduation from high school in México. Negative migrant selection in unobservables is detected.

We examine the effect of borrowing constraint facing new immigrants on the process of their assimilation in the new society. We shall do so in a two-period model. In period 1, immigrants invest, with some costs to them, in trying to assimilate. The probability of success in this endeavor depends on the amount invested and also on the level of the provision of a “public” good paid for by lump-sum taxation of “natives”. Those who succeed enjoy a higher level of productivity and therefore wages in period 2. The level of investment is endogenously determined. Assimilation also affects remittances by immigrants. Given this framework, we examine the effect of public support on the degree of assimilation and income repatriation. We do so under two scenarios regarding the credit market facing new immigrants. In the first, they can borrow as much as they want in period 1 at an exogenously given interest rate. In the second scenarios, there is a binding borrowing constraint. We compare the equilibrium under the two scenarios.

In this paper, we study partial identification of the distribution of treatment effects of a binary treatment for ideal randomized experiments, ideal randomized experiments with a known value of a dependence measure, and for data satisfying the selection-on-observables assumption, respectively. For ideal randomized experiments, (i) we propose nonparametric estimators of the sharp bounds on the distribution of treatment effects and construct asymptotically valid confidence sets for the distribution of treatment effects; (ii) we propose bias-corrected estimators of the sharp bounds on the distribution of treatment effects; and (iii) we investigate finite sample performances of the proposed confidence sets and the bias-corrected estimators via simulation.

Within the framework of potential efforts and strategies to employment generation for young people in Africa in general and Ethiopia in particular, the agricultural sector is increasingly considered as an important sector and a valuable means for poverty reduction, the promotion of economic development, and youth's economic independence. Renewed hope is placed on the sector to offer sustainable livelihood prospects for the rural youth. Yet, the success and sustainability of the sector require a proper understanding of how households allocate youth labor time in the sector and whether agricultural labor supply is responsive to economic incentives such as shadow wages. Using gender- and age-specific plot-level panel data, we systematically analyze the impacts of shadow wages of each household member on youth agricultural labor supply across types of farms. The results indicate that agricultural shadow wages matter for the youth's labor supply in the sector, but the impact differs for male and female youth. We also show that trends and patterns of youth labor supply vary across gender and whether they work on their own farm, and so do their labor returns. The results are consistent after controlling for individual heterogeneity and instrumenting for possible endogeneity. Taking into account the intensity of youth's actual involvement in the family farm, own farm or off-farm work instead of their stated intentions, the results challenge the presumption that youth are abandoning agriculture, at least in agricultural potential areas of Ethiopia. Instead, the frequent narrative of youth disengaging from agriculture may be a result of methodological flaws or data limitations. The findings suggest that it is necessary to invest in agricultural development to enhance labor productivity and employability of young people in agriculture.

This chapter examines the evolution of the number of days spent on sick leave following the 2011 reform which halved the maximum sick benefit provided by statutory health insurance in Hungary. This policy change sharply decreased benefits for a large group of high earners, while leaving the incentive to claim sickness benefits unchanged for lower earners, providing us with a “quasi-experimental” setup to identify the incentives effect of sickness benefits. We use a difference-in-differences type methodology to evaluate the short-term effect of the reform. We rely on high-quality administrative data and analyze a sample comprised of prime-age male employees with high earnings and stable employment. Our results show that the number of days spent on sick leave fell substantially for those experiencing the full halving of benefits. Estimating the response of the number of sick days with respect to the fall in potential sickness benefits, we find a significant elasticity of −0.45.