Publications

Most of the information presented on this page have been retrieved from RePEc with the kind authorization of Christian Zimmermann
Finding the best trade-off between performance and interpretability in predicting hospital length of stay using structured and unstructured dataJournal articleFranck Jaotombo, Luca Adorni, Badih Ghattas and Laurent Boyer, PLoS ONE, Volume 18, Issue 11, pp. e0289795, Forthcoming

Objective This study aims to develop high-performing Machine Learning and Deep Learning models in predicting hospital length of stay (LOS) while enhancing interpretability. We compare performance and interpretability of models trained only on structured tabular data with models trained only on unstructured clinical text data, and on mixed data. Methods The structured data was used to train fourteen classical Machine Learning models including advanced ensemble trees, neural networks and k-nearest neighbors. The unstructured data was used to fine-tune a pre-trained Bio Clinical BERT Transformer Deep Learning model. The structured and unstructured data were then merged into a tabular dataset after vectorization of the clinical text and a dimensional reduction through Latent Dirichlet Allocation. The study used the free and publicly available Medical Information Mart for Intensive Care (MIMIC) III database, on the open AutoML Library AutoGluon. Performance is evaluated with respect to two types of random classifiers, used as baselines. Results The best model from structured data demonstrates high performance (ROC AUC = 0.944, PRC AUC = 0.655) with limited interpretability, where the most important predictors of prolonged LOS are the level of blood urea nitrogen and of platelets. The Transformer model displays a good but lower performance (ROC AUC = 0.842, PRC AUC = 0.375) with a richer array of interpretability by providing more specific in-hospital factors including procedures, conditions, and medical history. The best model trained on mixed data satisfies both a high level of performance (ROC AUC = 0.963, PRC AUC = 0.746) and a much larger scope in interpretability including pathologies of the intestine, the colon, and the blood; infectious diseases, respiratory problems, procedures involving sedation and intubation, and vascular surgery. Conclusions Our results outperform most of the state-of-the-art models in LOS prediction both in terms of performance and of interpretability. Data fusion between structured and unstructured text data may significantly improve performance and interpretability.

The international diffusion of food innovations and the nutrition transition: retrospective longitudinal evidence from country-level data, 1970-2010Journal articleAnne-Celia Disdier, Fabrice Etile and Lorenzo Rotunno, BMJ GLOBAL HEALTH, Volume 8, Issue 11, pp. e012062, Forthcoming

IntroductionThere is a lack of quantitative evidence on the role of food innovations-new food ingredients and processing techniques-in the nutrition transition.ObjectiveDocument the distribution of food innovations across 67 high-income (HIC) and middle-income (MIC) countries between 1970 and 2010, and its association with the nutritional composition of food supply.MethodsWe used all available data on food patents, as compiled by the European Patent Office, to measure food innovations. We considered innovations directly received by countries from inventors seeking protection in their territories, and those embedded in processed food imports. Food and Agricultural Organization data were used to estimate the associations between international diffusion of food innovations and trends in total food supply and its macronutrient composition, after adjusting for confounding trends in demand-side factors. We identified the role of trade by simulating the changes in average diet due to innovations embedded in food imports.ResultsTrends in food innovations were positively and significantly associated with changes in daily per capita calorie supply available for human consumption in MIC between 1990 and 2010 (elasticity of 0.027, 95% CI 0.019 to 0.036). Food innovations were positively correlated with the share of animal and free fats in total food supply (elasticities of 0.044, 95% CI 0.030 to 0.058 for MIC between 1970 and 1989 and 0.023, 95% CI 0.003 to 0.043 for HIC between 1990 and 2010). Food innovations were associated with substitutions from complex carbohydrates towards sugars in total food supply for MIC after 1990 (elasticities of -0.037, 95% CI -0.045 to -0.029 for complex carbs, 0.082, 95% CI 0.066 to 0.098 for sugars). For these countries, the trade channel capturing access to innovations through imports of processed food played a key role.ConclusionPolicy-makers should consider the impacts of the international diffusion of food innovations in assessing the costs and benefits of international trade regulations.

The weakness of common job contactsJournal articleSofia Ruiz-Palazuelos, Maria Paz Espinosa and Jaromir Kovarik, EUROPEAN ECONOMIC REVIEW, Volume 160, pp. 104594, Forthcoming

Many people obtain job information from friends and acquaintances. However, one factor influencing labor-market outcomes that is ignored in the literature is the presence of overlapping friendship circles in social networks. We find that overlapping friendship networks produce correlated information flows, resulting in an increased probability of two events: either receiving redundant job offers or receiving no job offers at all. Consequently, people with common contact networks exhibit worse employment prospects even if they have the same number of information providers and compete with the same number of people for vacancies. In quantitative terms, the impact of overlapping friendship circles rivals that of the number of direct contacts and contacts' contacts. This implies that the results in Calvo-Armengol (2004) only apply for networks where people's friends are neither connected nor have common contacts. Because overlapping friendship circles are a crucial aspect of strong relationships, our findings uncover an alternative mechanism behind "The Strength of Weak Ties"(Granovetter, 1973): their ability to maintain independence in job information flows. We further show that people with common job contacts earn lower incomes on average. However, conditional on being employed, their expected wage is higher because they can take advantage of the multiple job offers received by selecting the one with the highest pay.

Assessment and determinants of depression and anxiety on a global sample of sexual and gender diverse people at high risk of HIV: a public health approachJournal articleErik Lamontagne, Vincent Leroy, Anna Yakusik, Warren Parker, Sean Howell and Bruno Ventelou, BMC PUBLIC HEALTH, Volume 24, Issue 1, pp. 215, Forthcoming

BackgroundSexual and gender diverse people face intersecting factors affecting their well-being and livelihood. These include homophobic reactions, stigma or discrimination at the workplace and in healthcare facilities, economic vulnerability, lack of social support, and HIV. This study aimed to examine the association between such factors and symptoms of anxiety and depression among sexual and gender diverse people.MethodsThis study is based on a sample of 108,389 gay, bisexual, queer and questioning men, and transfeminine people from 161 countries collected through a cross-sectional internet survey. We developed a multinomial logistic regression for each group to study the associations of the above factors at different severity scores for anxiety and depression symptoms.ResultsAlmost a third (30.3%) of the participants reported experiencing moderate to severe symptoms of anxiety and depression. Higher severity scores were found for transfeminine people (39%), and queer or questioning people (34.8%). Severe symptoms of anxiety and depression were strongly correlated with economic hardship for all groups. Compared to those who are HIV-negative, those living with HIV were more likely to report severe symptoms of anxiety and depression, and the highest score was among those who do not know their HIV status. Transfeminine people were the most exposed group, with more than 80% higher risk for those living with HIV suffering from anxiety and depression. Finally, homophobic reactions were strongly associated with anxiety and depression. The relative risk of severe anxiety and depression was 3.47 times higher for transfeminine people facing transphobic reactions than those with no symptoms. Moreover, anxiety and depression correlate with stigma or discrimination in the workplace and healthcare facilities.ConclusionsThe strong association between the severity of anxiety and depression, and socioeconomic inequality and HIV status highlights the need for concrete actions to meet the United Nations' pledge to end inequalities faced by communities and people affected by HIV. Moreover, the association between stigma or discrimination and anxiety and depression among sexual and gender diverse people is alarming. There is a need for bold structural public health interventions, particularly for transfeminine, queer and questioning people who represent three communities under the radar of national HIV programmes.

Salience or event-splitting? An experimental investigation of correlation sensitivity in risk-takingJournal articleMoritz Loewenfeld and Zheng Jiakun, Journal of the Economic Science and Association, Forthcoming

Salience theory relies on the assumption that not only the marginal distribution of lotteries, but also the correlation of payoffs across states impacts choices. Recent experimental studies on salience theory seem to provide evidence in favor of such correlation effects. However, these studies fail to control for event-splitting effects (ESE). In this paper, we seek to disentangle the role of correlation and event-splitting in two settings: 1) the common consequence Allais paradox as studied by Bordalo et al. (2012), Bruhin et al. (2022), and Frydman and Mormann (2018); 2) choices between Mao pairs as studied by Dertwinkel-Kalt and Köster (2020). In both settings, we find evidence suggesting that recent findings supporting correlation effects are largely driven by ESE. Once controlling for ESE, we find no consistent evidence for correlation effects. Our results thus shed doubt on the validity of salience theory in describing risky behavior.

Expectations, beliefs and the business cycle: tracing back to the deep economic driversJournal articleFrédéric Dufourt, Kazuo Nishimura and Alain Venditti, Economic Theory, Forthcoming

When can exogenous changes in beliefs generate endogenous fluctuations in rational expectation models? We analyze this question in the canonical one-sector and two-sector models of the business cycle with increasing returns to scale. A key feature of our analysis is that we express the uniqueness/multiplicity condition of equilibirum paths in terms of restrictions on five critical and economically interpretable parameters: the Frisch elasticities of the labor supply curve with respect to the real wage and to the marginal utility of wealth, the intertemporal elasticity of substitution in consumption, the elasticity of substitution between capital and labor, and the degree of increasing returns to scale. We obtain two clear-cut conclusions: belief-driven fluctuations cannot exist in the one-sector version of the model for empirically consistent values for these five parameters. By contrast, belief-driven fluctuations are a robust property of the twosector version of the model-with differentiated consumption and investment goods-, as they now emerge for a wide range of parameter values consistent with available empirical estimates. The key ingredients explaining these different outcomes are factor reallocation between sectors and the implied variations in the relative price of investment, affecting the expected return on capital accumulation.

Bayesian inference for non-anonymous growth incidence curves using Bernstein polynomials: an application to academic wage dynamicsJournal articleEdwin Fourrier-Nicolaï and Michel Lubrano, Studies in Nonlinear Dynamics & Econometrics, Issue online 2023-07-24, Forthcoming

The paper examines the question of non-anonymous Growth Incidence Curves (na-GIC) from a Bayesian inferential point of view. Building on the notion of conditional quantiles of Barnett (1976. “The Ordering of Multivariate Data.” Journal of the Royal Statistical Society: Series A 139: 318–55), we show that removing the anonymity axiom leads to a complex and shaky curve that has to be smoothed, using a non-parametric approach. We opted for a Bayesian approach using Bernstein polynomials which provides confidence intervals, tests and a simple way to compare two na-GICs. The methodology is applied to examine wage dynamics in a US university with a particular attention devoted to unbundling and anti-discrimination policies. Our findings are the detection of wage scale compression for higher quantiles for all academics and an apparent pro-female wage increase compared to males. But this pro-female policy works only for academics and not for the para-academics categories created by the unbundling policy.

The Macroeconomic Impact of the 1918–19 Influenza Pandemic in SwedenJournal articleMartin Karlsson, Mykhailo Matvieiev and Maksym Obrizan, The B.E. Journal of Macroeconomics, Forthcoming

In this paper, we develop an overlapping generations model with endogenous fertility and calibrate it to the Swedish historical data in order to estimate the economic cost of the 1918–19 influenza pandemic. The model identifies survivors from younger cohorts as main benefactors of the windfall bequests following the influenza mortality shock. We also show that the general equilibrium effects of the pandemic reveal themselves over the wage channel rather than the interest rate, fertility or labor supply channels. Finally, we demonstrate that the influenza mortality shock becomes persistent, driving the aggregate variables to lower steady states which costs the economy 1.819% of the output loss over the next century.

Valuation of ecosystem services and social choice: the impact of deliberation in the context of two different aggregation rulesJournal articleMariam Maki Sy, Charles Figuières, Hélène Rey-Valette, Richard B. Howarth and Rutger De Wit, Social Choice and Welfare, Forthcoming

This paper describes an empiric study of aggregation and deliberation—used during citizens’ workshops—for the elicitation of collective preferences over 20 different ecosystem services (ESs) delivered by the Palavas coastal lagoons located on the shore of the Mediterranean Sea close to Montpellier (S. France). The impact of deliberation is apprehended by comparing the collectives preferences constructed with and without deliberation. The same aggregation rules were used before and after deliberation. We compared two different aggregation methods, i.e. Rapid Ecosystem Services Participatory Appraisal (RESPA) and Majority Judgement (MJ). RESPA had been specifically tested for ESs, while MJ evaluates the merit of each item, an ES in our case, in a predefined ordinal scale of judgment. The impact of deliberation was strongest for the RESPA method. This new information acquired from application of social choice theory is particularly useful for ecological economics studying ES, and more practically for the development of deliberative approaches for public policies.

The Regularity of the Value Function of Repeated Games with Switching CostsJournal articleYevgeny Tsodikovich, Xavier Venel and Anna Zseleva, Mathematics of Operations Research, Forthcoming

We study repeated zero-sum games where one of the players pays a certain cost each time he changes his action. We derive the properties of the value and optimal strategies as a function of the ratio between the switching costs and the stage payoffs. In particular, the strategies exhibit a robustness property and typically do not change with a small perturbation of this ratio. Our analysis extends partially to the case where the players are limited to simpler strategies that are history independent―namely, static strategies. In this case, we also characterize the (minimax) value and the strategies for obtaining it.