Brice Romuald Gueyap Kounga

This paper studies identification and estimation in semiparametric logit models when social networks are endogenous. In many applications, unobserved individual traits shape both the outcome of interest and the formation of social ties, so standard logit specifications, including those augmented with common network controls, can be biased. I show how network data can be used to address this endogeneity without imposing a parametric structure on the link formation process. Although the outcome equation is semiparametric in this social component and the network formation process is left unspecified, the logistic distribution assumption is crucial for identification. I show that slope parameters are point identified by pairwise comparisons of agents who share identical network formation behavior. I propose feasible estimators based on matching agents using network similarity measures and establish their consistency and asymptotic normality. Monte Carlo simulations demonstrate good finite-sample performance, and an empirical application to microfinance adoption demonstrates that accounting for endogenous network formation materially affects estimated covariate effects.

This paper establishes the identification and provides an estimation algorithm of a nonparametric dyadic regression model where the unknown structural function is nonseparable, and the distribution of the unobservable random terms is assumed to be unknown. The identification and the estimation of the distribution of the unobservable random term are also proposed. I assume that our structural function is left-continuous and weakly increasing in the unobservable random terms. Moreover, I propose suitable normalization for the identification by allowing the structural function to have some desirable properties such as homogeneity of degree one in the unobservable random term and some of its observables. I conclude this study by assessing the finite sample properties of the proposed estimators in a Monte-Carlo simulation.

Trust is increasingly perceived as having a significant effect on trade, public goods provision, conflict resolution and even democratic consolidation. Using individual data from Afrobarometer survey rounds 6 and 7 in Africa, I find that citizens originated from the anglophone countries are more likely to trust local leaders than those originated from the francophone countries. Systematic tests of this finding are complicated by unobserved heterogeneity among nations due to variable pre- and post-colonial histories. In order to address endogeneity issues, I focus on Cameroon which includes regions colonized by both Britain and France, and I exploit the natural experiment provided by the anglophone-francophone border to identify the long term effects, if any, of both English and French colonization on trust using regression discontinuity on observations near the border. I show that regions on the British side of discontinuity have higher levels of trust toward local leaders. Although the ability to identify causal mechanisms is limited, the evidence suggests that communities on the British side have benefited from a policy of indirect rule and the lack of forced labor, which has produced stronger local institutions.

To what extent can Africa’s present-day ethnic-based discrimination be traced back to its colonial policies? This paper investigates the enduring impact of British colonial policies on ethnic discrimination in West Africa. Using individual data from Afrobarometer surveys rounds 7 and 8, covering 31 African countries, we examine whether the British Indirect Rule system has contributed to current levels of ethnicity-based discrimination. Our findings reveal that individuals in former British colonies are significantly more likely to experience ethnic discrimination.