Data analysis recipes: Using Markov Chain Monte Carlo

Abstract

Markov Chain Monte Carlo (MCMC) methods for sampling probability density functions (combined with abundant computational resources) have transformed the sciences, especially in performing probabilistic inferences, or fitting models to data. In this primarily pedagogical contribution, we give a brief overview of the most basic MCMC method and some practical advice for the use of MCMC in real inference problems. We give advice on method choice, tuning for performance, methods for initialization, tests of convergence, troubleshooting, and use of the chain output to produce or report parameter estimates with associated uncertainties. We argue that autocorrelation time is the most important test for convergence, as it directly connects to the uncertainty on the sampling estimate of any quantity of interest. We emphasize that sampling is a method for doing integrals; this guides our thinking about how MCMC output is best used.

A purely pedagogical contribution

References in corpus (7)

• The NumPy array: a structure for efficient numerical computation
• Exoplanet population inference and the abundance of Earth analogs from noisy, incomplete catalogs
• Markov Chain Monte Carlo Methods for Bayesian Data Analysis in Astronomy
• Inferring the eccentricity distribution
• Data analysis recipes: Fitting a model to data
• The Joker: A custom Monte Carlo sampler for binary-star and exoplanet radial velocity data
• Data analysis recipes: Probability calculus for inference

Cited by in corpus (159)

• Binary companions of evolved stars in APOGEE DR14: Search method and catalog of ~5,000 companions
• Bayesian inference for compact binary coalescences with BILBY: Validation and application to the first LIGO--Virgo gravitational-wave transient catalogue
• An introduction to Bayesian inference in gravitational-wave astronomy: parameter estimation, model selection, and hierarchical models
• Multi-system Bayesian constraints on the transport coefficients of QCD matter
• Data Analysis for Precision 21 cm Cosmology
• The Spur and the Gap in GD-1: Dynamical evidence for a dark substructure in the Milky Way halo
• Nested sampling for physical scientists
• The Featureless Transmission Spectra of Two Super-Puff Planets
• Pyaneti: a fast and powerful software suite for multi-planet radial velocity and transit fitting
• Inferring the Energy and Distance Distributions of Fast Radio Bursts using the First CHIME/FRB Catalog
• Higher order gravitational-wave modes with likelihood reweighting
• Bilby-MCMC: An MCMC sampler for gravitational-wave inference
• The Coherent Magnetic Field of the Milky Way
• Evidence of Three Mechanisms Explaining the Radius Anomaly of Hot Jupiters
• Galactic Archaeology with asteroseismic ages. II. Confirmation of a delayed gas infall using Bayesian analysis based on MCMC methods
• The UTMOST pulsar timing programme II: Timing noise across the pulsar population
• The surprising accuracy of isothermal Jeans modelling of self-interacting dark matter density profiles
• AGN Variability Analysis Handbook
• Massive neutrinos and cosmic composition
• The VMC survey -- XLIII. The spatially resolved star formation history across the Large Magellanic Cloud
• Bias and robustness of eccentricity estimates from radial velocity data
• Eryn : A multi-purpose sampler for Bayesian inference
• Adaptive weighting of Bayesian physics informed neural networks for multitask and multiscale forward and inverse problems
• The Relationship Between Globular Cluster Mass, Metallicity, and Light Element Abundance Variations
• Horizons: Nuclear Astrophysics in the 2020s and Beyond
• PRODIGE -- Envelope to Disk with NOEMA II. Small-scale temperature structure and a streamer feeding the SVS13A protobinary using CH3CN and DCN
• nestcheck: diagnostic tests for nested sampling calculations
• Standard-siren cosmology using gravitational waves from binary black holes
• Toward a Better Understanding of Cosmic Chronometers: Stellar Population Properties of Passive Galaxies at Intermediate Redshift
• Removing degeneracy and multimodality in gravitational wave source parameters
• Comprehensive analysis of a dense sample of FRB 121102 bursts
• Exploring dark matter spike distribution around the Galactic centre with stellar orbits
• Looking at Blazar Light Curve Periodicities with Gaussian Processes
• Host star metallicity of directly imaged wide-orbit planets: implications for planet formation
• Hierarchical multi-stage MCMC follow-up of continuous gravitational wave candidates
• Robust sampling for weak lensing and clustering analyses with the Dark Energy Survey
• Lorentz Factors of compact jets in Black hole X-ray binaries
• Cosmology with varying fundamental constants from hyperlight, coupled scalars
• Detectability of the subdominant mode in a binary black hole ringdown
• Inference of cosmic-ray source properties by conditional invertible neural networks
• Consistency of the Parkes Pulsar Timing Array Signal with a Nanohertz Gravitational-wave Background
• Methane Emission From a Cool Brown Dwarf
• The cosmic abundance of cold gas in the local Universe
• A multi-wavelength view of the neutron star binary 1FGL J1417.7--4402: A progenitor to canonical millisecond pulsars
• Self-consistent analysis of stellar clusters: An application to HST data of the halo globular cluster NGC 6752
• Constraints on Yukawa gravity parameters from observations of bright stars
• Exoplanet Characterization using Conditional Invertible Neural Networks
• Cosmological parameter estimation with Genetic Algorithms
• Parametrizing gravitational-wave polarizations
• Dissecting the Gaia HR diagram within 200 pc
• A comparison of optimisation algorithms for high-dimensional particle and astrophysics applications
• From Carbon to Cobalt: Chemical compositions and ages of $z\sim 0.7$ quiescent galaxies
• The Issues of Mismodelling Gravitational-Wave Data for Parameter Estimation
• Total mass density slopes of early-type galaxies using Jeans dynamical modelling at redshifts $0.29<z<0.55$
• Matter ejections behind the highs and lows of the transitional millisecond pulsar PSR J1023+0038
• Variational Inference as an alternative to MCMC for parameter estimation and model selection
• Bayesian Inference analysis of jet quenching using inclusive jet and hadron suppression measurements
• The First Day in the Life of a Magnetar: Evolution of the Inclination Angle, Magnetic Dipole Moment and Braking Index of Millisecond Magnetars During Gamma-Ray Burst Afterglows
• Probing Transit Timing Variation and its Possible Origin with Twelve New Transits of TrES-3b
• Application of a Steady-State Accretion Disk Model to Spectrophotometry and High-Resolution Spectra of Two Recent FU Ori Outbursts
• Simple and statistically sound recommendations for analysing physical theories
• Starspot mapping with adaptive parallel tempering I: Implementation of computational code
• Cosmological Inference from Galaxy-Clustering Power Spectrum: Gaussianization and Covariance Decomposition
• Benchmarking Simulation-Based Inference
• Bayesian Inference of Fine-Features of Nuclear Equation of State from Future Neutron Star Radius Measurements to 0.1km Accuracy
• Evidence for conservative mass transfer in the classical Algol system $\delta$ Librae from its surface carbon-to-nitrogen abundance ratio
• Understanding binary neutron star collisions with hypermodels
• Evidence for magnetic activity at starbirth: a powerful X-ray flare from the Class 0 protostar HOPS 383
• Direct-imaging Discovery of a Substellar Companion Orbiting the Accelerating Variable Star, HIP 39017
• Probing jet launching in neutron star X-ray binaries: the variable and polarized jet of SAX J1808.4-3658
• Stability Constrained Characterization of Multiplanet Systems
• Experimental determination of the dissociative recombination rate coefficient for rotationally-cold CH${}^{+}$ and its implications for the diffuse cloud chemistry
• TOI 122b and TOI 237b, two small warm planets orbiting inactive M dwarfs, found by \textit{TESS}
• OGLE-2019-BLG-1470LABc: Another Microlensing Giant Planet in a Binary System?
• High Sensitivity Observations of the Water Megamasers of NGC 1068: Precise Astrometry and Detailed Kinematics
• Exploring the Origins of Earth's Nitrogen: Astronomical Observations of Nitrogen-bearing Organics in Protostellar Environments
• Revisiting KELT-19Ab, WASP-156b and WASP-121b in the TESS Era
• NEID Reveals that The Young Warm Neptune TOI-2076 b Has a Low Obliquity
• Transverse Oscillations of the M87 Jet Revealed by KaVA Observations
• PRODIGE -- Envelope to Disk with NOEMA III. The origin of complex organic molecule emission in SVS13A
• Myrzakulov $F(T,Q)$ gravity: cosmological implications and constraints
• Detecting the periodicity of highly irregularly sampled light-curves with Gaussian processes: the case of SDSSJ025214.67-002813.7
• The MAGPI Survey: Impact of environment on the total internal mass distribution of galaxies in the last 5 Gyr
• Looking for Traces of Non-minimally Coupled Dark Matter in the X-COP Galaxy Clusters Sample
• Spica and the annual cycle of PKS B1322-110 scintillations
• MAXI and NuSTAR observations of the faint X-ray transient MAXI J1848-015 in the GLIMPSE-C01 Cluster
• Constraining Chameleon screening using galaxy cluster dynamics
• How accurately can we measure the baryon acoustic oscillation feature?
• A comparison of Bayesian sampling algorithms for high-dimensional particle physics and cosmology applications
• CHEX-MATE: CLUster Multi-Probes in Three Dimensions (CLUMP-3D), I. Gas Analysis Method using X-ray and Sunyaev-Zel'dovich Effect Data
• Central kinematics of the Galactic globular cluster M80
• Emerging Directions in Geophysical Inversion
• exoALMA. VIII. Probabilistic Moment Maps and Data Products using Non-parametric Linear Models
• The dispersion measure and scattering of Fast Radio Bursts: contributions from multi-components, and clues for the intrinsic properties
• VERITAS discovery of very high energy gamma-ray emission from S3 1227+25 and multiwavelength observations
• Constraining black hole feedback in galaxy clusters from X-ray power spectra
• Adaptive Kernel Density Estimation proposal in gravitational wave data analysis
• Velocity distribution of elliptical galaxies in the framework of Non-local Gravity model
• Deep Learning and genetic algorithms for cosmological Bayesian inference speed-up
• Flow Matching for Atmospheric Retrieval of Exoplanets: Where Reliability meets Adaptive Noise Levels
• A Dwarf Disrupting -- Andromeda XXVII and the North West Stream
• Testing generalized scalar-tensor theories of gravity with clusters of galaxies
• Does the Redshift Distribution of Swift Long GRBs Trace the Star-Formation Rate?
• Measurement of the vertical atmospheric density profile from the X-ray Earth occultation of the Crab Nebula with Insight-HXMT
• Exploiting Network Topology for Accelerated Bayesian Inference of Grain Surface Reaction Networks
• Accelerating Tests of General Relativity with Gravitational-Wave Signals using Hybrid Sampling
• The 31-year Rotation History of the Millisecond Pulsar J1939+2134 (B1937+21)
• Probing the absorption of gamma-rays by IR radiation from the dusty torus in FSRQs with the Cherenkov Telescope Array
• An n-dimensional Rosenbrock Distribution for MCMC Testing
• Spin precession frequencies of a test gyroscope around a naked singularity and quasi-periodic oscillations
• Tentative Evidence for Transit Timing Variations of WASP-161b
• New stellar age estimates using SPInS based on Gaia DR3 photometry and LAMOST DR8 abundances
• Probabilistic Inversions for Time-Distance Helioseismology
• Data Analysis Recipes: Products of multivariate Gaussians in Bayesian inferences
• Cosmological parameter constraints using phenomenological symbolic expressions: On the significance of symbolic expression complexity and accuracy
• Spectral evolution responsible for the transition from positive lags to negative lags in Gamma-ray Bursts
• Deep learning to improve the discovery of near-Earth asteroids in the Zwicky Transient Facility
• Quantifying the Impact of Starspot-Crossing Events on Retrieved Parameters from Transit Lightcurves
• Bayesian Active Search on Parameter Space: a 95 GeV Spin-0 Resonance in the ($B-L$)SSM
• The Featureless HST/WFC3 Transmission Spectrum of the Rocky Exoplanet GJ 1132b: No Evidence For A Cloud-Free Primordial Atmosphere and Constraints on Starspot Contamination
• Informative Bayesian model selection for RR Lyrae star classifiers
• Revisiting the Local Star-Forming Galaxies Observed in the HETDEX Pilot Survey
• Polarized multiwavelength emission from pulsar wind - accretion disk interaction in a transitional millisecond pulsar
• A Multi-wavelength Characterization of the 2023 Outburst of MAXI J1807+132: Manifestations of Disk Instability and Jet Emission
• One Stream or Two -- Exploring Andromeda's North West Stream
• The nature of the Eastern Extent in the outer halo of M31
• K2, Spitzer, and TESS Transits of Four Sub-Neptune Exoplanets
• Probing neutral outflows in z ~ 2 galaxies using JWST observations of Ca II H and K absorption lines
• Spectral Mixture Modeling with Laboratory Near-Infrared Data I: Insights into Compositional Analysis of Europa
• Constraints on a fifth force from the stellar orbits around the central supermassive black hole of the Milky Way
• Minimum gas mass accreted by spinning intermediate-mass black holes in stellar clusters
• Nauyaca: a new tool to determine planetary masses and orbital elements through transit timing analysis
• The LEGARE Project. I. Chemical evolution model of the Nuclear Stellar Disc in a Bayesian framework
• Detectability of Supernova Remnants with the Southern Wide-field Gamma-ray Observatory
• Rotation Curves in z~1-2 Star-Forming Disks: Comparison of Dark Matter Fractions and Disk Properties for Different Fitting Methods
• Quintessence dark energy model in non-linear $f(Q)$ theory with bulk-viscosity
• A Natural Explanation of the VPOS from Multistate Scalar Field Dark Matter
• Impact of model parameter degeneracy on leptonic radiation models. The case of blazar multi-wavelength spectra
• A kinematic and structural study of young open clusters in the Milky Way Galaxy using Gaia DR3 catalogue
• A Near-Infrared Extinction and Reddening Map Towards the Galactic Bulge Using UKIRT
• A Panchromatic JWST Spectrum of a Giant Starspot on the Fully Convective M-dwarf TOI-3884
• Using Computational Models to Uncover the Parameters of Three Kepler Binaries: KIC 5957123, KIC 8314879, and KIC 10727668
• Transverse Oscillations and Wave Propagation in the Magnetically Dominated M87 Jet
• The evolutionary history of ultra-compact accreting binaries. I. Chemical abundances and formation channel of the eclipsing AM CVn system ZTF J225237.05-051917.4 from HST spectroscopy
• Re-examining the Bayesian colour excess estimation for the local star-forming galaxies observed in the HETDEX Pilot Survey
• Cosmological implications and causality in $f(R,L_m,T)$ gravity theory with observational constraints
• From Geometry to Observation: Gravitational Waves and the Raychaudhuri Equation
• The morphological stability of open clusters: a new 2D perspective
• Parallel tempering as a mechanism for facilitating inference in hierarchical hidden Markov models
• Molecules with ALMA at Planet-forming Scales (MAPS) II: CLEAN Strategies for Synthesizing Images of Molecular Line Emission in Protoplanetary Disks
• Laser-probing the rotational cooling of molecular ions by electron collisions
• Quantifying the Quark Gluon Plasma
• Improving exoplanet mass characterisation with Bayesian model selection using the Learned Harmonic Mean Estimator
• Towards a Field Based Bayesian Evidence Inference from Nested Sampling Data
• Microlensing Events in the Galactic Plane Using the Zwicky Transient Facility
• Properties of the Lower Segment of M31's North West Stream
• High-precision broadband linear polarimetry of early-type binaries. V. The Binary System HD 165052 in Open Cluster NGC 6530
• K2-99 revisited: a non-inflated warm Jupiter, and a temperate giant planet on a 522-d orbit around a subgiant
• On the Presence of Angular-Velocity Offsets in Disk Galaxies