Dissertations / Theses on the topic 'Stochastic Dominance Approach'

Chapter 1: The Impact of Culture on the Second-Generation Immigrants’ Level of Trust in Canada Trust is one of the main elements of social capital; it determines the extent to which an individual cooperates with others. In this chapter, I assess whether cultural factors influence the level of trust in the population of second-generation immigrants in Canada. This paper is related to two strands of empirical literature. The first analyses the determinants of trust and the second studies the cultural transmission of values, attitudes and beliefs. I follow closely the literature on the cultural transmission and use an epidemiological approach to assess whether trust of second-generation immigrants is affected by their cultural heritage. This approach consists of comparing information about the outcomes of second-generation immigrants with that of the country of origin of their ancestry. We apply this approach using the Ethnic Diversity Survey (EDS), the World Value Survey (WVS) and the European Value Survey (EVS). Estimation results show that the average level of trust in the countries of origin of the ancestors of the second-generation immigrants has a strong significant impact on their level of trust. Thus, individual whose country of ancestry displays a high level of trust, tend to have a high level of trust. This provides evidence that individuals’ level of trust is not only explained by their personal experiences, characteristics, and the environment in which they live; but also by the culture in their country of ancestry. This means that culture does matter! I find that the results remain robust even if certain key countries are omitted or a different data set is used. Chapter 2: Decomposing Health Achievement and Socioeconomic Health Inequalities in Presence of Multiple Categorical Information This chapter presents a decomposition of the health achievement and the socioeconomic health inequality indices by multiple categorical variables and by regions. I adopt Makdissi and Yazbeck's (2014) counting approach to deal with the ordinal nature of the data of the United States National Health Interview Survey 2010. The findings suggest that the attributes that contribute the most to the deviation from perfect health in the United States are: anxiety, depression and exhaustion. Also, I find that the attributes that contribute the most to the total socioeconomic health inequality are ambulation, depression and pain. The regional decomposition results suggest that, if the aversion to socioeconomic health inequality is high enough, socioeconomic health inequalities between regions are the main contributors to the total socioeconomic health inequality in the United States. Chapter 3: Accounting for Freedom and Economic Resources in the Assessment of Changes in Women Poverty in Sub-Saharan Africa This chapter assesses the importance of freedom in women’s wellbeing in twelve Sub-Saharan Africa countries by using data from Demographic Health Surveys. This paper presents a poverty comparison by using the stochastic dominance approach and relies on the economic resources and freedom as the two aspects of wellbeing which evokes the multidimensionality of poverty. This study is related to the following three pieces of literature: the sequential stochastic dominance, the multidimensional poverty, the Sen’s capability approach which is based on freedom. This paper is built on Makdissi et al. (2014) but differs from it in a number of respects. First, it focuses on poverty instead of welfare. Secondly, it applies the Shapley decomposition to determine the contributions of the economic resource distribution and the incidence of the threat of domestic violence to poverty changes over time. Consistent with previous work on the importance of freedom, I find that more freedom, i.e. less threat of domestic violence, affects women’s wellbeing positively since it decreases women’s poverty. The results indicate that women’s wellbeing has improved in Burkina Faso, Ghana, Kenya, Lesotho, Madagascar, Malawi, Rwanda, Senegal, and Zimbabwe and deteriorated in Ethiopia, Nigeria and Tanzania.

In this dissertation we study several non-convex and stochastic optimization problems. The common theme is the use of mixed-integer programming (MIP) techniques including valid inequalities and reformulation to solve these problems. We first study a strategic capacity planning model which captures the trade-off between the incentive to delay capacity installation to wait for improved technology and the need for some capacity to be installed to meet current demands. This problem is naturally formulated as a MIP with a bilinear objective. We develop several linear MIP formulations, along with classes of strong valid inequalities. We also present a specialized branch-and-cut algorithm to solve a compact concave formulation. Computational results indicate that these formulations can be used to solve large-scale instances. We next study methods for optimization with joint probabilistic constraints. These problems are challenging because evaluating solution feasibility requires multidimensional integration and the feasible region is not convex. We propose and analyze a Monte Carlo sampling scheme to simplify the probabilistic structure of such problems. Computational tests of the approach indicate that it can yield good feasible solutions and reasonable bounds on their quality. Next, we study a MIP formulation of the non-convex sample approximation problem. We obtain two strengthened formulations. As a byproduct of this analysis, we obtain new results for the previously studied mixing set, subject to an additional knapsack inequality. Computational results indicate that large-scale instances can be solved using the strengthened formulations. Finally, we study optimization problems with stochastic dominance constraints. A stochastic dominance constraint states that a random outcome which depends on the decision variables should stochastically dominate a given random variable. We present new formulations for both first and second order stochastic dominance which are significantly more compact than existing formulations. Computational tests illustrate the benefits of the new formulations.