Curriculum vitæ

Professional experience

2025-

Deputy Head of the National Accounts Office for Public Administrations, DGFIP, Paris.

2024-2025

Head of the Summary, Financial Transactions and Public Debt Tables sector, DGFIP, Paris.

2021-2024

Data economist, Insee, Paris.

Summer 2020

Intern at the division Research and Development, NBB (National Bank of Belgium), Belgium.

2017 - 2019

Methodologist on Seasonal and Working Day Adjustments (SA-WDA), Insee, Paris.

2015 - 2017

Short-term economic analysis officer in the manufacturing industry, Insee, Paris.

Summer 2020

Intern research officer at the International Relations Department, INE (Instituto Nacional de Estadística), Spain.

Education

2020 -

PhD Student at EDGE, Nantes Atlantique Economics and Management Laboratory (LEMNA).

  • Real-time detection of turning points: contribution of the use of asymmetric filters in business cycle analysis.
  • Under the supervision of Olivier Darné (LEMNA) and Dominique Ladiray (Insee).

2019 - 2021

National School of Statistics and Economic Administration (ENSAE).

2014 - 2015

Master of Science in statistics-econometrics, specialisation in official statistics and statistical studies, ENSAI / Université Rennes 1.

2013 - 2014

Bachelor of Economics in Science of organizations and markets, applied economics, Université Paris-Dauphine.

2012 - 2013

Bachelor of Science in Mathematics equivalent, Université Rennes 1.

2012 - 2014

National School for Statistics and Information Analysis, France (ENSAI).

2010 - 2012

Post-secondary preparatory school in Mathematics, Physics and Computer Science (France’s Grandes écoles), Lycée Carnot, Dijon.

Publications / Interventions

Publications

Seasonally adjusted series are commonly used for business cycle analysis and turning point identification. However, when they are too noisy, additional smoothing is required to extract the short-term trend, known as the trend-cycle, which combines the long-term trend and short-term cyclical fluctuations. This extraction typically relies on symmetric moving averages. For real-time estimation, in the absence of future observations, it is necessary to use asymmetric filters. This leads to delays in turning point detection and revisions as new observations become available. This thesis aims to clarify why and how to publish the trend-cycle and provide recommendations for doing so.

Different recent approaches to building asymmetric moving averages are compared, both theoretically and empirically. Two extensions of the Henderson and Musgrave filters, traditionally used for trend-cycle estimation, are proposed: 1) reduction of revisions and delays in turning point detection through local parameterization; 2) integration of external regressors to build filters robust to certain shocks.

This work is accompanied by two R packages, rjd3filters and publishTC, which facilitate the application of the proposed methods, the study of filter properties, trend-cycle estimation, and their implementation in production.

  • Quartier-la-Tente A. (2025), « Et si l’on publiait la tendance-cycle ? », XVèmes Journées de Méthodologie Statistique de l’Insee. https://github.com/AQLT/publishTC.wp (French article).

It is common practice to seasonally adjust economic series in order to study business outlook and determine the state of the cycle at which the economy stands. However, when they are too noisy, additional smoothing is required to remove the irregularity and extract the short-term trend, known as the trend-cycle, which combines the long-term trend and short-term cyclical fluctuations. This article describes the advantages of publishing this trend-cycle component, the methods used by Statistics Canada and the Australian Bureau of Statistics (the only two institutes to publish this component) as well as two extensions that reduce the bias of real-time estimates and take direct account of the impact of atypical points to prevent them from biasing estimates. This article also describes recommendations for the presentation of this component and how to put it into production using automated reports. These, by applying it to a dozen INSEE publications (around 80 series).

This study is accompanied by an R package, publishTC, making it easy to implement all the methods and recommendations. It is fully reproducible and all the codes used are available under https://github.com/AQLT/publishTC.wp.

Seasonally adjusted series are usually used to analyse the business cycle and turning points. When the irregular is too high, it is preferable to smooth the series in order to analyse the trend-cycle component directly. This study focuses on the real-time estimation of the trend-cycle component around shocks and turning points. The linear moving averages classically used for estimating the trend-cycle, which are sensitive to the presence of atypical points, are compared with robust non-linear methods. We also propose a methodology for extending the Henderson and Musgrave moving averages to take account of external information and thus construct moving averages that are robust to the presence of certain shocks. We describe how to estimate confidence intervals for estimates derived from moving averages, thereby validating the use of these new moving averages. By comparing the methods on simulated and real series, we show that: building robust moving averages makes it possible to reduce revisions and better model turning points around shocks, without degrading the estimates when no shock is observed; robust non-linear methods do not make it possible to extract a trend-cycle component that is satisfactory for economic analysis, with sometimes significant revisions.

This study is fully reproducible and all the codes used are available under https://github.com/AQLT/robustMA.

  • Abbas R., Carnot N., Lequien M., Quartier-la-Tente A., Roux S. (2024), « What path to carbon neutrality? », Insee Analyse n°103.. (French article).

The European Union and France are committed to achieving carbon neutrality by 2050. However, there are several paths to this goal, differing in their emissions reduction profile and economic implications. The consequences of these paths are compared using a stylized model representing the transition from an economy relying on “brown” capital (greenhouse gas emitter) to an economy based on “green” capital (non-emitting). To limit global warming to a given level, the most effective approach is to plan from the outset to respect a carbon budget, i.e. a cap on cumulative emissions. This approach ensures an allocation of brown and green investments that limits the cost of the transition. For a limited carbon budget, it involves an initial scrapping of brown capital. Simply setting one-time reduction targets, like those in Fit for 55, does not provide sufficient incentives for the early elimination of brown capital when these targets are too far apart. It is preferable to set frequent targets (at most every five years) aligned with the trajectory respecting the carbon budget. Finally, for the same cumulative emissions between now and 2050, postponing the transition will ultimately lead to higher costs and more scrapped assets, making the adjustment less credible.

This paper examines and compares real-time estimates of the trend-cycle component using moving averages constructed with local polynomial regression. It enables the reproduction of Henderson’s symmetric and Musgrave’s asymmetric filters used in the X-13ARIMA-SEATS seasonal adjustment algorithm. This paper proposes two extensions of local polynomial filters for real-time trend-cycle estimates: first including a timeliness criterion to minimize the phase shift; second with procedure for parametrizing asymmetric filters locally while they are generally parametrized globally, which can be suboptimal around turning points. An empirical comparison, based on simulated and real data, shows that modeling polynomial trends that are too complex introduces more revisions without reducing the phase shift, and that local parametrization reduces the delay in detecting turning points and reduces revisions. The results are reproducible and all the methods can be easily applied using the R package rjd3filters.

  • Quartier-la-Tente A. (2024), “Using regression models with time-varying coefficients for short-term economic forecasting”, INSEE working paper (French article).

This study describes three methods for estimating linear regression models with time-varying coefficients: piecewise regression, local regression, and regression with stochastic coefficients (state-space modeling). It also details their implementation in R using the tvCoef package. Through a comparative analysis of around thirty quarterly forecasting models, we show that the use of these methods, especially thanks to the state-space modeling, reduces forecast errors when breakpoints are present in the coefficients. Moreover, even when traditional tests conclude that the coefficients are stable, regression with stochastic coefficients can still help reduce forecast errors. However, uncertainties related to estimating certain hyperparameters can increase real-time forecast errors, especially for local regression. Thus, an economic analysis of estimated parameters remains essential.

This study is fully reproducible and all the codes used are available under https://github.com/InseeFrLab/DT-tvcoef.

With an optimal investment – or stranding – choice model in carbon-intensive (brown) capital, which emits greenhouse gases, or in emissions-free (green) capital, we describe the optimal transitions to carbon neutrality that comply with climate constraints such as emission caps for a given date (Fit for 55) or carbon budgets. We show that:

  1. Anticipated stranding cannot occur with targets at specific dates.

  2. To limit warming to a given level, explicitly introducing this constraint in the form of a remaining carbon budget minimizes the associated economic cost, leading to high initial stranding with limited budgets. Emission caps set regularly from the first year, and chosen based on emissions from this optimal trajectory, result in a similar path.

  3. Given a cumulative emission level, delaying the transition increases costs and stranding.

  4. Total investment during and after the transition is lower than that in the initial state.

All the codes used are available at https://github.com/InseeFrLab/DT-way-to-net-zero.

  • Quartier-la-Tente A. (2024), “Real-time trend-cycle estimation: the contribution of asymmetric moving averages”, INSEE methodological working paper (French article).

This paper focuses on different approaches to build moving averages for real-time trend-cycle estimation and fast turning point detection. We propose a comparison of the main methods, based on a general unifying framework to derive linear filters. We also describe two possible extensions to local polynomial filters: the addition of a timeliness criterion to control the phase shift (delay in the detection of turning points) and a way to locally parameterize these filters. The empirical comparison of the methods shows that: the optimization problems of the filters from the Reproducing Kernel Hilbert Space (RKHS) theory increase the phase shift and the revisions of the trend-cycle estimates; modeling polynomial trends that are too complex introduces more revisions without decreasing the phase shift; for polynomial filters, a local parameterization reduces the phase shift and the revisions.

This study is fully reproducible and all the codes used are available under https://github.com/InseeFrLab/DT-est-tr-tc.

  • Abbas R., Carnot N., Lequien M., Quartier-la-Tente A., Roux S. (2023), contribution au rapport Mahfouz - Pisani-Ferry sur l’effet macro-économique de la transition bas carbone, rapport de synthèse p79-81 et rapport thématique sur le marché du capital p47-57.

  • Babet D., Lequien M., Quartier-la-Tente A. (2022), “The contribution of macroeconomic models to simulate the effects of higher energy import prices”, Conjoncture in France, March, p. 16-17.

  • Quartier-la-Tente A. (2022), “Real-time detection of turning points: the contribution of asymmetric filters to turning-point detection”, 13e Journées de Méthodologie Statistique (French article).

  • Ladiray D. et Quartier-la-Tente A. (2018), « Du bon usage des modèles Reg-ARIMA en désaisonnalisation », 13e Journées de Méthodologie Statistique (French article).

  • Pham H. et Quartier-la-Tente A. (2018), « Désaisonnaliser les séries très longues par sous-période, gains et choix de la longueur de traitement », 13e Journées de Méthodologie Statistique (French article).

  • Dortet-Bernadet V., Lenseigne F., Parent C., Quartier-la-Tente A., Stoliaroff-Pépin A-M., Plouhinec C. (2016), “After two years of turbulence, the French aeronautical sector is ready to take off again”, Conjoncture in France, December, p. 19-37.

  • Glotain M., Quartier-la-Tente A. (2015), “New sub-sector business climate indicators to improve economic outlook analysis”, Conjoncture in France, June, p. 35-54.

  • Quartier-la-Tente A. (2015), “To what extent does the integration of sub-sectoral information improve the quality of manufacturing production forecasting?”, Master’s thesis.

Reviewer for the journals : Statéco, Journal of Official Statistics, Statistical Journal of the IAOS, International Journal of Operational Research, The R journal.

Interventions

Trainings

2022-

Trainer on time series analysis with R (12h), CEPE, Paris.

2021-2022

Lecturer in time series analysis, ENSAE, Paris.

2021

Seasonal with JDemetra+ et RJDemetra (24h), RTE, Paris.

2019-

Trainer on seasonal and working days adjustment (SA-WDA) (24h), CEPE, Paris.

2017 - 2019

Trainer on seasonal and working days adjustment (SA-WDA),INSEE, Paris.

2016

Lecturer in introduction to the statistical software , ENSAE, Paris.

Cooperations

Organization of a regional seminar on real sector statistics on seasonal adjustment to the member states of AFRITAC West (AFW, ~50 participants).

Technical assistance on the production of seasonally adjusted and working day adjusted of Quarterly National Accounts (QNA).

Technical assistance on the production monthly indicators of economic growth (MIEG).

Technical assistance on the production monthly indicators of economic growth (MIEG).

Technical assistance on the production of seasonally adjusted and working day adjusted of Quarterly National Accounts (QNA).

Technical assistance on the production of seasonally adjusted and working day adjusted of Quarterly National Accounts (QNA) and Monthly Indicators of Economic Growth (MIEG).

Technical assistance on the construction of index of industrial production (IIP) and on seasonal adjustment.

Technical assistance on liquidity forecasting to the National Bank of North Macedonia.

Technical assistance on liquidity forecasting to the Central Bank of Honduras.

Trainer on manipulation and forecast of time series with R to the BCEAO.

Member of the Eurostat seasonal adjustment center of Excellence: reflections on seasonal adjustment methods; development of R packages around JDemetra+, maintenance and distribution. Technical assistance to several European countries.

Technical assistance on seasonal adjustment methods to a Serbian Delegation.

Trainer on forecasting models and construction of synthetic indicators to the BCEAO.

Technical assistance on the use of business surveys in forecasting National Accounts to a Serbian Delegation.