A semiparametric Bayesian model for randomised block designs

Bush, Christopher; MacEachern, Steven N.

doi:10.1093/biomet/83.2.275

Cited by 258 publications

(226 citation statements)

References 10 publications

Supporting

Mentioning

224

Contrasting

Unclassified

Order By: Relevance

“…Here we review two different samplers for doing so. The first corresponds to algorithm "three" in Neal (1998), which itself derives from the work of Bush and MacEachern (1996), West et al (1994), MacEachern and Muller (1998), and Neal (1992). The second is a sequential posterior estimation algorithm that corresponds to the techniques in Fearnhead and Clifford (2003), Fearnhead (2004), Sanborn et al (2006) and is related to Wood and Griffiths (2007).…”

Section: Infinite Gaussian Mixture Modelmentioning

confidence: 99%

A nonparametric Bayesian alternative to spike sorting

Wood

Black

2008

Journal of Neuroscience Methods

View full text Add to dashboard Cite

a b s t r a c tThe analysis of extra-cellular neural recordings typically begins with careful spike sorting and all analysis of the data then rests on the correctness of the resulting spike trains. In many situations this is unproblematic as experimental and spike sorting procedures often focus on well isolated units. There is evidence in the literature, however, that errors in spike sorting can occur even with carefully collected and selected data. Additionally, chronically implanted electrodes and arrays with fixed electrodes cannot be easily adjusted to provide well isolated units. In these situations, multiple units may be recorded and the assignment of waveforms to units may be ambiguous. At the same time, analysis of such data may be both scientifically important and clinically relevant. In this paper we address this issue using a novel probabilistic model that accounts for several important sources of uncertainty and error in spike sorting. In lieu of sorting neural data to produce a single best spike train, we estimate a probabilistic model of spike trains given the observed data. We show how such a distribution over spike sortings can support standard neuroscientific questions while providing a representation of uncertainty in the analysis. As a representative illustration of the approach, we analyzed primary motor cortical tuning with respect to hand movement in data recorded with a chronic multi-electrode array in non-human primates. We found that the probabilistic analysis generally agrees with human sorters but suggests the presence of tuned units not detected by humans.

show abstract

Section: Infinite Gaussian Mixture Modelmentioning

confidence: 99%

A nonparametric Bayesian alternative to spike sorting

Wood

Black

2008

Journal of Neuroscience Methods

View full text Add to dashboard Cite

show abstract

“…The second method is the Polya urn Gibbs sampler of MacEachern (1994), Bush and MacEachern (1996), and MacEachern and Müller (1998). The Gibbs sampler sequentially samples from the full conditional distributions having mass functions of the form p(z i |z −i , y), where z −i is the collection of cluster membership variables with the exception of z i .…”

Section: Partition Estimationmentioning

confidence: 99%

“…Hence, a fixed α is recommended. Arguments and experiments regarding fixed precision are also prevalent in the DP literature (Bush and MacEachern 1996;Daumé III 2007;Dunson and Park 2008).…”

Section: Sensitivity To Dpm Precision αmentioning

confidence: 99%

profdpm: AnRPackage for MAP Estimation in a Class of Conjugate Product Partition Models

Shotwell¹

2013

J. Stat. Soft.

View full text Add to dashboard Cite

The profdpm package facilitates inference at the posterior mode for a class of product partition models. Dirichlet process mixtures are currently the only available class members. Several methods are implemented to search for the maximum posterior estimate of the data partition. This article discusses the relevant theory, the R and underlying C implementation, and examples of high level functionality.

show abstract

“…The posterior distribution of t can be obtained readily from the sampling procedure. Bush and MacEachern (1996) suggest embedding an optional additional step in the Gibbs sampling procedure: let the number of clusters identified at iteration m be t ðmÞ ; this means that there are t ðmÞ distinct values of the p's, which are labeled as h ðmÞ ¼ h 1 ðmÞ ; h 2 ðmÞ ; . .…”

Section: Nonparametric Distribution For Effectsmentioning

confidence: 99%

A Thurstonian Model for Quantitative Genetic Analysis of Ranks: A Bayesian Approach

Gianola

Simianer

2006

Genetics

View full text Add to dashboard Cite

A fully Bayesian method for quantitative genetic analysis of data consisting of ranks of, e.g., genotypes, scored at a series of events or experiments is presented. The model postulates a latent structure, with an underlying variable realized for each genotype or individual involved in the event. The rank observed is assumed to reflect the order of the values of the unobserved variables, i.e., the classical Thurstonian model of psychometrics. Parameters driving the Bayesian hierarchical model include effects of covariates, additive genetic effects, permanent environmental deviations, and components of variance. A Markov chain Monte Carlo implementation based on the Gibbs sampler is described, and procedures for inferring the probability of yet to be observed future rankings are outlined. Part of the model is rendered nonparametric by introducing a Dirichlet process prior for the distribution of permanent environmental effects. This can lead to potential identification of clusters of such effects, which, in some competitions such as horse races, may reflect forms of undeclared preferential treatment. L ATENT variable models for describing mechanismsby which some continuous scale maps into ordered or unordered categories of response have a long tradition in quantitative genetics and psychometry. For example, the threshold-liability model for ordinal categories dates back to Wright (1934), Dempster and Lerner (1950), Grü neberg (1952), and Falconer (1965; see Gianola (1982) for a review. Extremal models were pioneered in psychology by Thurstone (1927) and were adapted by Bock and Jones (1968) to explain choices between unordered alternatives.Suppose that an observation is an assignment into one of M mutually exclusive and exhaustive categories of response. The classical Thurstonian extremal model postulates the existence of some latent or unobserved continuous valued vector y M 31 ¼ fy i g, such that category i is observed when y i is larger than the other M À 1 elements of the vector. The probability of observing an assignment into category M, say, is given by Prðy M . y M À1 ; y M . y M À2 ; . . . ; y M . y 1 j parametersÞ;

show abstract

A semiparametric Bayesian model for randomised block designs

Cited by 258 publications

References 10 publications

A nonparametric Bayesian alternative to spike sorting

A nonparametric Bayesian alternative to spike sorting

profdpm: AnRPackage for MAP Estimation in a Class of Conjugate Product Partition Models

A Thurstonian Model for Quantitative Genetic Analysis of Ranks: A Bayesian Approach

Contact Info

Product

Resources

About