We use an equivalent form of Markowitz's mean-variance utility function, based on Rao's Quadratic Entropy (RQE), to enrich the standard capital asset pricing model (CAPM), both in the presence and in the absence of a risk-free asset. The resulting equilibrium, which we denote RQE-CAPM, offers important new insights about the pricing of risk. Notably, it reveals that the reason for which the standard CAPM does not price idiosyncratic risk is not only because the market portfolio is law of large numbers diversified but also because the model implicitly assumes agents' total risk aversion and their correlation diversification risk preference balance each other exactly. We then demonstrate that idiosyncratic risk is priced in a general RQE-CAPM where agents' total risk aversion and their correlation diversification risk preference coefficients are not necessary equal. Our general RQE-CAPM therefore offers a unifying way of thinking about the pricing of idiosyncratic risk, including cases where such risk is negatively priced, and is relevant for the literature assessing the idiosyncratic risk puzzle. It also provides a natural theoretical underpinning for the empirical tests of the CAPM or the pricing of idiosyncratic risk performed in some existence studies.
 

Why do some societies embrace innovative technologies, policies, and ideas, while others are slow to adopt, or even resist, them? We focus on features of an innovation that are expected to affect the incumbent elite’s economic activities, and hence the elite’s reaction. The elite can choose whether to appropriate the innovation for itself; encourage its adoption; tax, regulate, or limit or block it. Six features of the innovation affect the elite response: i) whether it is easy to replicate; ii) whether it complements or competes with the elite’s sources of income; iii) whether its impact is broad or narrow; iv) whether it is location-dependent, and v) concealable; vi) whether it requires large fixed costs. Some of these factors have been considered in other work; here we assess them together. We provide illustrative evidence of the relevance and generality of the model to understand the fate of a variety of innovations.
 

We study the social integration of ethnic minority children in the context of an early childhood program conducted in Turkey aimed at preparing 5-year-old native and Syrian refugee children for primary school. We randomly assign children to groups with varying ethnic composition and find that exposure to children of the other ethnicity leads to an increase in the formation of interethnic friendships, especially for Turkish children. We also find that the Turkish language skills of Syrian children are better developed in classes with a larger presence of Turkish children. We then develop a model of friendship formation with two key mechanisms: preference bias and congestion in the friendship formation process. Structural estimation of the model suggests that interethnic exposure reduces the share of own-ethnicity friends (homophily) and has a non-monotonic effect on the propensity to form own-ethnicity friendships beyond what would be expected given the size of the group (inbreeding homophily). Counterfactual analysis indicates that improvement in the language skills of Syrian children can offset more than half of the effect that ethnic bias has on friendship formation patterns. Finally, we find that for Syrian children exposure to Turkish children in the pre-school program has a long-term effect on primary school absenteeism.
 

Increasing evidence suggests that incarceration, under certain circumstances, can improve inmates’ social reintegration upon release. Yet, the mechanisms through which incarceration can lead to successful rehabilitation remain largely unknown. This paper finds that participation in social rehabilitation programs while incarcerated can significantly reduce recidivism. This result is entirely driven by inmates whose risk and needs were evaluated by a widely used assessment tool identifying their criminogenic needs. For this group, we estimate that participation in these programs reduces recidivism by about 9 percentage points within three years following release. Our results suggest targeting criminogenic needs is crucial for successful rehabilitation. We also find considerable heterogeneous program treatment effects: inmates with a high overall risk score, or who exhibit procriminal attitudes, benefit little if at all from program participation. We investigate the stability of the treatment effect coefficients and conclude they unlikely suffer from an omitted variable bias.

We analyze the interactions between social norms, the prevalence of regulated acts, and  policies. These interactions are impacted by people’s inability to directly observe actors’ behavior. Norms are ineffctive incentivizers when acts are committed either very frequently or very infrequently, because noisy signals of behavior are then too weak to alter people’s beliefs about others’ behavior. This cuts against the dynamics of the ‘honor-stigma’ model (Bénabou and Tirole 2006, 2011) and reverses its implications with even moderately noisy signals. With unobservable acts, the review process through which incentives are provided becomes an additional policy variable whose optima we characterize.
 

We examine both theoretically and empirically how migration affects cultural change in home and host countries. Our theoretical model integrates various compositional and cultural transmission mechanisms of migration-based cultural change for which it delivers distinctive testable predictions on the sign and direction of convergence. We then use the World Value Survey for the period 1981-2014 to build time-varying measures of cultural similarity for a large number of country pairs and exploit within country-pair variation over time. Our evidence is inconsistent with the view that immigrants are a threat to the host country’s culture. While migrants do act as vectors of cultural diffusion and bring about cultural convergence, this is mostly to disseminate cultural values and norms from host to home countries (i.e., cultural remittances).
 

Is culture a determinant of a jurisdiction’s comparative advantage? U.S. states that display a high level of generalized trust specialize in more “complex” industries that use contracts more intensively in their input-output relationships. This pattern is not driven by differences in states’ other observable characteristics or by unobservable time-varying industry- or state-specific factors, and it does not reflect selection by export destination. Theoretical considerations suggest that trust may be endogenous to the location of complex industries. An instrumental variable strategy that leverages the contemporary trust impact of historical racial discrimination confirms that trust factors into the comparative advantage of U.S. states.
 

Having young children can push women into self-employment to reconcile the demands of motherhood with their professional ambitions. However, if self-employment offers very few opportunities for decent pay and access to wage employment depends on education, then, motherhood may no longer matter to women’s self-employment. In this paper, we formalize this idea theoretically and test it empirically using data from Nigeria. We use an identification strategy that corrects selection bias and the endogeneity of fertility jointly. We find no evidence of a causal effect of motherhood on women’s self-employment. This result is robust to several alternative specifications. However, we also find that motherhood increases the probability of self-employment for single women but not for married women. These findings suggest that the social setting governs the importance of motherhood for women’s self-employment.
 

Background: Adult studies have shown that nursing overtime and unit overcrowding is associated with increased adverse patient events but there exists little evidence for the Neonatal Intensive Care Unit (NICU).

Objectives: To predict the onset on nosocomial infections and medical accidents in a NICU using machine learning models.

Subjects: Retrospective study on the 7,438 neonates admitted in the CHU de Québec NICU (capacity of 51 beds) from 10 April 2008 to 28 March 2013. Daily administrative data on nursing overtime hours, total regular hours, number of admissions, patient characteristics, as well as information on nosocomial infections and on the timing and type of medical errors were retrieved from various hospital-level datasets.

Methodology: We use a generalized mixed effects regression tree model (GMERT) to elaborate predictions trees for the two outcomes. Neonates’ characteristics and daily exposure to numerous covariates are used in the model. GMERT is suitable for binary outcomes and is a recent extension of the standard tree-based method. The model allows to determine the most important predictors.

Results: DRG severity level, regular hours of work, overtime, admission rates, birth weight and occupation rates are the main predictors for both outcomes. On the other hand, gestational age, C-Section, multiple births, medical/surgical and number of admissions are poor predictors.

Conclusion: Prediction trees (predictors and split points) provide a useful management tool to prevent undesirable health outcomes in a NICU.

We conducted a series of field experiments to investigate the ability of experimentally measured risk preferences to predict the contractual choices of workers in the real labour market. In a first set of experiments we measured workers’ risk preferences using the lottery approach of Holt and Laury (2002). We did this twice: once for low-stakes lotteries (LSL) and once for high-stakes (HSL). Each worker subsequently made 12 decisions, choosing between his/her regular piece-rate contract and a series of fixed wage contracts, each offereing a different fixed wage. One of the twelve decisions was then chosen at random and the worker was paid according to his/her choice for that decision over a period of two working days. The risk preferences measured from the HSL effectively predict the contract choices; those from the LSL are irrelevant. We also find that high-ability workers prefer piece-rate contracts.
 

This paper extends the work of Baltagi et al. (2018) to the popular dynamic panel data model. We investigate the robustness of Bayesian panel data models to possible misspecification of the prior distribution. The proposed robust Bayesian approach departs from the standard Bayesian framework in two ways. First, we consider the e-contamination class of prior distributions for the model parameters as well as for the individual effects. Second, both the base elicited priors and the econtamination priors use Zellner (1986)’s g-priors for the variance-covariance matrices. We propose a general “toolbox” for a wide range of specifications which includes the dynamic panel model with random effects, with cross-correlated effects `a la Chamberlain, for the Hausman-Taylor world and for dynamic panel data models with homogeneous/heterogeneous slopes and cross-sectional dependence. Using a Monte Carlo simulation study, we compare the finite sample properties of our proposed estimator to those of standard classical estimators. The paper contributes to the dynamic panel data literature by proposing a general robust Bayesian framework which encompasses the conventional frequentist specifications and their associated estimation methods as special cases.

Change-point processes are one flexible approach to model long time series. We propose a method to uncover which model parameter truly vary when a change-point is detected. Given a set of breakpoints, we use a penalized likelihood approach to select the best set of parameters that changes over time and we prove that the penalty function leads to a consistent selection of the true model. Estimation is carried out via the deterministic annealing expectation-maximization algorithm. Our method accounts for model selection uncertainty and associates a probability to all the possible time-varying parameter specications. Monte Carlo simulations highlight that the method works well for many time series models including heteroskedastic processes. For a sample of 14 Hedge funds (HF) strategies, using an asset based style pricing model, we shed light on the promising ability of our method to detect the time-varying dynamics of risk exposures as well as to forecast HF returns.
 

We develop and estimate a structural model that incorporates service intensity and endogenous contract choice into the standard labour supply framework. We apply our model to data collected on specialist physicians working in Quebec(Canada). These physicians are typically paid a fee-for-service (FFS) contract. Our panel data set covers a period of policy reform which allowed physicians either to remain on FFS or to adopt a mixed remuneration (MR) contract, under which they receive a per diem as well as a reduced FFS. We estimate the preference parameters of physicians governing the choice of contract and their hours worked and services provided. We use our estimates to simulate labour supply elasticities, to predict (ex ante) the effects of contracts on physician behaviour, and to evaluate selection effects. The supply of services is reduced under a MR contract, suggesting incentives matter. The hours spent seeing patients is less sensitive to incentives than the supply of services. Our results suggest that a reform forcing all physicians to adopt the MR system would have had substantially larger effects on physician behaviour than were measured under the observed reform.

We measure the response of physicians to monetary incentives using matched administrative and time-use data on specialists from Québec (Canada). These physicians were paid fee-for-service contracts and supplied a number of different services. We model physician behaviour and derive a conditional earnings function that returns the maximum earnings a physician can generate in the labour market, conditional on total hours worked. The earnings function is estimated using both limitedinformation methods and full-information methods. Limited-information methods impose fewer restrictions on the data, but are less informative over incentive effects. Le Chatelier effects imply that they identify lower bounds to the own-price substitution effects. Full-information methods explain earnings and hours simultaneously. They identify the full response to incentives, including income effects. Our results confirm that physicians respond to financial incentives. The own-price substitution effects of a relative price change are both economically and statistically significant. Income effects are present, but are overridden when prices are increased for individual services. They are more prominent in the presence of broad-based fee increases. In such cases, the income effect empirically dominates the substitution effect, which leads physicians to reduce their supply of services.

In communities highly dependent on rainfed agriculture for their livelihoods, the common occurrence of climatic shocks such as droughts can lower the opportunity cost of having children, and raise fertility. Using longitudinal household data from Madagascar, we estimate the causal effect of drought occurrences on fertility, and explore the nature of potential mechanisms driving this effect. We exploit exogenous within-district year-to-year variation in rainfall deficits, and find that droughts occurring during the agricultural season significantly increase the number of children born to women living in agrarian communities. This effect is long lasting, as it is not reversed within four years following the drought occurrence. Analyzing the mechanism, we find that droughts have no effect on common underlying factors of high fertility such as marriage timing and child mortality. Furthermore, droughts have no significant effect on fertility if they occur during the non-agricultural season or in non-agrarian communities, and their positive effect in agrarian communities is mitigated by irrigation. These findings provide evidence that a low opportunity cost of having children is the main channel driving the fertility effect of drought in agrarian communities.

The paper investigates the links between homeownership, employment and earnings for which no consensus exists in the literature. Our analysis is cast within a dynamic setting and the endogeneity of each outcome is assessed through the estimation of a flexible panel multivariate model with random effects. The data we use are drawn from the French sample of the EU Survey on Income and Living Conditions for the years 2004–2013. The error terms are both correlated across equations and autocorrelated. Individual random effects are also correlated across equations. The model is estimated using a simulated maximum likelihood estimator and particular care is given to the initial conditions problem. Our results show that while homeowners have longer employment and unemployment spells, they must contend with lower earnings than tenants upon reemployment. They also stress the importance of unobserved heterogeneity in explaining the transitions on the labour and housing markets, and the relationship between earnings and the latter two. Failure to properly account for this is likely to yield biased parameter estimates.

We study peer effects on the formation of beliefs regarding college participation. We present a structural model of learning in friendship networks. We show that the model is identified and we present a Bayesian estimation procedure. We estimate the model using data on teenagers’ beliefs regarding college participation, controlling for preferences and academic achievement. We find that, on average, friends’ beliefs account for about 12% of the updating process. We also find strong heterogeneity among schools and individuals. In particular, we find substantial unobserved individual heterogeneity, which casts doubt on the efficiency of network-targeted public policies.

This paper develops a monitoring and forecasting model for the aggregate monthly number of commercial bank failures in the U.S. We extract key sectoral predictors from the large set of macroeconomic variables proposed by McCracken and Ng (2016) and incorporate them in a hurdle negative binomial model to predict the number of monthly commercial bank failures. We uncover a strong and robust relationship between the predictor synthesizing housing industry variables and bank failures. This relationship suggests the existence of a link between developments in the housing sector and the vulnerability of commercial banks to non-performing loans increases and asset deterioration. We assess different specifications

We consider a decision maker who is responsible for issuing flood warnings for the population. The population is uncertain about the credibility of the warnings and adjusts its beliefs following false alerts or missed events. We show that low credibility leads the decision maker to issue warnings for lower probabilities of flooding. In practice, those probabilities are provided by hydrological forecasts. We therefore use our model to compare welfare under alternative real-world hydrological forecasts. We find that when forecasts include non-realistic extreme scenarios, the economy may remain stuck in a state characterized by many false alerts and poor credibility.

Recent advances in the collective model literature suggest ways to estimate the complete allocation of resources within households, using assignable goods and assuming adult preference similarity across demographic groups (or across spouses). While it makes welfare analysis at the individual level possible, the predictive power of the model is unknown. We propose the ?rst validation of this approach, exploiting a unique dataset from Bangladesh in which the detailed expenditure on private goods by each family member is collected. Individualized expenditure allows us to test the identifying assumptions and to derive ?observed?resource sharing within families, which can be compared to the resource allocation predicted by the model. Sharing between parents and children is well predicted on average while the model detects key aspects like the extent of pro-boy discrimination. Results overall depend on the identifying good: clothing provides the best ?t compared to other goods as it best validates the preference-similarity assumption. The model leads to accurate measures of child and adult poverty, indicating the size and direction of the mistakes made when using the traditional approach based on per adult equivalent expenditure (i.e. ignoring within-household inequality). This assessment of existing approaches to measure individual inequality and poverty is crucial for both academic and policy circles and militates in favor of a systematic use of collective models for welfare analyses.

We measure the response of physicians to monetary incentives using matched administrative and time-use data on specialists from Québec (Canada). These physicians were paid fee-for-service contracts and supplied a number of different services. Our sample covers a period during which the Québec government changed the prices paid for clinical services. We apply these data to a multitasking model of physician labour supply, measuring two distinct responses. The first is the labour-supply response of physicians to broad-based fee increases. The second is the response to changes in the relative prices of individual services. Our results confirm that physicians respond to incentives in predictable ways. The own-price substitution effects of a relative price change are both economically and statistically significant. Income effects are present, but are overridden when prices are increased for individual services. They are more prominent in the presence of broad-based fee increases. In such cases, the income effect empirically dominates the substitution effet, which leads physicians to reduce their supply of clinical services.

This paper investigates international index return predictability using option-implied information. We document the significant predictive power of the variance risk premium (VRP), Foster-Hart risk (FH), and higher-order moments for horizons ranging from 1 to 250 days. Our results from predictive regressions show that these four risk-neutral metrics, which have the advantage of daily updating, perform well internationally. VRP and FH risk are significant predictors for several horizons, including less than one month (VRP) and longer horizons (FH). Risk-neutral skewness and kurtosis are significant for several countries across multiple horizons. Out-of-sample forecasts and utility gain calculations confirm the statistical and economic significance of these risk-neutral variables internationally.

Civil conflicts spill over into neighboring countries. This paper proposes a theory of the contagion of civil wars. Weak territorial control facilitates the emergence of a regional market for war inputs in the “porous frontier.” The contagion effect is nonlinear and creates multiple equilibrium situations of regional complexes of civil conflicts. This helps explain the observed patterns of regional clustering of conflict and institutional quality, and raises identification issues in the measurement of the contagion effect. We also derive a positive spillover of civil wars: governments are sometimes in a position to avoid contagion by improving their institutions. Finally, we explore the policy implications for military intervention, and military and institutional cooperation.

We investigate whether peer effects at work differ by gender and whether gender differences in peer effects -if any- depend on work organization. We develop a social network model with gender heterogeneity that we test in a real-effort laboratory experiment. We compare sequential networks in which information flows from peers to the worker and simultaneous networks where it disseminates bi-directionally. We identify strong gender differences as females disregard their peers’ performance in simultaneous networks, while males are influenced by peers in both networks. Females may perceive the environment in simultaneous networks as being more competitive than in sequential networks.

We analyze the causal effect of parental education on the potential mismatch between child monetary poverty and multidimensional deprivations. First, in a simple model of parental investment in child outcomes, we demonstrate that the misalignment between household monetary resources and parental education causes a mismatch. Indeed, a match between poverty and deprivation occurs whenever household consumption expenditure and parental education are correlated. Second, using micro-level data from Tanzania, we find that parental education has a negative effect on the probability that a monetarily non-poor child suffers some basic deprivations, and a positive effect on the likelihood that a monetarily poor child suffers no basic deprivations.

We conduct a stated-choice experiment where respondents are asked to rate various insurance products aimed to protect against financial risks associated with long-term care needs. Using exogenous variation in prices from the survey design, and objective risks computed from a dynamic microsimulation model, these stated-choice probabilities are used to predict market equilibrium for long-term care insurance using the framework developped by Einav et al. (2010). We investigate in turn causes for the low observed take-up of long-term care insurance in Canada despite substantial residual out-of-pocket financial risk. We first find that awareness and knowledge of the product is low in the population: 44% of respondents who do not have long-term care insurance were never offered this type of insurance while overall 31% report no knowledge of the product. Although we finnd evidence of adverse selection, results suggest it plays a minimal role in limiting take-up. On the demand side, once respondents have been made aware of the risks, we finnd that demand remains low, in part because of misperceptions of risk, lack of bequest motive and home ownership which may act as a substitute.

I propose a simple simulation procedure for large games with multiple equilibria. The simulation procedure is based on a best-response dynamic. The implied equilibrium selection mechanism is intuitive: more stable equilibria are selected with higher probability.

Fault-based liability regimes require an inquiry into the nature of the defendant’s conduct, whereas this type of inquiry is absent in strict liability regimes. Therefore, verdicts reached through fault-based liability regimes can convey superior information compared to verdicts reached through strict liability regimes. Further reflection reveals that this advantage is enjoyed by fault-based liability regimes only if the evidence related to the nature of defendants’ actions is such ciently informative. Otherwise, admitting such evidence can add noise to the information conveyed through verdicts. Therefore, liability regimes have a function of tuning signals conveyed on to third parties, which, in turn, causes deterrence effects by a¤ecting the informal sanctions imposed on defendants who are found liable. We construct a model wherein this function is formalized, and we identify the optimal liability regime and burden of proof as a function of various factors (e.g. the commonality of the harmful act, and the informativeness of the evidence).

We conduct an experiment where participants choose between actions that provide private benefits but may also impose losses on strangers. Three legal environments are compared: no law, strict liability for the harm caused to others, and an efficiently designed negligence rule where damages are paid only when the harmful action causes a net social loss. Legal obligations are either perfectly enforced (Severe Law) or only weakly so (Mild Law), i.e., material incentives are then nondeterrent. We investigate how legal obligations and social norms interact. Our results show that liability rules strengthen pro-social behavior and suggest that strict liability has a greater effect than the negligence rule.

We study how social interactions influence entrepreneurs' attitudes toward risk. We conduct two risk-taking experiments within workshops organized for young Ugandan entrepreneurs. Between the two experiments, the entrepreneurs participate in a networking activity where they build relationships and discuss with each other. We collect detailed data on peer network formation and on participants' choices before and after the networking activity. Our design implicitly controls for homophily effects (i.e. the tendency of individuals to develop relationships with people who have similar characteristics). We find that risk aversion is affected by social conformity. Participants tend to become more (less) risk averse in the second experiment if the peers they discuss with are on average more (less) risk averse in the first experiment. This suggests that social interactions play a role in shaping risk preferences.

This paper develops tests of the null hypothesis of linearity in the context of autoregressive models with Markov-switching means and variances. These tests are robust to the identification failures that plague conventional likelihood-based inference methods. The approach exploits the moments of normal mixtures implied by the regime-switching process and uses Monte Carlo test techniques to deal with the presence of an autoregressive component in the model specification. The proposed tests have very respectable power in comparison to the optimal tests for Markov-switching parameters of Carrasco et al. (2014) and they are also quite attractive owing to their computational simplicity. The new tests are illustrated with an empirical application to an autoregressive model of U.S. output growth.

A new model - the factorial hidden Markov volatility (FHMV) model - is proposed for financial returns and their latent variances. It is also applicable to model directly realized variances. Volatility is modeled as a product of three components: a Markov chain driving volatility persistence, an independent discrete process capable of generating jumps in the volatility, and a predictable (data-driven) process capturing the leverage effect. An economic interpretation is attached to each one of these components. Moreover, the Markov chain and jump components allow volatility to switch abruptly between thousands of states, and the transition matrix of the model is structured in such a way as to generate a high degree of volatility persistence. In-sample results on six financial time series highlight that the FHMV process compares favorably to state-of-the-art volatility models. A forecasting experiment shows that it also outperforms its competitors when predicting volatility over time horizons ranging from one to one hundred days.

Change-point time series specifications constitute flexible models that capture unknown structural changes by allowing for switches in the model parameters. Nevertheless most models suffer from an over-parametrization issue since typically only one latent state variable drives the switches in all parameters. This implies that all parameters have to change when a break happens. To gauge whether and where there are structural breaks in realized variance, we introduce the sparse change-point HAR model. The approach controls for model parsimony by limiting the number of parameters which evolve from one regime to another. Sparsity is achieved thanks to employing a nonstandard shrinkage prior distribution. We derive a Gibbs sampler for inferring the parameters of this process. Simulation studies illustrate the excellent performance of the sampler. Relying on this new framework, we study the stability of the HAR model using realized variance series of several major international indices between January 2000 and August 2015.

Almost 40% of Canadian youth who left postsecondary education in 1999 had returned two years later. This paper investigates the extent to which schooling discontinuities affect post-graduation starting wages and whether the latter are influenced by the reasons behind these discontinuities. We use data from the 2007 National Graduate Survey. We apply Lewbel’s (2012) generated instruments approach. The source of identification is a heteroscedastic covariance restriction of the error terms that is a feature of many models of endogeneity. We also perform two-stage quantile regressions. We find a positive effect on wages of temporary interruption for men who held a full-time job during their out-of-school spell(s). Both men and women witness a wage decrease if their interruption depends on health issues. Women bear a wage penalty if their interruption is due to a part-time job, to lack of money, or is caused by reasons other than health, work, and money.

This study explores the ‘brain drain’ explanation for the concentration of incomes in Canada during the past thirty years, namely, that high-skilled Canadians have made use of the high salaries on offer in the United States to extract higher salaries at home. If this is the case, then for a given level of US salaries, the threat to accept outside offers should be more credible when the Canadian dollar is depreciating against the US dollar, and weaker when the Canadian dollar is appreciating. The data are broadly consistent with this claim: income concentration worsened during the depreciations of the 1980s and 1990s, and eased when the Canadian dollar began to appreciate in value. The paper develops a simple two-parameter model based on the propositions that high earners in Canada can use US salaries to bargain for higher salaries, and that Canadian high earners can shelter part of their income from personal income taxes. It also offers some preliminary evidence about the parameter values consistent with available data. The results suggest that higher top marginal personal income tax rates may actually accentuate top-end after-tax income inequality. If high earners are able to use their bargaining power to extract pay increases to offset higher tax rates, the the burden of increased taxes will be pushed down to those lower down in the income distribution, leaving the after-tax income distribution more unequal than it was before.

This paper proposes a new formulation of the Maximum Diversification indexation strategy based on Rao’s Quadratic Entropy (RQE). It clarifies the investment problem underlying the Most Diversified Portfolio (MDP) formed with this strategy, identifies the source of the MDP’s out-of-sample performance, and suggests dimensions along which this performance can be improved. We show that these potential improvements are quantitatively important and are robust to portfolio turnover, portfolio risk, estimation window, and covariance matrix estimation.

Chaque année, une part significative des dépenses gouvernementales est consacrée au sport de niveau professionnel ou amateur. Certains analystes affirment que ces investissements contribuent fortement au succès d’un pays aux Jeux olympiques (JO). Nous présentons une analyse économétrique du nombre de médailles obtenues aux JO. Nous introduisons l’investissement public en sport comme facteur potentiellement important du nombre de médailles remportées par un pays, en prenant soin de contrôler pour l’hétérogénéité inobservable des pays participants aux JO. Nous présentons, à notre connaissance, la première modélisation du succès olympique utilisant des spécifications de comptage (count data model) en panel estimées à l’aide de variables instrumentales et captant les caractéristiques individuelles et invariantes des nations. Selon les spécifications du modèle retenues, un pays aux caractéristiques moyennes aurait dû accroître son investissement de 72 à 94 millions de dollars, ceteris paribus, afin d’obtenir une médaille supplémentaire aux JO d’été de Londres en 2012..

This paper estimates the causal impact of party affiliation (Republican or Democrat) of U.S. governors on pollution. Using a regression discontinuity design, gubernatorial election data, and air quality data from U.S. Environmental Protection Agency (EPA), we find that pollution is lower under Democratic governors. We identify that this is mostly due to environmental policies enacted by Democratic governors.

This paper shows how to compare the size of the middle class in income distributions using a polarization index that do not account for identification. We derive a class of polarization indices where the antagonism function is constant in identification. The comparison of distributions using an index from this class motivates the introduction of an alienation dominance surface, which is a function of an alienation threshold. We first prove that a distribution has a large alienation component in polarization compared to another if the former always has a larger dominance surface than the latter regardless of the value of the alienation threshold. Then, we show that the distribution with large dominance surface is more concentrated in the tails and has a smaller middle class than the other distribution. We implement statistical inference and test dominance betweenpairs of distributions using the asymptotic theory and Intersection Union tests. Our methodology is illustrated in comparing the declining of the middle class across pairwise distributions of twenty-two countries from the Luxembourg Income Study data base.

We study some recent developments and challenges in the empirics of the effects of social networks. We focus in particular on researchers’ ability to make policy recommendations based on a standard linear econometric model. We examine the potential compatibility between this type of econometric model and a microeconomic theoretical approach based on fundamentals, such as preferences, technology and decision processes. We discuss sources of identification for the social multiplier as well as for the identity of the key player. We study the possibility of testing endogeneity in network formation. We analyse the use of proxy variables and their impact for the causal interpretation of the peer effect coefficients. Our analysis suggests that greater care should be taken in grounding econometric network models to sound and credible theoretical underpinnings.

This paper discusses the choice of the number of participants for within-subjects (WS) designs and between-subjects (BS) designs based on simulations of statistical power allowing for different numbers of experimental periods. We illustrate the usefulness of the approach in the context of field experiments on gift exchange. Our results suggest that a BS design requires between 4 to 8 times more subjects than a WS design to reach an acceptable level of statistical power. Moreover, the predicted minimal sample sizes required to correctly detect a treatment effect with a probability of 80% greatly exceed sizes currently used in the literature. Our results suggest that adding experimental periods in an experiment can substantially increase the statistical power of a WS design, but have very little effect on the statistical power of the BS design. Finally, we discuss issues relating to numerical computation and present the powerBBK package programmed for STATA. This package allows users to conduct their own analysis of power for the different designs (WS and BS), conditional on user specified experimental parameters (true effect size, sample size, number of periods, noise levels for control and treatment, error distributions), statistical tests (parametric and nonparametric), and estimation methods (linear regression, binary choice models (probit and logit), censored regression models (tobit)).