arXiv subjects

Sandra Paterlini

Publications and source records attributed to Sandra Paterlini.

12 recordsLinked to original sources

arXiv2026

Asymptotic Theory for Graphical SLOPE: Precision Estimation and Pattern Convergence

This paper studies Graphical SLOPE for precision matrix estimation, with emphasis on its ability to recover both sparsity and clusters of edges with equal or similar strength. In a fixed-dimensional regime, we establish that the root-$n$ scaled estimation error converges to the unique minimizer of a strictly convex optimization problem defined through the directional derivative of the SLOPE penalty. We also establish convergence of the induced SLOPE pattern, thereby obtaining an asymptotic characterization of the clustering structure selected by the estimator. A comparison with GLASSO shows that the grouping property of SLOPE can substantially improve estimation accuracy when the precision matrix exhibits structured edge patterns. To assess the effect of departures from Gaussianity, we then analyze Gaussian-loss precision matrix estimation under elliptical distributions. In this setting, we derive the limiting distribution and quantify the inflation in variability induced by heavy tails relative to the Gaussian benchmark. We also study TSLOPE, based on the multivariate $t$-loss, and derive its limiting distribution. The results show that TSLOPE offers clear advantages over GSLOPE under heavy-tailed data-generating mechanisms. Simulation evidence suggests that these qualitative conclusions persist in high-dimensional settings, and an empirical application shows that SLOPE-based estimators, especially TSLOPE, can uncover economically meaningful clustered dependence structures.

math.ST↗

arXiv2025

Selection Confidence Sets for Equally Weighted Portfolios

Given a universe of N assets, investors often form equally weighted portfolios (EWPs) by selecting subsets of assets. EWPs are simple, robust, and competitive out-of-sample, yet the uncertainty about which subset truly performs best is largely ignored. Traditional approaches typically rely on a single selected portfolio, but this fails to consider alternative investment strategies that may perform just as well when accounting for statistical uncertainty. To address this selection uncertainty, we introduce the Selection Confidence Set (SCS) for EWPs: the set of all portfolios that, under a given loss function and at a specified confidence level, contains the unknown set of optimal portfolios under repeated sampling. The SCS quantifies selection uncertainty by identifying a range of plausible portfolios, challenging the idea of a uniquely optimal choice. Like a confidence set, its size reflects uncertainty -- growing with noisy or limited data, and shrinking as the sample size increases. Theoretically, we establish that the SCS covers the unknown optimal selection with high probability and characterize how its size grows with underlying uncertainty, corroborating these results through Monte Carlo experiments. Applications to the French 17-Industry Portfolios and Layer-1 cryptocurrencies underscore the importance of accounting for selection uncertainty when comparing equally weighted strategies.

q-fin.PM↗

arXiv2023

Sparse Graphical Modelling via the Sorted L$_1$-Norm

Sparse graphical modelling has attained widespread attention across various academic fields. We propose two new graphical model approaches, Gslope and Tslope, which provide sparse estimates of the precision matrix by penalizing its sorted L1-norm, and relying on Gaussian and T-student data, respectively. We provide the selections of the tuning parameters which provably control the probability of including false edges between the disjoint graph components and empirically control the False Discovery Rate for the block diagonal covariance matrices. In extensive simulation and real world analysis, the new methods are compared to other state-of-the-art sparse graphical modelling approaches. The results establish Gslope and Tslope as two new effective tools for sparse network estimation, when dealing with both Gaussian, t-student and mixture data.

stat.ME↗

arXiv2022

Environmental, Social, Governance scores and the Missing pillar -- Why does missing information matter?

Environmental, Social, and Governance (ESG) scores measure companies' performance concerning sustainability and societal impact and are organized on three pillars: Environmental (E), Social (S), and Governance (G). These complementary non-financial ESG scores should provide information about the ESG performance and risks of different companies. However, the extent of not yet published ESG information makes the reliability of ESG scores questionable. To explicitly denote the not yet published information on ESG category scores, a new pillar, the so-called Missing (M) pillar, is formulated. Environmental, Social, Governance, and Missing (ESGM) scores are introduced to consider the potential release of new information in the future. Furthermore, an optimization scheme is proposed to compute ESGM scores, linking them to the companies' riskiness. By relying on the data provided by Refinitiv, we show that the ESGM scores strengthen the companies' risk relationship. These new scores could benefit investors and practitioners as ESG exclusion strategies using only ESG scores might exclude assets with a low score solely because of their missing information and not necessarily because of a low ESG merit.

q-fin.RM↗

arXiv2022

A generalized precision matrix for t-Student distributions in portfolio optimization

The Markowitz model is still the cornerstone of modern portfolio theory. In particular, when focusing on the minimum-variance portfolio, the covariance matrix or better its inverse, the so-called precision matrix, is the only input required. So far, most scholars worked on improving the estimation of the input, however little attention has been given to the limitations of the inverse covariance matrix when capturing the dependence structure in a non-Gaussian setting. While the precision matrix allows to correctly understand the conditional dependence structure of random vectors in a Gaussian setting, the inverse of the covariance matrix might not necessarily result in a reliable source of information when Gaussianity fails. In this paper, exploiting the local dependence function, different definitions of the generalized precision matrix (GPM), which holds for a general class of distributions, are provided. In particular, we focus on the multivariate t-Student distribution and point out that the interaction in random vectors does not depend only on the inverse of the covariance matrix, but also on additional elements. We test the performance of the proposed GPM using a minimum-variance portfolio set-up by considering S\&P 100 and Fama and French industry data. We show that portfolios relying on the GPM often generate statistically significant lower out-of-sample variances than state-of-art methods.

q-fin.ST↗

arXiv2021

ESG, Risk, and (Tail) Dependence

While environmental, social, and governance (ESG) trading activity has been a distinctive feature of financial markets, the debate if ESG scores can also convey information regarding a company's riskiness remains open. Regulatory authorities, such as the European Banking Authority (EBA), have acknowledged that ESG factors can contribute to risk. Therefore, it is important to model such risks and quantify what part of a company's riskiness can be attributed to the ESG scores. This paper aims to question whether ESG scores can be used to provide information on (tail) riskiness. By analyzing the (tail) dependence structure of companies with a range of ESG scores, that is within an ESG rating class, using high-dimensional vine copula modelling, we are able to show that risk can also depend on and be directly associated with a specific ESG rating class. Empirical findings on real-world data show positive not negligible ESG risks determined by ESG scores, especially during the 2008 crisis.

q-fin.RM↗

arXiv2021

A 2-stage elastic net algorithm for estimation of sparse networks with heavy tailed data

We propose a new 2-stage procedure that relies on the elastic net penalty to estimate a network based on partial correlations when data are heavy-tailed. The new estimator allows to consider the lasso penalty as a special case. Using Monte Carlo simulations, we test the performance on several underlying network structures and four different multivariate distributions: Gaussian, t-Student with 3 and 20 degrees of freedom and contaminated Gaussian. Simulation analysis shows that the 2-stage estimator performs best for heavy-tailed data and it is also robust to distribution misspecification, both in terms of identification of the sparsity patterns and numerical accuracy. Empirical results on real-world data focus on the estimation of the European banking network during the Covid-19 pandemic. We show that the new estimator can provide interesting insights both for the development of network indicators, such as network strength, to identify crisis periods and for the detection of banking network properties, such as centrality and level of interconnectedness, that might play a relevant role in setting up adequate risk management and mitigation tools.

stat.ME↗

arXiv2021

New estimation approaches for graphical models with elastic net penalty

In the context of undirected Gaussian graphical models, we introduce three estimators based on elastic net penalty for the underlying dependence graph. Our goal is to estimate the sparse precision matrix, from which to retrieve both the underlying conditional dependence graph and the partial correlation graph. The first estimator is derived from the direct penalization of the precision matrix in the likelihood function, while the second from using conditional penalized regressions to estimate the precision matrix. Finally, the third estimator relies on a 2-stages procedure that estimates the edge set first and then the precision matrix elements. Through simulations we investigate the performances of the proposed methods on a large set of well-known network structures. Empirical results on simulated data show that the 2-stages procedure outperforms all other estimators both w.r.t. estimating the sparsity pattern in the graph and the edges' weights. Finally, using real-world data on US economic sectors, we estimate dependencies and show the impact of Covid-19 pandemic on the network strength.

stat.ME↗

arXiv2019

Modelling Extremal Dependence for Operational Risk by a Bipartite Graph

We introduce a statistical model for operational losses based on heavy-tailed distributions and bipartite graphs, which captures the event type and business line structure of operational risk data. The model explicitly takes into account the Pareto tails of losses and the heterogeneous dependence structures between them. We then derive estimators for individual as well as aggregated tail risk, measured in terms of Value-at-Risk and Conditional-Tail-Expectation for very high confidence levels, and provide also an asymptotically full capital allocation method. Estimation methods for such tail risk measures and capital allocations are also proposed and tested on simulated data. Finally, by having access to real-world operational risk losses from the Italian banking system, we show that even with a small number of observations, the proposed estimation methods produce reliable estimates, and that quantifying dependence by means of the empirical network has a big impact on estimates at both individual and aggregate level, as well as for capital allocations.

q-fin.RM↗

arXiv2017

Sparse Portfolio Selection via the sorted $\ell_{1}$-Norm

We introduce a financial portfolio optimization framework that allows us to automatically select the relevant assets and estimate their weights by relying on a sorted $\ell_1$-Norm penalization, henceforth SLOPE. Our approach is able to group constituents with similar correlation properties, and with the same underlying risk factor exposures. We show that by varying the intensity of the penalty, SLOPE can span the entire set of optimal portfolios on the risk-diversification frontier, from minimum variance to the equally weighted. To solve the optimization problem, we develop a new efficient algorithm, based on the Alternating Direction Method of Multipliers. Our empirical analysis shows that SLOPE yields optimal portfolios with good out-of-sample risk and return performance properties, by reducing the overall turnover through more stable asset weight estimates. Moreover, using the automatic grouping property of SLOPE, new portfolio strategies, such as SLOPE-MV, can be developed to exploit the data-driven detected similarities across assets.

q-fin.PM↗

arXiv2015

Asset Allocation Strategies Based on Penalized Quantile Regression

It is well known that quantile regression model minimizes the portfolio extreme risk, whenever the attention is placed on the estimation of the response variable left quantiles. We show that, by considering the entire conditional distribution of the dependent variable, it is possible to optimize different risk and performance indicators. In particular, we introduce a risk-adjusted profitability measure, useful in evaluating financial portfolios under a pessimistic perspective, since the reward contribution is net of the most favorable outcomes. Moreover, as we consider large portfolios, we also cope with the dimensionality issue by introducing an l1-norm penalty on the assets weights.

q-fin.PM↗

arXiv2012

Adaptive Minimax Estimation over Sparse $\ell_q$-Hulls

Given a dictionary of $M_n$ initial estimates of the unknown true regression function, we aim to construct linearly aggregated estimators that target the best performance among all the linear combinations under a sparse $q$-norm ($0 \leq q \leq 1$) constraint on the linear coefficients. Besides identifying the optimal rates of aggregation for these $\ell_q$-aggregation problems, our multi-directional (or universal) aggregation strategies by model mixing or model selection achieve the optimal rates simultaneously over the full range of $0\leq q \leq 1$ for general $M_n$ and upper bound $t_n$ of the $q$-norm. Both random and fixed designs, with known or unknown error variance, are handled, and the $\ell_q$-aggregations examined in this work cover major types of aggregation problems previously studied in the literature. Consequences on minimax-rate adaptive regression under $\ell_q$-constrained true coefficients ($0 \leq q \leq 1$) are also provided. Our results show that the minimax rate of $\ell_q$-aggregation ($0 \leq q \leq 1$) is basically determined by an effective model size, which is a sparsity index that depends on $q$, $t_n$, $M_n$, and the sample size $n$ in an easily interpretable way based on a classical model selection theory that deals with a large number of models. In addition, in the fixed design case, the model selection approach is seen to yield optimal rates of convergence not only in expectation but also with exponential decay of deviation probability. In contrast, the model mixing approach can have leading constant one in front of the target risk in the oracle inequality while not offering optimality in deviation probability.

math.ST↗