Astrostatistics & Data Science — Eric Ford

← Research Themes

Astrostatistics & Data Science

Extracting reliable scientific conclusions from astronomical observations requires sophisticated statistical methods. Our group develops and applies Bayesian inference, MCMC algorithms, Gaussian processes, approximate Bayesian computation, and physics-informed machine learning to problems across exoplanet science.

Key Projects

Reviews & Methodology

I have contributed to review articles and methodological frameworks that survey the state of the art in statistical exoplanet science. Hara & Ford (Annual Review of Statistics and Its Application, 2023) frames radial velocity analysis as detection and parameter estimation in unevenly-sampled multivariate time series with correlated stochastic signals. I also contributed to community planning for AI in the Mathematical and Physical Sciences (Ferguson et al. 2025).

MCMC for Exoplanet Analysis

Our group has a long history of applying Markov chain Monte Carlo methods to radial velocity exoplanet surveys, beginning with early work on incorporating MCMC into RV analysis (Ford 2005, 2006). This continues with differential-evolution MCMC and Bayesian evidence estimation for multi-planet radial-velocity systems (Nelson et al. 2014, 2020), enabling robust detection and characterization of planetary signals in the presence of stellar noise.

Multi-Dimensional Nonparametric Models

The MRExo package implements nonparametric and probabilistic frameworks for jointly modeling planet observables such as mass, radius, insolation, and stellar mass. Kanodia et al. (2023) generalized earlier mass-radius relationships to handle up to four observables simultaneously, with asymmetric uncertainties and upper limits, revealing how composition trends evolve with insolation and host-star mass.

Correlated Noise in EPRV Time Series

Achieving the mass precision needed to characterize Earth-analog planets requires careful treatment of correlated noise in radial velocity time series. Our work (Luhn et al. 2023) quantified how correlated stellar and instrumental noise propagates into planet mass uncertainties, establishing realistic limits on what current and future EPRV surveys can achieve and informing observing strategy for detecting Earth-mass planets.

Selected Publications

  • Architectures of Exoplanetary Systems. IV: A Multi-planet Model for Reproducing the Radius Valley and Intra-system Size Similarity of Planets around Kepler's FGK Dwarfs
    He, Matthias Y., Ford, Eric B. (2026), arXiv e-prints, arXiv:2601.13480. abstract doi
  • The Future of Artificial Intelligence and the Mathematical and Physical Sciences (AI+MPS)
    Ferguson, Andrew et al. (2025), arXiv e-prints, arXiv:2509.02661. abstract doi
  • Enhancing Exoplanet Surveys via Physics-informed Machine Learning
    Ford, Eric B. (2025), 19, 1-10. abstract doi
  • Order-by-order Modeling of Exoplanet Radial Velocity Data
    Langford, Zachary et al. (2025), PASP, 137, 114503. abstract doi
  • Searching for Low-mass Exoplanets amid Stellar Variability with a Fixed Effects Linear Model of Line-by-line Shape Changes
    Salzer, Joseph et al. (2025), AJ, 170, 179. abstract doi
  • Earths within Reach: Evaluation of Strategies for Mitigating Solar Variability using 3.5 years of NEID Sun-as-a-Star Observations
    Ford, Eric B. et al. (2024), arXiv e-prints, arXiv:2408.13318. abstract doi
  • Data-Driven Modeling of Telluric Features and Stellar Variability with StellarSpectraObservationFitting.jl
    Gilbertson, Christian et al. (2024), arXiv e-prints, arXiv:2408.17289. abstract doi
  • Statistical Methods for Exoplanet Detection with Radial Velocities
    Hara, Nathan C., Ford, Eric B. (2023), Annual Review of Statistics and Its Application, 10, 623-649. abstract doi
  • Beyond Two-dimensional Mass─Radius Relationships: A Nonparametric and Probabilistic Framework for Characterizing Planetary Samples in Higher Dimensions
    Kanodia, Shubham et al. (2023), ApJ, 956, 76. abstract doi
  • Debiasing the Minimum-mass Extrasolar Nebula: On the Diversity of Solid Disk Profiles
    He, Matthias Y., Ford, Eric B. (2022), AJ, 164, 210. abstract doi
  • FIESTA II. Disentangling Stellar and Instrumental Variability from Exoplanetary Doppler Shifts in the Fourier Domain
    Zhao, J., Ford, Eric B., Tinney, C.~G. (2022), ApJ, 935, 75. abstract doi
  • The EXPRES Stellar Signals Project II. State of the Field in Disentangling Photospheric Velocities
    Zhao, Lily L. et al. (2022), AJ, 163, 171. abstract doi
  • Friends and Foes: The Conditional Occurrence of Planetary Companions to Transiting Exoplanets and their Impact on Radial Velocity Follow-up Observations
    He, Matthias Y., Ford, Eric B., Ragozzine, Darin (2021), 122. abstract doi
  • Following Up the Kepler Field: Masses of Targets for Transit Timing and Atmospheric Characterization
    Jontof-Hutter, Daniel et al. (2021), AJ, 161, 246. abstract doi
  • Evidence for a Nondichotomous Solution to the Kepler Dichotomy: Mutual Inclinations of Kepler Planetary Systems from Transit Duration Variations
    Millholland, Sarah C. et al. (2021), AJ, 162, 166. abstract doi
  • Toward Extremely Precise Radial Velocities. II. A Tool for Using Multivariate Gaussian Processes to Model Stellar Activity
    Gilbertson, Christian et al. (2020), ApJ, 905, 155. abstract doi
  • Quantifying the Bayesian Evidence for a Planet in Radial Velocity Data
    Nelson, Benjamin E. et al. (2020), AJ, 159, 73. abstract doi
  • Scheduling Discovery in the 2020s
    Bellm, Eric et al. (2019), 51, 125. abstract doi
  • Architectures of exoplanetary systems - I. A clustered forward model for exoplanetary systems around Kepler's FGK stars
    He, Matthias Y., Ford, Eric B., Ragozzine, Darin (2019), MNRAS, 490, 4575-4605. abstract doi
  • Occurrence Rates of Planets Orbiting FGK Stars: Combining Kepler DR25, Gaia DR2, and Bayesian Inference
    Hsu, Danley C. et al. (2019), AJ, 158, 109. abstract doi
  • The Next Decade of Astroinformatics and Astrostatistics
    Siemiginowska, Aneta et al. (2019), \baas, 51, 355. abstract doi
  • The efficiency of geometric samplers for exoplanet transit timing variation models
    Tuchow, Noah W. et al. (2019), MNRAS, 484, 3772-3784. abstract doi
  • Improving the Accuracy of Planet Occurrence Rates from Kepler Using Approximate Bayesian Computation
    Hsu, Danley C. et al. (2018), AJ, 155, 205. abstract doi
  • Improving Exoplanet Detection Power: Multivariate Gaussian Process Models for Stellar Activity
    Jones, David E. et al. (2017), arXiv e-prints, arXiv:1711.01318. abstract doi
  • Evidence for Two Hot-Jupiter Formation Paths
    Nelson, Benjamin E., Ford, Eric B., Rasio, Frederic A. (2017), AJ, 154, 106. abstract doi
  • Future of High-Dimensional Data-Driven Exoplanet Science
    Ford, Eric B. (2016), 699, 012007. abstract doi
  • Geometric adaptive Monte Carlo in random environment
    Papamarkou, Theodore, Lindo, Alexey, Ford, Eric B. (2016), arXiv e-prints, arXiv:1608.07986. abstract doi
  • The Small Exoplanet Mass-Radius Relation: Quantifying the Astrophysical Scatter
    Wolfgang, Angie, Rogers, Leslie A., Ford, Eric B. (2016), IAU Focus Meeting, 29A, 223-223. abstract doi
  • Probabilistic Mass-Radius Relationship for Sub-Neptune-Sized Planets
    Wolfgang, Angie, Rogers, Leslie A., Ford, Eric B. (2016), ApJ, 825, 19. abstract doi
  • Time Variation of Kepler Transits Induced by Stellar Spots - A Way to Distinguish between Prograde and Retrograde Motion. II. Application to KOIs
    Holczer, Tomer et al. (2015), ApJ, 807, 170. abstract doi
  • RUN DMC: An Efficient, Parallel Code for Analyzing Radial Velocity Observations Using N-body Integrations and Differential Evolution Markov Chain Monte Carlo
    Nelson, Benjamin, Ford, Eric B., Payne, Matthew J. (2014), ApJS, 210, 11. abstract doi
  • Transit Timing Observations from Kepler. II. Confirmation of Two Multiplanet Systems via a Non-parametric Correlation Analysis
    Ford}, Eric B. et al. (2012), ApJ, 750, 113. abstract doi
  • Almost All of Kepler's Multiple-planet Candidates Are Planets
    Lissauer, Jack J. et al. (2012), ApJ, 750, 112. abstract doi
  • A Bayesian Surrogate Model for Rapid Time Series Analysis and Application to Exoplanet Observations
    Ford, Eric B., Moorhead, Althea V., Veras, Dimitri (2011), arXiv e-prints, arXiv:1107.4047. abstract doi
  • Transit Timing Observations from Kepler. I. Statistical Analysis of the First Four Months
    Ford, Eric B. et al. (2011), ApJS, 197, 2. abstract doi
  • The Distribution of Transit Durations for Kepler Planet Candidates and Implications for Their Orbital Eccentricities
    Moorhead, Althea V. et al. (2011), ApJS, 197, 1. abstract doi
  • Observational biases in determining extrasolar planet eccentricities in single-planet systems
    Zakamska, Nadia L., Pan, Margaret, Ford, Eric B. (2011), MNRAS, 410, 1895-1910. abstract doi
  • Adaptive Scheduling Algorithms for Planet Searches
    Ford, Eric B. (2008), AJ, 135, 1008-1020. abstract doi
  • Cadence optimisation and exoplanetary parameter sensitivity
    Kane, Stephen R., Ford, Eric B., Ge, Jian (2008), 249, 115-118. abstract doi
  • Role of Dynamical Research in the Detection and Characterization of Exoplanets
    Ford, Eric B. et al. (2007), arXiv e-prints, arXiv:0705.2781. abstract doi
  • Structure and Evolution of Nearby Stars with Planets. II. Physical Properties of ~1000 Cool Stars from the SPOCS Catalog
    Takeda, Genya et al. (2007), ApJS, 168, 297-318. abstract doi
  • Improving the Efficiency of Markov Chain Monte Carlo for Analyzing the Orbits of Extrasolar Planets
    Ford, Eric B. (2006), ApJ, 642, 505-522. abstract doi
  • The Effects of Multiple Companions on the Efficiency of Space Interferometry Mission Planet Searches
    Ford, Eric B. (2006), PASP, 118, 364-384. abstract doi
  • Quantifying the Uncertainty in the Orbits of Extrasolar Planets
    Ford, Eric B. (2005), AJ, 129, 1706-1717. abstract doi
  • Choice of Observing Schedules for Astrometric Planet Searches
    Ford, Eric B. (2004), PASP, 116, 1083-1092. abstract doi

Software

ExpectationMaximizationPCA.jl

Julia code for computing a "weighted" PCA using EM algorithm.

PlanetSEmu

Emulating the distribution of planetary architectures.

RUN DMC

Radial velocity Using N-body Differential evolution Markov Chain Monte Carlo. Efficient parallel Bayesian code for fitting multi-planet radial velocity data with self-consistent N-body integrations, particularly for systems near mean-motion resonances.