Aki Vehtari 2026-11-05
Aki Vehtari develops computational Bayesian statistics, including probabilistic programming, model diagnostics, model assessment and Gaussian processes. His author research page describes these as connected parts of a Bayesian workflow: specify a model, compute its implications, check the computation and examine predictive adequacy.[ref]
He coauthored Bayesian Data Analysis by Andrew Gelman and others. A posterior distribution summarizes uncertainty conditional on the model and data; checking whether that model reproduces important observations is a further task. This distinction connects Bayesian inference with posterior predictive checks, rather than treating successful computation as sufficient evidence that the model is suitable.[ref]
Bayesian Data Analysis by Andrew Gelman and others. Third-edition author list and model-checking exposition
Andrew Gelman Created 2026-10-25 Updated 2026-11-05
Andrew Gelman works on Bayesian statistics, statistical modelling and the interpretation of data in scientific and social questions. His research and teaching connect hierarchical Bayesian models, regression, computation and statistical graphics. His Columbia research page describes applications ranging from survey inference and elections to environmental and medical measurements.[ref]
A characteristic modelling problem is learning about many related groups: completely separate estimates can be noisy, while a single common estimate can hide differences. A hierarchical Bayesian model estimates group parameters together and lets the data influence their degree of pooling. Model checking, including posterior predictive checks, then asks whether simulated observations reproduce scientifically relevant features of the actual data. This connects fitting a model with examining the adequacy of its assumptions.
Portrait of Andrew Gelman
. Andrewgelman, 13 May 2026. CC BY 4.0, via Wikimedia Commons. Source. Bayesian hierarchical model 2026-11-05
A Bayesian hierarchical model is a statistical model used in Bayesian statistics, in which parameters at one level have a prior distribution controlled by parameters at another level. Those shared hyperparameters can themselves receive a hyperprior. For grouped observations , group parameters and shared parameters , one common conditional-independence structure isThe hierarchy specifies how information can be shared; the data are not assumed to become independent merely because they are listed in different groups.[ref]
Stan User's Guide by Stan Development Team. Regression Models, Hierarchical regression and Hierarchical priors
A normal distribution example makes partial pooling explicit. Let and . Conditional on known , completing the square gives the posterior meanFor , , , and , this is4, halfway between the group mean and the shared mean. More precise group data increase . In a full hierarchy with uncertain hyperparameters, their posterior distribution must also be integrated over; simply fixing fitted values omits that uncertainty.
A measurement application appears in Blaza Toman's2017 calibration study. Shared uncertain calibration inputs induce correlations among results; the Bayesian hierarchical model represents this structure within the model rather than treating all replicates as independent.[ref]
Rigorous evaluation of chemical measurement uncertainty: Liquid chromatographic analysis methods using detector response factor calibration by Blaza Toman and others. Introduction and §3.2: Bayesian observation model and shared calibration inputs
Bayesian statistics Created 2026-09-24 Updated 2026-10-14
Bayesian statistics expresses uncertainty about an unknown statistical parameter through a probability distribution, then uses Bayes' theorem to update it after observing data. The prior distribution describes uncertainty before the current observations; the likelihood function describes how the statistical model generates those observations at each parameter value; the posterior distribution describes uncertainty conditional on the observations and that model. A physical parameter can have one fixed value while its value remains uncertain to us. Assigning it a probability distribution represents that uncertainty under the chosen model, rather than requiring the physical parameter to change randomly between measurements.
For example, suppose ten Bernoulli trials are independent conditional on an unknown heads probability , with a beta distribution prior . Eight heads and two tails give the posterior distribution by Beta-binomial conjugacy. Its posterior mean is , between the prior mean and observed binomial proportion . The Bayesian posterior below computes the whole update, and the credible interval below summarizes its remaining uncertainty. The conjugate update is explained in MIT 18.05, Reading 15: beta and normal conjugate priors.
The useful feature is that one posterior distribution supports several questions: a posterior mean estimates a value, a credible interval reports a range, and a posterior predictive distribution predicts a future observation while averaging over parameter uncertainty. With conditionally independent new data, today's posterior distribution can become tomorrow's prior distribution. These conclusions remain conditional on the statistical model and prior distribution; a precise update does not establish that either assumption fits the experiment.
A historical starting point is Thomas Bayes's essay in the 1763 volume of the Royal Society's Philosophical Transactions, communicated after his death by Richard Price. Its opening problem asks for uncertainty about an unknown event probability given observed successes and failures: the same direction of reasoning illustrated by the coin example. See Bayes and Price, An Essay towards solving a Problem in the Doctrine of Chances, opening letter and problem.
Blaza Toman 2026-11-05
Blaza Toman is a statistician whose work connects Bayesian statistics, design of experiments and measurement uncertainty in metrology. Her institutional biography records a statistics doctorate in1987 and joining the National Institute of Standards and Technology in2000. Her research includes uncertainty assessment and statistical analysis of comparisons between laboratories.[ref]
Her2017 first-authored paper with colleagues examined uncertainty evaluation in chromatographic measurement calibration. The study compared calculation through measurement equations, including correlations, with a Bayesian hierarchical model. A central point is that several measurements can share uncertain inputs: treating them as independent can underestimate the uncertainty of a combined result.[ref]
An invented calibration example makes this concrete. Let two detector signals be100 and110 units, with the same estimated response signal units per milligram. The inferred amounts and are10 and11 milligrams. If the true is1% larger, both inferred amounts must decrease together, while their ratio remains1.1. Repeating signal readings can reduce independent reading noise, but it does not by itself eliminate this shared uncertainty in . This illustrates why the structure of an experiment matters to its statistical model.[ref]
Rigorous evaluation of chemical measurement uncertainty: Liquid chromatographic analysis methods using detector response factor calibration by Blaza Toman and others. Introduction: shared response-factor correlations; numerical example independently composed
Credible interval Created 2026-09-28 Updated 2026-10-14
A credible interval is an interval containing a prescribed amount of posterior probability for an unknown scalar statistical parameter . For a continuous posterior distribution with posterior density , its endpoints satisfyThe conditioning includes the chosen statistical model and prior distribution. For a discrete posterior distribution, exact equality may be impossible because of its probability masses; an interval can instead be required to contain at least the requested posterior probability. An interval compresses the full posterior distribution into a range whose uncertainty can be communicated in the parameter's own units. See MIT 18.05, Class 16: probability intervals.
For the eight-head, two-tail example in Bayesian statistics, the posterior density is on . Its cumulative distribution function, obtained by integration of this polynomial, isSolving and by the bisection method givesThese are numerical approximations to the exact quantiles defined by those equations; the endpoints were computed from the cumulative distribution function, rather than read off a plot. The resulting equal-tailed credible interval leaves 2.5% posterior probability on each side. Its shaded area is 95% of the total area under the posterior density.
Credible intervals are not unique. The one-sided credible interval also has 95% posterior probability, but leaves all 5% outside it on the right. A highest density region instead selects points above a density threshold; it need not be an equal-tailed credible interval, and when the posterior density has separated peaks it need not be one interval at all. Thus a reported credible interval should specify its construction.
A 95% credible interval makes a statement about the statistical parameter conditional on these observed data and the Bayesian model. A 95% confidence interval instead refers to the coverage probability of a procedure under repeated sampling at a fixed parameter value. These are different conditioning statements: 95% posterior probability does not by itself imply 95% coverage probability for every fixed parameter. The confidence interval article develops that sampling interpretation.
Donald Rubin Created 2026-10-25 Updated 2026-11-05
Donald Rubin's work connects Causal inference, missing data and Bayesian statistics. His Harvard profile lists Causal inference in experiments and observational studies, nonresponse in sample surveys, and Bayesian and empirical Bayesian methods as research interests.[ref]
The potential outcomes framework makes a causal comparison explicit by distinguishing the outcomes that would occur under alternative treatments. Only the outcome under the received treatment is observed for each individual, so identifying an average treatment effect requires design or modelling assumptions. In missing-data analysis, multiple imputation propagates uncertainty by analyzing several completed datasets and pooling their results with Rubin's rules. These ideas explain why filling in one convenient value and then treating it as observed generally understates uncertainty.
Portrait of Donald B. Rubin
. Photograph of Donald B. Rubin linked from the Harvard Department of Statistics profile and labelled Don Rubin. Hal S. Stern Created 2026-10-25 Updated 2026-11-05
Hal S. Stern is a statistician whose research includes Bayesian statistics and the analysis of forensic evidence. He is a coauthor of Bayesian Data Analysis by Andrew Gelman and others and of the article with Andrew Gelman explaining why a difference between statistical significance and nonsignificance need not itself be statistically significant. This distinction separates the comparison of two estimated effects from two separate hypothesis tests.[ref]
Portrait of Hal S. Stern
. Photograph linked by the author’s University of California, Irvine homepage; photographer and licence are not asserted. Source. Joseph Born Kadane Created 2026-10-25 Updated 2026-11-05
Joseph Born Kadane is a statistician whose work connects Bayesian statistics, decision theory and applications of probability to practical evidence. In his own research statement, he describes work on prior elicitation: constructing probability distributions from an investigator's background knowledge, as well as on the foundations and computation of Bayesian inference.[ref]
https://www.stat.cmu.edu/GSS/kadane.html. Carnegie Mellon, Joseph B. Kadane research statement, theoretical interests
His institutional biography records that he joined Carnegie Mellon in 1971 and headed its statistics department from 1972 to 1981.[ref]
https://www.cmu.edu/dietrich/statistics-datascience/people/emeritus/joseph-kadane.html. Carnegie Mellon departmental biography, Bio
In computing, his name is also attached to Kadane's algorithm for the maximum subarray problem: the best segment ending at a new position either extends the preceding best-ending segment or starts at that position. This gives a linear-time dynamic programming solution.Portrait of Joseph Born Kadane
. Photograph from Carnegie Mellon University's official researcher profile. Source. Maximum likelihood estimation Created 2026-09-24 Updated 2026-10-14
Maximum likelihood estimation is a method of statistical estimation: within a specified statistical model, choose the statistical parameter values that maximize the likelihood function of the observed data. For a parameter set and observations , its exact requirement isThe equality requires an attained, finite maximum; a supremum approached only at an excluded boundary is not enough. The resulting rule is a maximum-likelihood estimator. The likelihood function uses a probability mass function for discrete data and a probability density function for continuous data. See MIT 18.05, Reading 10b, sections 3 and 3.2.
The direction of the comparison is the interesting part: hold the observations fixed and vary the statistical parameter. Ten independent Bernoulli trials with eight successes and two failures give the maximum-likelihood estimate , as derived in log-likelihood. This chooses the member of the statistical model that assigns the greatest mass to that outcome. It does not assert an posterior probability that this parameter value is true. Bayesian statistics combines the same likelihood function with a prior distribution to obtain a posterior distribution; maximum a posteriori estimation maximizes that posterior mass or density instead.
The method turns many fitting tasks into one maximization problem. In the normal distribution model with known variance, it recovers the sample mean and ordinary least squares, while binomial regression and Poisson regression use different sampling assumptions to build their own likelihood functions. The log-likelihood turns independent contributions into a sum, exposing score equations and observed information. A peak's location gives an estimate; its shape records how much the observed data distinguish nearby parameter values.
Existence, uniqueness, bias, and statistical consistency are separate questions. Normal mean and variance maximum-likelihood estimators include a variance estimate with bias, likelihood supremum at an excluded boundary gives nonexistence, and the Neyman-Scott incidental parameter problem gives inconsistency. The usual asymptotic normality of a maximum likelihood estimator requires assumptions: a consistent estimator at an interior true parameter in a fixed finite-dimensional model with identifiability, sufficient smoothness and control of log-likelihood derivatives, and finite nonsingular Fisher information. A common parameter-independent support of a probability distribution is part of a standard sufficient framework; see Rigollet, MIT 18.650, Maximum Likelihood Estimation, slides 22-23. This is a description of the regular setting, not a complete theorem's hypotheses. The exact endpoint limit for a shifted exponential distribution shows why changing support can produce a different rate and a nonnormal limit. These properties do not follow just from maximizing a function.
In his 1922 paper in the Royal Society's Philosophical Transactions A, R. A. Fisher explicitly distinguished likelihood from probability and described choosing the parameter values with greatest likelihood. Section 6 also discusses comparing likelihoods after giving the maximum value one, the convention used in the figures here. See Fisher, On the Mathematical Foundations of Theoretical Statistics, section 6, pp. 326-328, DOI 10.1098/rsta.1922.0009.
Prior probability Created 2026-09-24 Updated 2026-10-14
Prior probability describes uncertainty before the current observations are incorporated. For a statistical parameter , a prior distribution assigns probabilities to its possible ranges, conditional on background information and a statistical model. A continuous prior density specifies these probabilities through integration:Here the probability density function is relative to Lebesgue measure ; a discrete prior distribution instead uses a probability mass function and sums. Density at one point is not the probability of that point. A nonnegative kernel with infinite total mass is an improper prior, whose use requires a separate check of posterior propriety.
For the coin model in Bayesian statistics, the beta distribution has prior density on . Its mean is and its variance is . It favors moderate heads probabilities without ruling out values near zero or one. For example,The prior curve in Bayesian posterior makes this preference visible; moment matching for a beta prior explains how to choose a beta distribution from a desired mean and variance.
A prior distribution lets earlier evidence or elicited knowledge contribute to statistical inference when the current sample size is limited. It also exposes assumptions that can be checked by prior elicitation and a prior predictive check. Before the same eight heads and two tails, a uniform prior would give posterior mean , compared with under : the observations do not uniquely determine a Bayesian posterior. Even a uniform prior makes a choice of parameter coordinates; its child article explains why changing coordinates can destroy uniformity.
Robert Kass Created 2026-10-25 Updated 2026-11-05
Robert Kass connects Bayesian statistics with statistical methods for neural data. His research includes Bayes factors, prior distributions, asymptotic inference and the analysis of spike trains. His institutional research statement describes using point-process models to analyze the timing of neuronal activity and relationships between brain regions.[ref]
https://www.stat.cmu.edu/~kass/about.html. Author Bio Sketch, Bayesian inference and neural-data analysis
A spike train is naturally represented by a point process: the data include event times rather than only a continuous response or total count. A statistical model can then express how firing intensity changes with an experimental condition or recent activity. This makes the choice of model part of the scientific question about neural communication, while uncertainty calculations distinguish a fitted pattern from a reproducible relationship.
Homepage: www.stat.cmu.edu/~kass/
Robert E. Kass
. Statistical parameter Created 2026-10-05 Updated 2026-10-07
A statistical parameter indexes a family of probability distributions in a statistical model. It is fixed in a frequentist sampling model; a prior distribution makes it random for Bayesian statistics. Different statistical parameter values should produce different observable distributions when identifiability is claimed.






