Software

Open-source code accompanying my research: software packages and replication code. Everything is available on GitHub under the MIT license.

Packages

Co-author(s): Chen Tong

Python (NumPy/SciPy) and Julia (VoigtInference.jl): two implementations with a common interface, cross-validated to within 10−12.

[GitHub] [Software note, arXiv] [Theory paper, arXiv]

Description: Exact likelihood calculus and conditional attribution for the Voigt profile, the convolution of a Gaussian and a Cauchy distribution: density, score, Hessian, Fisher information, maximum likelihood estimation, and the conditional moments of the Gaussian component (deconvolution), all from a single Faddeeva evaluation per observation and with numerically robust far-tail behavior. Installation and quick-start examples are in the README on GitHub.

Co-author(s): Ilya Archakov

Julia package (GFT.jl) and an R port with the same API (base R only), available on CRAN.

[GitHub] [CRAN] [Paper, arXiv]

Install: R: install.packages("GFT")    Julia: using Pkg; Pkg.add(url = "https://github.com/reinhardhansen/GFT")

Description: Forward and inverse generalized Fisher transformation of correlation matrices, γ = vecl(log C), which maps the positive definite correlation matrices one-to-one onto the Euclidean space of dimension n(n−1)/2 (Archakov and Hansen, 2021, Econometrica). The inverse is computed with the GFT-FP+N algorithm: matrix-free inexact Newton steps with fixed-point safeguards that guarantee global convergence.

Replication Code

  • Bartlett Couplings of the Onion and Vine LKJ Samplers (2026). [Code] [Zenodo] [arXiv]
  • Exact Likelihood Inference and Robust Filtering for Gauss-Cauchy Convolution Models, with Chen Tong (2026). [Code] [arXiv]
  • Generalized Reduced Rank Regression. [Code]
  • Principled Identification of Structural Dynamic Models, with Neville Francis and Chen Tong (2025). [Code] [arXiv]
  • Moments by Integrating the Moment-Generating Function, with Chen Tong (2024). [Code] [arXiv]
  • Relative Contagiousness of Emerging Virus Variants: An Analysis of the Alpha, Delta, and Omicron SARS-CoV-2 Variants, Econometrics Journal (2022). [Code] [arXiv]