Ricardo Masini

About

Ricardo Masini is an Assistant Professor at the University of California, Davis, Department of Statistics. His research encompasses a broad range of topics in statistics and econometrics, including counterfactual analysis, high-dimensional data analysis, and the development of new estimation techniques. His work often involves the application of advanced statistical methods such as machine learning, copulas, and factor models to address complex problems in economic and statistical inference. Masini has contributed to the theoretical and methodological foundations of statistical analysis, with publications in leading journals such as the Journal of Econometrics, Annals of Statistics, and the Journal of the American Statistical Association. His research includes the development of bounds for U-statistics, the integration of random forest methods with linear models, and the exploration of distributional counterfactual analysis in high-dimensional setups. He has also worked on the refinement of asymptotic approximations, the use of artificial controls for high-dimensional panel data, and the creation of statistical software tools, including an R package for artificial counterfactual estimation. His work aims to balance flexibility and interpretability in statistical modeling, advancing the understanding and application of modern statistical techniques in econometrics and related fields.

Research topics

• Computer Science
• Artificial Intelligence
• Statistics
• Econometrics
• Mathematics
• Economics
• Psychology
• Social psychology

Selected publications

• Bridging factor and sparse models

  The Annals of Statistics · 2023-08-01 · 44 citations

  article

  Factor and sparse models are widely used to impose a low-dimensional structure in high-dimensions. However, they are seemingly mutually exclusive. We propose a lifting method that combines the merits of these two models in a supervised learning methodology that allows for efficiently exploring all the information in high-dimensional datasets. The method is based on a flexible model for high-dimensional panel data with observable and/or latent common factors and idiosyncratic components. The mode…

  PublisherDOI

• Yurinskii's Coupling for Martingales

  arXiv (Cornell University) · 2022-10-01 · 3 citations

  preprintOpen access

  Yurinskii's coupling is a popular theoretical tool for non-asymptotic distributional analysis in mathematical statistics and applied probability, offering a Gaussian strong approximation with an explicit error bound under easily verifiable conditions. Originally stated in $\ell_2$-norm for sums of independent random vectors, it has recently been extended both to the $\ell_p$-norm, for $1 \leq p \leq \infty$, and to vector-valued martingales in $\ell_2$-norm, under some strong conditions. We pres…

  PublisherOA PDFDOI

• Constrained Polynomial Likelihood

  Journal of Business and Economic Statistics · 2024-09-03 · 2 citations

  article

  We develop a nonnegative polynomial minimum-norm likelihood ratio (PLR) of two distributions of which only moments are known. The sample PLR converges to the unknown population PLR under mild conditions. The methodology allows for additional shape restrictions, as we illustrate with two empirical applications. The first develops a PLR for the unknown transition density of a jump-diffusion process, while the second extracts a positive density directly from option prices. In both cases, we show th…

  PublisherDOI

• Higher-order refinements of small bandwidth asymptotics for density-weighted average derivative estimators

  Journal of Econometrics · 2024-09-21 · 2 citations

  articleSenior author
  PublisherDOI

• Regularized Estimation of High-Dimensional Vector AutoRegressions with\n Weakly Dependent Innovations

  arXiv (Cornell University) · 2019-12-18 · 2 citations

  preprintOpen access1st authorCorresponding

  There has been considerable advance in understanding the properties of sparse\nregularization procedures in high-dimensional models. In time series context,\nit is mostly restricted to Gaussian autoregressions or mixing sequences. We\nstudy oracle properties of LASSO estimation of weakly sparse\nvector-autoregressive models with heavy tailed, weakly dependent innovations\nwith virtually no assumption on the conditional heteroskedasticity. In contrast\nto current literature, our innovation proces…

  PublisherOA PDFDOI

Frequent coauthors

• Marcelo C. Medeiros

  University of Illinois Urbana-Champaign

  42 shared

• Carlos Carvalho

  Pontifical Catholic University of Rio de Janeiro

  13 shared

• Jianqing Fan

  12 shared

• Eduardo Mendes

  Institut polytechnique de Grenoble

  8 shared

• Victor Orestes

  3 shared

• Matias D. Cattaneo

  3 shared

• Gabriel Vasconcelos

  Brazilian Development Bank

  2 shared

• Yuri Fonseca

  2 shared

Similar researchers at University of California, Davis

• Xin Liuh-101
• Alan Hastingsh-97
• James Crutchfieldh-63