Data analysis recipes: Fitting a model to data

Abstract

We go through the many considerations involved in fitting a model to data, using as an example the fit of a straight line to a set of points in a two-dimensional plane. Standard weighted least-squares fitting is only appropriate when there is a dimension along which the data points have negligible uncertainties, and another along which all the uncertainties can be described by Gaussians of known variance; these conditions are rarely met in practice. We consider cases of general, heterogeneous, and arbitrarily covariant two-dimensional uncertainties, and situations in which there are bad data (large outliers), unknown uncertainties, and unknown but expected intrinsic scatter in the linear relationship being fit. Above all we emphasize the importance of having a "generative model" for the data, even an approximate one. Once there is a generative model, the subsequent fitting is non-arbitrary because the model permits direct computation of the likelihood of the parameters or the posterior probability distribution. Construction of a posterior probability distribution is indispensible if there are "nuisance parameters" to marginalize away.

a chapter from a non-existent book

Cited by in corpus (121)

• Inferring the star-formation histories of massive quiescent galaxies with BAGPIPES: Evidence for multiple quenching mechanisms
• The Atlas3D project - XV. Benchmark for early-type galaxies scaling relations from 260 dynamical models: mass-to-light ratio, dark matter, Fundamental Plane and Mass Plane
• The Canadian Cluster Comparison Project: detailed study of systematics and updated weak lensing masses
• The H$\alpha$ emission of nearby M dwarfs and its relation to stellar rotation
• WATCHDOG: A Comprehensive All-Sky Database of Galactic Black Hole X-ray Binaries
• Planck 2015 results. XXVII. The Second Planck Catalogue of Sunyaev-Zeldovich Sources
• Data analysis recipes: Using Markov Chain Monte Carlo
• The origin of accreted stellar halo populations in the Milky Way using APOGEE, $\text{Gaia}$, and the EAGLE simulations
• Newly-quenched galaxies as the cause for the apparent evolution in average size of the population
• The VANDELS survey: the star-formation histories of massive quiescent galaxies at 1.0 < z < 1.3
• Transit Detection in the MEarth Survey of Nearby M Dwarfs: Bridging the Clean-First, Search-Later Divide
• Machine-Learned Identification of RR Lyrae Stars from Sparse, Multi-band Data: the PS1 Sample
• Clarifying the Hubble constant tension with a Bayesian hierarchical model of the local distance ladder
• Red giants observed by CoRoT and APOGEE: The evolution of the Milky Way's radial metallicity gradient
• Three years of Sun-as-a-star radial-velocity observations on the approach to solar minimum
• Recalibration of the virial factor and M-sigma relation for local active galaxies
• Constructing A Flexible Likelihood Function For Spectroscopic Inference
• Revisiting the Integrated Star Formation Law. Paper I: Non-Starbursting Galaxies
• Three Years of HARPS-N High-Resolution Spectroscopy and Precise Radial Velocity Data for the Sun
• On The Intrinsic Diversity of Type II-Plateau Supernovae
• Measuring Distances and Reddenings for a Billion Stars: Towards A 3D Dust Map from Pan-STARRS 1
• Chemo-kinematics of the $Gaia$ RR Lyrae: the halo and the disc
• AGN vs. host galaxy properties in the COSMOS field
• Carnegie Supernova Project-II: Extending the Near-Infrared Hubble Diagram for Type Ia Supernovae to $z\sim 0.1$
• Constraining New Physics Models with Isotope Shift Spectroscopy
• Radii of Young Star Clusters in Nearby Galaxies
• TESS Hunt for Young and Maturing Exoplanets (THYME) VI: an 11 Myr giant planet transiting a very low-mass star in Lower Centaurus Crux
• GHASP: an Hα kinematic survey of spiral and irregular galaxies -- IX. The NIR, stellar and baryonic Tully-Fisher relations
• Mutual distance dependence drives the observed jet power - radio luminosity scaling relations in radio galaxies
• Thermodynamic perturbations in the X-ray halo of 33 clusters of galaxies observed with Chandra ACIS
• Fitting $f(Q,T)$ gravity models with a $\Lambda$CDM limit using H(z) and Pantheon data
• Elemental Abundances in M31: The Kinematics and Chemical Evolution of Dwarf Spheroidal Satellite Galaxies
• A Case Against Spinning PAHs as the Source of the Anomalous Microwave Emission
• The PAU Survey: An improved photo-$z$ sample in the COSMOS field
• The similarity of the stellar mass fractions of galaxy groups and clusters
• Standard Galactic Field RR Lyrae II: A Gaia DR2 calibration of the period-Wesenheit-metallicity relation
• PHANGS-HST: Star Cluster Spectral Energy Distribution Fitting with CIGALE
• Constraints on interacting dark energy models through cosmic chronometers and Gaussian process
• Abundance-age relations with red clump stars in open clusters
• The non-linear infrared-radio correlation of low-z galaxies: implications for redshift evolution, a new radio SFR recipe, and how to minimize selection bias
• Testing asteroseismology with Gaia DR2: Hierarchical models of the Red Clump
• Redback: A Bayesian inference software package for electromagnetic transients
• The First Maps of ${\kappa }_d$ -- the Dust Mass Absorption Coefficient -- in Nearby Galaxies, with DustPedia
• A new determination of the primordial helium abundance using the analyses of HII region spectra from SDSS
• Prospects for Galactic and stellar astrophysics with asteroseismology of giant stars in the $TESS$ Continuous Viewing Zones and beyond
• Gaia-ESO Survey: The analysis of pre-main sequence stellar spectra
• A Probabilistic Approach to Fitting Period-Luminosity Relations and Validating Gaia Parallaxes
• The characteristic halo masses of half-a-million WISE-selected quasars
• CoMaLit - II. The scaling relation between mass and Sunyaev-Zel'dovich signal for Planck selected galaxy clusters
• Discovery of 36 eclipsing EL CVn binaries found by the Palomar Transient Factory
• Explaining temporal variations in the jet position angle of the blazar OJ 287 using its binary black hole central engine model
• Radial abundance gradients in the outer Galactic disk as traced by main-sequence OB stars
• Disc-Jet Coupling in the Terzan 5 Neutron Star X-ray Binary EXO 1745$-$248
• On parametrised cold dense matter equation of state inference
• Dynamical dark energy models in the light of Gravitational-Wave Transient Catalogues
• Constraints on variation of fine structure constant from joint SPT-SZ and XMM-Newton observations
• Secondary infall model and dark matter scaling relations in intermediate redshift early - type galaxies
• The Far-Infrared Radio Correlation at low radio frequency with LOFAR/H-ATLAS
• Re-observing the NLS1 Galaxy RE J1034+396. I. the Long-term, Recurrent X-ray QPO with a High Significance
• Globular clusters as tracers of the dark matter content of dwarfs in galaxy clusters
• The Fundamental Plane in the LEGA-C Survey: unraveling the $M/L$ variations of massive star-forming and quiescent galaxies at $z\sim 0.8$
• Kinematic modelling of clusters with Gaia: the Death Throes of the Hyades
• BAO from angular clustering: optimization and mitigation of theoretical systematics
• Likelihood Non-Gaussianity in Large-Scale Structure Analyses
• The Metal-Poor Stellar Halo in RAVE-TGAS and its Implications for the Velocity Distribution of Dark Matter
• The Re-Acceleration of the Shock Wave in the Radio Remnant of SN 1987A
• Modeling Kepler Eclipsing Binaries: Homogeneous Inference of Orbital & Stellar Properties
• Constraints on Yukawa gravity parameters from observations of bright stars
• The evolution of the Milky Way's thin disc radial metallicity gradient with K2 asteroseismic ages
• A New Method to Quantify X-ray Substructures in Clusters of Galaxies
• Microturbulent velocity from stellar spectra: a comparison between different approaches (Research Note)
• Sizing Up the Milky Way: A Bayesian Mixture Model Meta-Analysis of Photometric Scale Length Measurements
• Correlation between the gas-phase metallicity and ionization parameter in extragalactic HII regions
• Modelling the M*-SFR relation at high redshift: untangling factors driving biases in the intrinsic scatter measurement
• A Flux Scale for Southern Hemisphere 21cm EoR Experiments
• Improving sampling and calibration of GRBs as distance indicators
• On the evolution of cluster scaling relations
• Elemental abundances in M31: [Fe/H] and [α/Fe] in M31 Dwarf Galaxies Using Coadded Spectra
• Supernova PTF12glz: a possible shock breakout driven through an aspherical wind
• Bayesian correction of $H(z)$ data uncertainties
• The spatially-resolved gas and dust connection in neutral inflows and outflows in nearby AGN
• Made-to-measure modeling of observed galaxy dynamics
• Extended Dust Emission from Nearby Evolved Stars
• Generalised Fisher Matrices
• Introducing PT-REX, the Point-to-point TRend EXtractor
• Jupiter as an Exoplanet: Insights from Cassini Phase Curves
• Relationship between the Line Width of the Atomic and Molecular ISM in M33
• Constraints from Fermi observations of Long Gamma-Ray Bursts on cosmological parameters
• Where Is the Flux Going? The Long-Term Photometric Variability of Boyajian's Star
• Bayesian Linking of Geosynchronous Orbital Debris Tracks as seen by the Large Synoptic Survey Telescope
• Weak lensing shear estimation beyond the shape-noise limit: a machine learning approach
• NIR Tully-Fisher in the Zone of Avoidance. - II. 21 cm HI-line spectra of southern ZOA galaxies
• A Method for Selecting M dwarfs with an Increased Likelihood of Unresolved Ultra-cool Companionship
• Probing cosmic acceleration by strong gravitational lensing systems
• Galaxy And Mass Assembly (GAMA): The absence of stellar mass segregation in galaxy groups and consistent predictions from GALFORM and EAGLE simulations
• Bayesian analysis of Juno/JIRAM's NIR observations of Europa
• The Curious Case of Swift J1753.5-0127: A Black Hole Low-mass X-ray Binary Analogue to Z Cam Type Dwarf Novae
• Testing the chemical homogeneity of chemically tagged dissolved birth clusters
• Confirmation of the Long-Period Planet Orbiting Gliese 411 and the Detection of a New Planet Candidate
• The XMM Cluster Survey: evolution of the velocity dispersion -- temperature relation over half a Hubble time
• Data analysis recipes: Probability calculus for inference
• The first shear measurements from precision weak lensing
• System parameters of three short period cataclysmic variable stars
• Measuring glitch recoveries and braking indices with Bayesian model selection
• Galactic Magnetic Turbulence from Radio data
• A Spatially Resolved Radio Spectral Index Study of the Dwarf Irregular Galaxy NGC\,1569
• The 31-year Rotation History of the Millisecond Pulsar J1939+2134 (B1937+21)
• Aeolian sediment transport on Io from lava-frost interactions
• Decomposing galaxies with BANG: an automated morpho-kinematical decomposition of the SDSS-DR17 MaNGA survey
• The JWST EXCELS Survey: gas-phase metallicity evolution at 2 < z < 8
• Optimization of the multiple sampling and signal extraction in non-destructive exposures
• Fe XII and Fe XIII Line Widths in the Polar Off-limb Solar Corona up to 1.5 Rsun
• DECam Survey for Low-Mass Stars and Substellar Objects in the UCL and LCC Subgroups of the Sco-Cen OB Association (SCOCENSUS)
• Mean Occupation Function of High Redshift Quasars from the Planck Cluster Catalog
• Scaling of population resilience with dispersal length and habitat size
• Biases in inferring dark matter profiles from dynamical and lensing measurements
• Probing the anomalous positron fraction origin with fully leptonic decaying gravitino dark matter candidates
• New Giant Planet beyond the Snow Line for an Extended MOA Exoplanet Microlens Sample
• Titan in Transit: Ultraviolet Occultation Observations Reveal a Complex Atmospheric Structure
• From Geometry to Observation: Gravitational Waves and the Raychaudhuri Equation
• The link between star formation and gas in nearby galaxies