Prior distributions for variance parameters in hierarchical models (comment on article by Browne and Draper)
Open accessThe DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index; 1 of the 23 sources its claims cite were checked for support.
Abstract
Various noninformative prior distributions have been suggested for scale parameters in hierarchical models. We construct a new folded-noncentral-$t$ family of conditionally conjugate priors for hierarchical standard deviation parameters, and then consider noninformative and weakly informative priors in this family. We use an example to illustrate serious problems with the inverse-gamma family of "noninformative" prior distributions. We suggest instead to use a uniform prior on the hierarchical standard deviation, using the half-$t$ family when the number of groups is small and in other settings where a weakly informative prior is desired. We also illustrate the use of the half-$t$ family for hierarchical modeling of multiple variance parameters such as arise in the analysis of variance.
Overview
CoChat Summary
TL;DR
Gelman argues that inverse-gamma “noninformative” priors for hierarchical variance parameters can badly distort posterior inference, especially when the group-level variance is near zero or the number of groups is small. He recommends a uniform prior on the hierarchical standard deviation when groups are not few, and half-t/half-Cauchy weakly informative priors otherwise, developed within a folded-noncentral-t conditionally conjugate family.
Key findings
- The inverse-gamma(ε, ε) family is not reliably noninformative: as ε → 0 it yields an improper posterior, and in the 8-schools example inverse-gamma(1, 1) and inverse-gamma(0.001, 0.001) priors on σ²_α constrained posterior inferences and increased shrinkage relative to a uniform prior on σ_α.
- A uniform prior on σ_α performed well for the 8-schools data (J = 8), but with only J = 3 schools it produced an extremely long right tail and undershrinkage; a half-Cauchy prior with scale A = 25 removed much of that unrealistic upper tail.
- For multiple variance components, Gelman recommends a hierarchical half-Cauchy model with scale estimated from data; in the 5 × 5 × 2 split-plot latin square Anova with nine variance components, the Cauchy scale parameter A was estimated at 1.8 with a 95% posterior interval of [0.5, 5.1].
- The folded-noncentral-t family, obtained via a redundant multiplicative parameterization, provides conditionally conjugate priors for σ_α and includes the improper uniform density (ν = −1) and proper half-Cauchy (ν = 1) as special cases.
Methods
- Conceptual/comment paper using a simple two-level normal hierarchical model: y_ij ∼ N(μ + α_j, σ²_y), α_j ∼ N(0, σ²_α), focusing on the prior for σ_α.
- Illustrates with the 8-schools example (J = 8, 6000 Bugs simulation draws), a 3-schools subset, and a 5 × 5 × 2 split-plot latin square Anova with nine variance components.
- Uses a parameter-expanded form y_ij ∼ N(μ + ξη_j, σ²_y), η_j ∼ N(0, σ²_η), with σ_α = |ξ|σ_η, to construct and compare uniform, inverse-gamma, half-Cauchy, and hierarchical half-Cauchy priors.
Limitations
- The paper states that noninformative and weakly informative priors are inherently provisional: after fitting, one should inspect the posterior and revise the prior if it does not make sense.
- The paper notes that the uniform prior on σ_α has a positive miscalibration and yields an improper posterior for J = 1 or 2; inverse-gamma inferences are sensitive to ε; and half-Cauchy scale choices are weakly informative rather than fully objective.
- Evident from the text: the recommendations rest on illustrative examples and conceptual argument rather than a broad simulation study or systematic empirical comparison, and extensions to nonlinear, multivariate, and more complex hierarchical models are left for further work.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 1 Not valid · 14 Not checked · 56 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Similarly, there are no always-nonnegative classical unbiased estimators of σ α or σ 2 α in the hierarchical model.”
- Also stated in: § 7.1 Prior distributions for variance parameters · plain
“Similarly, there are no alwaysnonnegative classical unbiased estimators of σ α or σ 2 α in the hierarchical model.”
§ Prior distributions for variance parameters in hierarchical models(Comment on Article by Browne and Draper) > 2.4 Calibration
What the sources say
- Could not verifycites Bickel and Blackwell (1967) matched to “A Note on Bayes Estimates” (1967) sourceExperimental — accuracy not yet measured
The introduction (p. 1) and Theorem 1.3 (p. 3) concern when an unbiased Bayes estimate must have zero Bayes risk. Searches for hierarchical models, σₐ, σ²ₐ, and always-nonnegative classical unbiased estimators found no passage addressing the claimed nonexistence result. (LLM, conf=0.77)
- Not checked — no full text of the sourcecites Meng and Zaslavsky (2002) matched to “Single observation unbiased priors” (2002) source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 7.1 Prior distributions for variance parameters · plain
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“If J is low, the uniform prior density tends to lead to high estimates of σ α , as discussed in Section 5.2.”
§ Prior distributions for variance parameters in hierarchical models(Comment on Article by Browne and Draper) > 7.1 Prior distributions for variance parameters
hedgedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In contrast, the hierarchical half-Cauchy model performs a great deal of shrinkage, especially of the high ranges of the intervals.”
- Also stated in: § Bugs model: a half-Cauchy prior distribution on sigma.theta is induced # using a normal prior on xi and an inverse-gamma on tau.eta model { for (j in 1:J){ # J = the number of schools y[j] ~dnorm (theta[j], tau.y[j]) # data model: the likelihood theta[j] <-mu.theta+ xi*eta[j] tau.y[j] <-pow(sigma.y[j],-2) } xi ~dnorm (0, tau.xi) tau.xi <-pow(prior.scale,-2) for (j in 1:J){ eta[j] ~dnorm (0, tau.eta) # hierarchical model for theta } tau.eta ~dgamma (.5, .5)# chi^2 with 1 d.f.sigma.theta<-abs(xi)/sqrt(tau.eta)# cauchy = normal/sqrt(chi^2) mu.theta ~dnorm (0.0, 1.0E-6) # noninformative prior on mu } · plain
“The half-Cauchy model gives much sharper inferences, using the partial pooling that comes with fitting a hierarchical model.”
§ Prior distributions for variance parameters in hierarchical models(Comment on Article by Browne and Draper) > 6.2 Superpopulation and finite-population standard deviations
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Bugs model: a half-Cauchy prior distribution on sigma.theta is induced # using a normal prior on xi and an inverse-gamma on tau.eta model { for (j in 1:J){ # J = the number of schools y[j] ~dnorm (theta[j], tau.y[j]) # data model: the likelihood theta[j] <-mu.theta+ xi*eta[j] tau.y[j] <-pow(sigma.y[j],-2) } xi ~dnorm (0, tau.xi) tau.xi <-pow(prior.scale,-2) for (j in 1:J){ eta[j] ~dnorm (0, tau.eta) # hierarchical model for theta } tau.eta ~dgamma (.5, .5)# chi^2 with 1 d.f.sigma.theta<-abs(xi)/sqrt(tau.eta)# cauchy = normal/sqrt(chi^2) mu.theta ~dnorm (0.0, 1.0E-6) # noninformative prior on mu } · plain
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This prior distribution is even more sharply peaked near zero and further distorts posterior inferences, with the problem arising because the marginal likelihood for σ α remains high near zero.”
§ Prior distributions for variance parameters in hierarchical models(Comment on Article by Browne and Draper) > 5.1 Noninformative prior distributions for the 8-schools problem
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The uniform prior distribution seems fine for the 8-school analysis”
- Also stated in: § 5.2 Weakly informative prior distribution for the 3-schools problem · plain
“the default uniform prior gave reasonable results”
- Also stated in: § 7.1 Prior distributions for variance parameters · hedged
“Figure 1 illustrates the generally robust properties of the uniform prior density on σ α .”
§ Prior distributions for variance parameters in hierarchical models(Comment on Article by Browne and Draper) > 5.2 Weakly informative prior distribution for the 3-schools problem
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 5.2 Weakly informative prior distribution for the 3-schools problem · plain
26 more claims
Create a free account to see all 71 claims and every source verdict.
- It may state two separate claims as one. 34
- Probably not a substantial claim. 12
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Because the uniform distribution tends to unduly favor presence of heterogeneity in discrimination and calibration estimates across studies,58,59”
From A framework for meta-analysis of prediction model studies with binary and time-to-event outcomes (2019) · cites this paper as [59]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Prior distributions for variance parameters in hierarchical models(Comment on Article by Browne and Draper) > 7.1 Prior distributions for variance parameters
“we see conditional conjugacy in the wider class of half-t distributions on σ α , which include the uniform and half-Cauchy densities on σ α (as well as inverse-gamma on σ 2 α ) as special cases.”
§ Prior distributions for variance parameters in hierarchical models(Comment on Article by Browne and Draper) > 3.2 Folded-noncentral-t prior distribution for σ α
“In the limit that the denominator is specified exactly, we have a folded normal distribution; conversely, specifying the numerator exactly yields the square-root-inverse-χ 2 distribution for σ α , as in Section 3.1.”
Citations
Cites
Gelman, A., Carlin, J. B., Stern, H. S., & Rubin, D. B. (2003) · doi:10.1201/9780429258480 · Cited by 27,276
Self-citationKass, R. E., & Raftery, A. E. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476572 · Cited by 12,558
Sampling-based approaches to calculating marginal densities
Gelfand, A. E., & Smith, A. F. M. (1990) · Journal of the American Statistical Association · doi:10.1080/01621459.1990.10476213 · Cited by 6,606 · cited 1×
“Typically, enough data will be available to estimate µ and σy that one can use any reasonable noninformative prior distribution—for example, p(µ, σy) ∝ 1 or p(µ, log σy) ∝ 1.”
Introducing Multilevel Modeling
Kreft, I., & de Leeuw, J. (1998) · doi:10.4135/9781849209366 · Cited by 2,997
POSTERIOR PREDICTIVE ASSESSMENT OF MODEL FITNESS VIA REALIZED DISCREPANCIES
Gelman, A., Meng, X., & Stern, H. S. (1996) · Cited by 2,638
Self-citationBayes and Empirical Bayes Methods for Data Analysis
(2001) · Technometrics · doi:10.1198/tech.2001.s608 · Cited by 2,098
INADMISSIBILITY OF THE USUAL ESTIMATOR FOR THE MEAN OF A MULTIVARIATE NORMAL DISTRIBUTION
Stein, C. (1956) · Contribution to the Theory of Statistics · doi:10.1525/9780520313880-018 · Cited by 1,841
Bayesian Approaches to Clinical Trials and Health‐Care Evaluation
Spiegelhalter, D. J., Abrams, K. R., & Myles, J. P. (2003) · Wiley eBooks · doi:10.1002/0470092602 · Cited by 1,673
Parametric empirical Bayes inference: theory and applications
Morris, C. N. (1983) · Journal of the American Statistical Association · doi:10.1080/01621459.1983.10477920 · Cited by 1,448 · cited 1×
“On the theoretical side, hierarchical models allow a more “objective” approach to inference by estimating the parameters of prior distributions from data rather than requiring them to be specified using subjective information (see James and Stein, 1960, Efron and Morris, 1975, and Morris, 1983).”
The Selection of Prior Distributions by Formal Rules
Kass, R. E., & Wasserman, L. (1996) · Journal of the American Statistical Association · doi:10.1080/01621459.1996.10477003 · Cited by 1,308
Research works printed but not linked: 5
- Box, G. E. P. and Tiao, G. C. (1973). Bayesian Inference in Statistical Analysis. Reading, Mass.: Addison-Wesley.
- James, W. and Stein, C. (1960). "Estimation with quadratic loss." In Neyman, J. (ed.), Proceedings of the Fourth Berkeley Symposium, volume 1, 361–380. Berkeley: University of California Press.
- Johnson, N. L. and Kotz, S. (1972). Distributions in Statistics. New York: Wiley. 4 vols.
- Liu, C. (2001). "Bayesian analysis of multivariate probit models. Discussion of “The art of data augmentation” by D. A. van Dyk and X. L. Meng." Journal of Computational and Graphical Statistics, 10: 75–81.
- Raudenbush, S. W. and Bryk, A. S. (2002). Hierarchical Linear Models. Thousand Oaks, Calif.: Sage., second edition.
Cited by
Items 3,801–3,900 of 4,089
Ling, X.-X., Gabrio, A., & Baio, G. (2025) · PharmacoEconomics · doi:10.1007/s40273-025-01511-1
“For example, Gelman recommended the half-t family of prior distributions on the original-scale standard deviation [16], but the article primarily focused on hierarchical Normal models, which may not always align with CEA data.”
Fast Variational Inference of Latent Space Models for Dynamic Networks Using Bayesian P-Splines
Loyal, J. D. (2025) · Bayesian Analysis · doi:10.1214/25-ba1545
Plausible Values and Multilevel Models in Large-Scale Assessments
Jehangir, K., & Fox, J. (2025) · Journal of Educational and Behavioral Statistics · doi:10.3102/10769986251348679
“The recovered level-2 variances with the SLCM PVs were (most likely) mainly driven by the inverse-gamma prior, which is known to lead to a PVs in Multilevel models small overestimation of the true variance when the true variance is (close to) zero (Gelman, 2006).”
Hierarchical Bayesian Modelling on Predicting East Java Province Population
Chee, D. K. W., Iriawan, N., & Widhianingsih, T. D. A. (2024) · doi:10.1109/incitest64888.2024.11121518
Ahmadi, H., Titze, N., Wild, K. J., & Rodehutscord, M. (2025) · Scientific Reports · doi:10.1038/s41598-025-15101-w
The Effect of Space, Time and Night-Time Light Intensity on Antenatal Care Coverage in Bangladesh
Baffour, B., Das, S., Talukder, A., & Richardson, A. (2025) · Spatial Demography · doi:10.1007/s40980-025-00144-4 · Cited by 1
Determinants of Health Literacy and their Impact on Residents in Newham, LondonPreprint
Green, N., & Hawkings, Y.-R. (2025) · medRxiv · doi:10.1101/2025.08.26.25334435
“MRP is a statistical technique that combines multilevel modelling with post-stratification to estimate sub-national characteristics from survey data Park et al (2004, 2006).”
Ozkan, F. (2025) · Research Square · doi:10.21203/rs.3.rs-7474211/v1
Optimal Bayesian regression with a non-informative prior: Order-recursive and incremental learning
Reihanian, S., Zollanvari, A., & Fazli, S. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131476
Lee, J., & Choi, J. (2025) · Journal of Applied Statistics · doi:10.1080/02664763.2025.2555593
“For parameter estimation, we assumed non-informative priors of the coefficients: In addition, the prior distributions for all the standard deviations were assumed to follow a uniform distribution, Uniform (0, 10), as suggested by Gelman [14].”
Assessing end-of-season performance as a function of average minutes played for NBA players
Jewell, M., Page, G. L., & Reese, C. S. (2025) · Journal of Quantitative Analysis in Sports · doi:10.1515/jqas-2023-0038
Advances in Fault-Slip Inversion Using Bayesian Inference
Tomita, F. (2025) · Zisin (Journal of the Seismological Society of Japan 2nd ser ) · doi:10.4294/zisin.2024-23
Pascual, C. B., & Jain, S. (2025) · Statistics in Biopharmaceutical Research · doi:10.1080/19466315.2025.2565157
“This prior choice for σ was adapted from a recommendation of Gelman (2006) for variance parameters in hierarchical models.”
Spatial Knockoff Bayesian Variable Selection in Genome-Wide Association Studies
Ee, J. J. V., Gamba, D., Lasky, J. R., Vahsen, M. L., & Hooten, M. B. (2025) · Bayesian Analysis · doi:10.1214/25-ba1556 · Cited by 1
“The prior is also heavy tailed, an attractive property for minimally informative variance parameters in hierarchical models (Gelman, 2006), with density proportional to f ( h ) = 1 (1+ h ) 2 .”
Anokye, F., Li, M., Walker, S., & Hurford, A. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1013562 · Cited by 1
Aniyan, A. S., George, D., & Abraham, L. (2025) · International Journal of Reliability Quality and Safety Engineering · doi:10.1142/s021853932550041x
Moffat, R., & Cross, E. S. (2025) · Imaging Neuroscience · doi:10.1162/imag.a.962
“In doing so, we drew on existing knowledge regarding the possible outcomes in a way that allows for plausible large effects and for the data to dominate the structure of the posterior distribution ( Gelman, 2006; Lemoine, 2019).”
Korobilis, D., Mamatzakis, E. C. M., & Pappas, V. (2025) · Journal of Econometrics · doi:10.1016/j.jeconom.2025.106109
“The resulting prior achieves the ‘‘weakly informative’’ behavior advocated by Gelman (2006), providing regularization benefits while remaining sufficiently flexible to let the data dominate when the likelihood is informative.”
InfluentialZhang, Z., Jian, S.-M., Zang, J.-B., & Zhao, X. (2025) · Case Studies in Construction Materials · doi:10.1016/j.cscm.2025.e05443
Mandal, A., Linero, A. R., Bandyopadhyay, D., et al. (2025) · Journal of nonparametric statistics · doi:10.1080/10485252.2025.2574708
“In alignment with the Gaussian error model (Linero 2022), we employ a half-Cauchy prior for γ denoted as γ ∼ Cauchy + ( 0, γ 0 ) to provide a weakly informative and heavy-tailed regularisation allowing large values of γ when supported by the data, while avoiding the over-concentration near zero typical of Inverse-Gamm…”
InfluentialEstimation of Daily Smoking Prevalence for Disaggregated Statistical Areas in Australia
Das, S., Baffour, B., Richardson, A., Cramb, S. M., & Haslett, S. J. (2025) · Australian & New Zealand Journal of Statistics · doi:10.1111/anzs.70025
“In the model development, the fixed-effects parameters are assumed to follow a weakly informative prior distribution, 𝑝 ( 𝜷 ) = N ( 0 , 100 𝐼 ) , while the half-Cauchy priors are used for the standard deviation parameters following Gelman (2006).”
Badawy, M. H., Nannapaneni, S., Poursina, D., et al. (2025) · Journal of Environmental Science and Health Part B · doi:10.1080/03601234.2025.2577024
“The distributions of the priors are set up as weakly informative to avoid any extra assumption imposition on the model [17] as follows: β 0 0 100 ,”
Bentley, M., Tapley, A., Davey, A., Moad, D., Turner, A., Ralston, A., Tait, J., Mundy, B., van Driel, M., Holliday, E. G., et al. (2025) · Education for Primary Care · doi:10.1080/14739879.2025.2559845
“Non-informative, or weakly informative prior distributions were used: an improper flat prior over the real numbers for fixed effects, and a half stu-dent-t prior with 3 degrees of freedom and scale parameter of 2.5 for random effect variances, as previously recommended [22].”
InfluentialUnmasking and rethinking hierarchical inefficiency in healthcare systems
Unuia, T. J., Andrews, A., & Kimpton, S. (2025) · Social Science & Medicine · doi:10.1016/j.socscimed.2025.118738 · Cited by 2
Acute stress reduces risk-aversion by changing magnitude perceptionPreprint
Renkert, M., de Hollander, G., Aydogan, G., Bedi, S., Forbes, P., Lamm, C., & Ruff, C. C. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.11.03.685504 · Cited by 2
López, R. F., Cristián Mardones, P., Sosa-Gómez, G., & Navarrete, J. P. (2025) · Annals of Operations Research · doi:10.1007/s10479-025-06911-2
Avcı, E. (2025) · Journal of Biopharmaceutical Statistics · doi:10.1080/10543406.2025.2575941
“…sample sizes (Prevost et al. 2000; Dias et al. 2013), while others have focused on general considerations for variance parameters (Spiegelhalter et al. 2004; Gelman 2006; Neuenschwander and Schmidli 2020) or systematically reviewed commonly used cases in the literature (Debray et al. 2015).”
Measuring the crust-superfluid coupling time-scale for 105 UTMOST pulsars with a Kalman filter
Dong, W., Melatos, A., O’Neill, N. J., Meyers, P. M., & Boek, D. K. (2025) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staf2053 · Cited by 4
Modeling Psychophysical Data in R: A Comparative Study of Four Model FrameworksPreprint
Balestrucci, P., Mezzetti, M., Scaleia, B. L., & Moscatelli, A. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.11.17.688833
“…parameters while accounting for their associated uncertainties, incorporated in the second level of the model: In line with the recommendations of Gelman (2006); Gelman et al. (2008), who advocate the use of this prior to mitigate overfitting and underfitting, a Cauchy distribution with…”
Detecting Transition Points in the Slope-Intercept Relation in Linear Latent Growth Models
Lee, D., & Hancock, G. R. (2025) · Multivariate Behavioral Research · doi:10.1080/00273171.2025.2583158
Demystifying Posterior Distributions: A Tutorial on Their Derivation
Du, H., Liu, F., Zhang, Z., et al. (2025) · Multivariate Behavioral Research · doi:10.1080/00273171.2025.2570250
“Here, we illustrate one such prior for r 2 : In hierarchical models with a small number of groups, Gelman (2006) suggested that a half-Cauchy prior might be more effective and inverse gamma prior, as it avoids distorting inferences in regions of high likelihood: r � half − Cauchy ð c Þ : This prior…”
Makalic, E., & Schmidt, D. F. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4972-6_2
Chen, I., Wu, Z., Harlow, S. D., Karvonen-Gutierrez, C. A., Hood, M. M., & Elliott, M. R. (2025) · Journal of Applied Statistics · doi:10.1080/02664763.2025.2589991 · Cited by 1
“In general, since estimating individual variances will be more computationally intensive, we recommend setting P S ≤ P ; that is, allowing more flexibility in the mean regression function, unless there is reason to believe that a more flexible variance trend is justified.”
JSTMapp: A web-based joint spatiotemporal modelling and mapping application for epidemiologists
Ngwira, A., Manda, S., Karimuribo, E. D., et al. (2025) · PLoS ONE · doi:10.1371/journal.pone.0332607
“While the uniform is considered to be less informative than the log-Gamma, the half-Cauchy is robust to changes in the hyperparameters compared to the log-Gamma [14,17,18].”
Chen, M., Guo, L.-Q., Fang, W., et al. (2025) · Materials and Structures · doi:10.1617/s11527-025-02889-2
“An identity bijection for the distribution-form M 1 is chosen as (20)”
Jansson, A. K., Schumacher, T. L., Oldmeadow, C. J., Grotowski, M., Cone, L., Guppy, M., Herbert, J., Attia, J. R., Brown, L., May, J., et al. (2025) · Diabetes Obesity and Metabolism · doi:10.1111/dom.70339 · Cited by 1
“Random intercepts were included for Gelman 20 and reflecting the expectation that between-site variability would be greater than within-individual variability.”
Augmented binary method for basket trials (ABBA)
Cherlin, S., & Wason, J. M. S. (2025) · Statistical Methods in Medical Research · doi:10.1177/09622802251403365
Benitez, B., Frankforter, T. L., Nich, C., Paris, M., & Kiluk, B. D. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02197-7
“Shrinkagepriors were speci fi ed for the variances of the random effects ( half-t (0, 10, 3)) to mitigate the in fl ation of false positives that can occur due to testing several hypotheses ( “ multiplicity ” ) 71,72 .”
Ferrari, L., & Ventrucci, M. (2025) · Scandinavian Journal of Statistics · doi:10.1111/sjos.70042 · Cited by 2
“The conjugate Inverse Gamma priors have been found to lead to overfitting (Gelman, 2006; Lunn et al., 2009; Simpson et al., 2017) and are now being replaced as the default choice by Penalized Complexity (PC) priors (Simpson et al., 2017) in the R package INLA (Rue et al., 2009), which provides fast…”
Falahati, G., Biglarian, A., Behboudi‐Gandevani, S., & Yarandi, R. B. (2025) · Health Science Reports · doi:10.1002/hsr2.71626
“…prior for binomial data and improper prior distribution uniform (0,10) instead of inverse ‐ gamma for heterogeneity to avoid improper estimation of the posterior distribution [91 – 93], however, the effect of prior distribution can be diluted when the sample size of the data is sufficiently large.”
Kroglund, I. B., Østnes, J. E., Patten, M. A., Ciesielski, T. M., & Jaspers, V. L. B. (2025) · Environmental Research · doi:10.1016/j.envres.2025.123548
Enhancing interpretability for Bayesian basket trial designs by effective sample size
Chen, X., Zhang, J., Yang, W., et al. (2025) · BMC Medical Research Methodology · doi:10.1186/s12874-025-02715-x
“To the best of our knowledge, existing methods for quantifying the degree of borrowing in basket trials lack sufficient intuitiveness, e.g., posterior estimate of the between-group variance [25, 26].”
Joint mixed-effects models for causal inference in clustered network-based observational studies
McNealis, V., Moodie, E. E. M., & Dean, N. (2025) · Statistical Methods in Medical Research · doi:10.1177/09622802251403355 · Cited by 4
Assessing spatial disparities: a Bayesian linear regression approach
Wu, K. L., & Banerjee, S. (2024) · Biostatistics · doi:10.1093/biostatistics/kxaf048 · Cited by 8
“Non-informative priors, such as uniform distributions on [ 0 , 1 , induce extreme posterior overfitting in overly parameterized models (Gelman, 2006; Simpson et al., 2017).”
Differentiation of Matrix Expressions
Wakefield, J. (2012) · Springer series in statistics · doi:10.1007/978-1-4419-0925-1_13
Other One-Parameter Models and Their Conjugate Priors
Cowles, M. K. (2012) · Springer texts in statistics · doi:10.1007/978-1-4614-5696-4_6
Approximations to Continuous Dynamical Processes in Hierarchical Models
Cangelosi, A. R. (2008)
More Realism Please: Introduction to Multiparameter Models
Cowles, M. K. (2012) · Springer texts in statistics · doi:10.1007/978-1-4614-5696-4_7
Lurier, T., Rousset, É., Gasqui, P., Sala, C., Claustre, C., Abrial, D., Dufour, P., CRÉMOUX, R. D., Gache, K., Delignette‐Muller, M. L., et al. (2021) · Figshare · doi:10.6084/m9.figshare.14418156
Perez-Panades, J., Botella-Rocamora, P., & Martinez-Beneito, M. A. (2020) · Figshare · doi:10.6084/m9.figshare.13336102
Qian, J., Wu, Y., Zhu, C., et al. (2024) · Figshare · doi:10.6084/m9.figshare.26683672
Additional file 4 of Costs of multimorbidity: a systematic review and meta-analyses
Tran, P. B., Kazibwe, J., Nikolaidis, G. F., Linnosmaa, I., Rijken, M., & van Olmen, J. (2022) · Figshare · doi:10.6084/m9.figshare.20336987
Additional file 1 of Different routes to liking: how readers arrive at narrative evaluations
Mak, M., Faber, M., & Willems, R. M. (2022) · Figshare · doi:10.6084/m9.figshare.20408619
Maheu‐Giroux, M., Sardinha, L., Stöckl, H., Meyer, S. R., Godin, A., Alexander, M. J., & García-Moreno, C. (2022) · Figshare · doi:10.6084/m9.figshare.19959725
Wu, D., Goldfeld, K. S., & Petkova, E. (2024) · Figshare · doi:10.6084/m9.figshare.26564157
Additional file 1 of Costs of multimorbidity: a systematic review and meta-analyses
Tran, P. B., Kazibwe, J., Nikolaidis, G. F., Linnosmaa, I., Rijken, M., & van Olmen, J. (2022) · Figshare · doi:10.6084/m9.figshare.20336978
Chen, X., Zhang, J., Jiang, L., et al. (2023) · Figshare · doi:10.6084/m9.figshare.22618612
Wu, D., Goldfeld, K. S., & Petkova, E. (2024) · Figshare · doi:10.6084/m9.figshare.26564169
Xu, S. (2012) · Springer eBooks · doi:10.1007/978-0-387-70807-2_3
Ghaffari, S., Bouchonville, K. J., Saleh, E., Schmidt, R. E., Offer, S. M., & Sinha, S. (2024) · Figshare · doi:10.6084/m9.figshare.26608368
Qian, J., Wu, Y., Zhu, C., et al. (2024) · Figshare · doi:10.6084/m9.figshare.26683669
Kim, J., Lawson, A. B., Neelon, B., Korte, J. E., Eberth, J. M., & Chowell, G. (2023) · Figshare · doi:10.6084/m9.figshare.23733118
Wu, D., Goldfeld, K. S., & Petkova, E. (2024) · Figshare · doi:10.6084/m9.figshare.26564178
Ghaffari, S., Bouchonville, K. J., Saleh, E., Schmidt, R. E., Offer, S. M., & Sinha, S. (2024) · Figshare · doi:10.6084/m9.figshare.26608374
Qian, J., Wu, Y., Zhu, C., et al. (2024) · Figshare · doi:10.6084/m9.figshare.25264352
Ghaffari, S., Bouchonville, K. J., Saleh, E., Schmidt, R. E., Offer, S. M., & Sinha, S. (2024) · Figshare · doi:10.6084/m9.figshare.26608359
Wu, D., Goldfeld, K. S., & Petkova, E. (2024) · Figshare · doi:10.6084/m9.figshare.26564163
Ghaffari, S., Bouchonville, K. J., Saleh, E., Schmidt, R. E., Offer, S. M., & Sinha, S. (2024) · Figshare · doi:10.6084/m9.figshare.26608377
Grantham, K. L., Kasza, J., Heritier, S., Carlin, J. B., & Forbes, A. B. (2022) · Figshare · doi:10.6084/m9.figshare.19596266
Kim, J. H., Lawson, A. B., Neelon, B., Korte, J. E., Eberth, J. M., & Chowell, G. (2023) · Figshare · doi:10.6084/m9.figshare.23733112
Wang, Y., Travis, J., & Gajewski, B. (2022) · Figshare · doi:10.6084/m9.figshare.19634732
Bedaso, N. G., & Debusho, L. K. (2022) · Figshare · doi:10.6084/m9.figshare.19418653
Wu, D., Goldfeld, K. S., & Petkova, E. (2024) · Figshare · doi:10.6084/m9.figshare.26564151
Wu, D., Goldfeld, K. S., & Petkova, E. (2024) · Figshare · doi:10.6084/m9.figshare.26564175
Wang, Y., Travis, J., & Gajewski, B. (2022) · Figshare · doi:10.6084/m9.figshare.19634738
Kim, J. H., Lawson, A. B., Neelon, B., Korte, J. E., Eberth, J. M., & Chowell, G. (2023) · Figshare · doi:10.6084/m9.figshare.23733115
Wu, D., Goldfeld, K. S., & Petkova, E. (2024) · Figshare · doi:10.6084/m9.figshare.26564166
Ghaffari, S., Bouchonville, K. J., Saleh, E., Schmidt, R. E., Offer, S. M., & Sinha, S. (2024) · Figshare · doi:10.6084/m9.figshare.26608380
Wu, D., Goldfeld, K. S., & Petkova, E. (2024) · Figshare · doi:10.6084/m9.figshare.26564154
Qian, J., Wu, Y., Zhu, C., et al. (2024) · Figshare · doi:10.6084/m9.figshare.25264436
Additional file 1 of Bayesian historical borrowing with longitudinal large-scale assessments
Kaplan, D. E., Chen, J., Lyu, W., & Yavuz, S. (2024) · Figshare · doi:10.6084/m9.figshare.26562283
Wu, D., Goldfeld, K. S., & Petkova, E. (2024) · Figshare · doi:10.6084/m9.figshare.26564184
Ghaffari, S., Bouchonville, K. J., Saleh, E., Schmidt, R. E., Offer, S. M., & Sinha, S. (2024) · Figshare · doi:10.6084/m9.figshare.26608362
Palmero, F., Hefley, T. J., Lacasa, J., Almeida, L. F., Haro, R., Garcia, F. O., Salvagiotti, F., & Ciampitti, I. A. (2024) · Figshare · doi:10.6084/m9.figshare.26945199
Ghaffari, S., Bouchonville, K. J., Saleh, E., Schmidt, R. E., Offer, S. M., & Sinha, S. (2024) · Figshare · doi:10.6084/m9.figshare.26608371
Ghaffari, S., Bouchonville, K. J., Saleh, E., Schmidt, R. E., Offer, S. M., & Sinha, S. (2024) · Figshare · doi:10.6084/m9.figshare.26608365
Wu, D., Goldfeld, K. S., & Petkova, E. (2024) · Figshare · doi:10.6084/m9.figshare.26564181
Runcie, D. E., Qu, J., Cheng, H., & Crawford, L. (2021) · Figshare · doi:10.6084/m9.figshare.15047698
Additional file 2 of Costs of multimorbidity: a systematic review and meta-analyses
Tran, P. B., Kazibwe, J., Nikolaidis, G. F., Linnosmaa, I., Rijken, M., & van Olmen, J. (2022) · Figshare · doi:10.6084/m9.figshare.20336981
Wu, D., Goldfeld, K. S., & Petkova, E. (2024) · Figshare · doi:10.6084/m9.figshare.26564172
Runcie, D. E., Qu, J., Cheng, H., & Crawford, L. (2021) · Figshare · doi:10.6084/m9.figshare.15047701
Lurier, T., Rousset, É., Gasqui, P., Sala, C., Claustre, C., Abrial, D., Dufour, P., CRÉMOUX, R. D., Gache, K., Delignette‐Muller, M. L., et al. (2021) · Figshare · doi:10.6084/m9.figshare.14418153
Wu, D., Goldfeld, K. S., & Petkova, E. (2024) · Figshare · doi:10.6084/m9.figshare.26564160
Bayesian kernel projections for classification of high dimensional data
WILSON, S. P. (2011) · Arrow@dit (Dublin Institute of Technology)
Bayesian latent variable models for the analysis of experimental psychology dataPreprint
Vandekerckhove, J., & Merkle, E. C. (2018) · OSF Preprints (OSF Preprints)
A compilation of history & theory dissertations by third year students from SAUL I
Keane, S., Panter, N., Walsh, G., et al. (2009) · Arrow@dit (Dublin Institute of Technology) · doi:10.34961/917
Daniells, L., Mozgunov, P., Bedding, A., et al. (2023) · University of Regensburg Publication Server (University of Regensburg) · doi:10.5283/epub.75933
Metadata
- Authors
- Gelman, A.
- Affiliations
- Columbia University (US)
- Corresponding author
- Gelman, Andrew
- ORCID
- Gelman, Andrew
- Venue
- Bayesian Analysis
- Publisher
- Institute of Mathematical Statistics
- Published
- 2006-09-01
- Volume
- 1
- Issue
- 3
- Pages
- 515-534
- ISSN
- 1931-6690 (ISSN-L)
- 1936-0975
- OpenAlex
- W1536497620
- Semantic Scholar
- 63d40805d4635b70f6b5aa07fc2c9821480cfc1e
- Cited by
- 4,050
- References
- 34
- Citations by year
- 2026: 194 · 2025: 218 · 2024: 237 · 2023: 237 · 2022: 282 · 2021: 312 · 2020: 320 · 2019: 281 · 2018: 266 · 2017: 263 · 2016: 235 · 2015: 217 · 2014: 176 · 2013: 142 · 2012: 184
- FWCI
- 78.70
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by
- Locations
- Bayesian Analysis (publishedVersion, cc-by)
- Project Euclid (Cornell University) (submittedVersion)
- Funders
- National Science Foundation
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Distribution Estimation and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Methods and Mixture Models
- Keywords
- prior distributions, hierarchical models, scale parameter, non-informative priors, weakly informative priors, uniform prior, analysis of variance
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-02, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-02 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.