Bayesian inference of population expansions in domestic bovines

< p > The past population dynamics of four domestic and one wild species of bovine were estimated using Bayesian skyline plots, a coalescent Markov chain Monte Carlo method that does not require an assumed parametric model of demographic history. Four dom

Bayesian inference for multidimensional NMR image reconstruction

Reconstruction of an image from a set of projections has been adapted to generate multidimensional nuclear magnetic resonance (NMR) spectra, which have discrete features that are relatively sparsely distributed in space. For this reason, a reliable reconstruction can be made from a small number of projections. This new concept is called Projection Reconstruction NMR (PR-NMR). In this paper, multidimensional NMR spectra are reconstructed by Reversible Jump Markov Chain Monte Carlo (RJMCMC). This statistical method generates samples under the assumption that each peak consists of a small number of parameters: position of peak centres, peak amplitude, and peak width. In order to find the number of peaks and shape, RJMCMC has several moves: birth, death, merge, split, and invariant updating. The reconstruction schemes are tested on a set of six projections derived from the three-dimensional 700 MHz HNCO spectrum of a protein HasA.

Rebuilding the limit order book: Sequential Bayesian inference on hidden states

The limit order book of an exchange represents an information store of market participants' future aims and for many traders the information held in this store is of interest. However, information loss occurs between orders being entered into the exchange and limit order book data being sent out. We present an online algorithm which carries out Bayesian inference to replace information lost at the level of the exchange server and apply our proof of concept algorithm to real historical data from some of the world's most liquid futures contracts as traded on CME GLOBEX, EUREX and NYSE Liffe exchanges. © 2013 © 2013 Taylor & Francis.

Bayesian inference and learning in Gaussian process state-space models with Particle MCMC

State-space models are successfully used in many areas of science, engineering and economics to model time series and dynamical systems. We present a fully Bayesian approach to inference and learning (i.e. state estimation and system identification) in nonlinear nonparametric state-space models. We place a Gaussian process prior over the state transition dynamics, resulting in a flexible model able to capture complex dynamical phenomena. To enable efficient inference, we marginalize over the transition dynamics function and, instead, infer directly the joint smoothing distribution using specially tailored Particle Markov Chain Monte Carlo samplers. Once a sample from the smoothing distribution is computed, the state transition predictive distribution can be formulated analytically. Our approach preserves the full nonparametric expressivity of the model and can make use of sparse Gaussian processes to greatly reduce computational complexity.

Bayesian inference of plastosphere viscosities near the Kunlun Fault, northern Tibet

IEECAS SKLLQG

Ages of 24 widespread tephras erupted since 30,000 years ago in New Zealand, with re-evaluation of the timing and palaeoclimatic implications of the Lateglacial cool episode recorded at Kaipo bog

Tephras are important for the NZ-INTIMATE project because they link all three records comprising the composite inter-regional stratotype developed for the New Zealand climate event stratigraphy (NZ-CES). Here we firstly report new calendar ages for 24 widespread marker tephras erupted since 30,000 calendar (cal.) years ago in New Zealand to help facilitate their use as chronostratigraphic dating tools for the NZ-CES and for other palaeoenvironmental and geological applications. The selected tephras comprise 12 rhyolitic tephras from Taupo, nine rhyolitic tephras from Okataina, one peralkaline rhyolitic tephra from Tuhua, and one andesitic tephra each from Tongariro and Egmont/Taranaki volcanic centres. Age models for the tephras were obtained using three methods: (i) C-based wiggle-match dating of wood from trees killed by volcanic eruptions (these dates published previously); (ii) flexible depositional modelling of a high-resolution C-dated age-depth sequence at Kaipo bog using two Bayesian-based modelling programs, Bacon and OxCal's P_Sequence function, and the IntCal09 data set (with SH offset correction-44±17yr); and (iii) calibration of C ages using OxCal's Tau_Boundary function and the SHCal04 and IntCal09 data sets. Our preferred dates or calibrated ages for the 24 tephras are as follows (youngest to oldest, all mid-point or mean ages of 95% probability ranges): Kaharoa AD 1314±12; Taupo (Unit Y) AD 232±10; Mapara (Unit X) 2059±118cal.yrBP; Whakaipo (Unit V) 2800±60cal.yrBP; Waimihia (Unit S) 3401±108cal.yrBP; Stent (Unit Q) 4322±112cal.yrBP; Unit K 5111±210cal.yrBP; Whakatane 5526±145cal.yrBP; Tuhua 6577±547cal.yrBP; Mamaku 7940±257cal.yrBP; Rotoma 9423±120cal.yrBP; Opepe (Unit E) 9991±160cal.yrBP; Poronui (Unit C) 11,170±115cal.yrBP; Karapiti (Unit B) 11,460±172cal.yrBP; Okupata 11,767±192cal.yrBP; Konini (bed b) 11,880±183cal.yrBP; Waiohau 14,009±155cal.yrBP; Rotorua 15,635±412cal.yrBP; Rerewhakaaitu 17,496±462cal.yrBP; Okareka 21,858±290cal.yrBP; Te Rere 25,171±964cal.yrBP; Kawakawa/Oruanui 25,358±162cal.yrBP; Poihipi 28,446±670cal.yrBP; and Okaia 28,621±1428cal.yrBP.Secondly, we have re-dated the start and end of the Lateglacial cool episode (climate event NZce-3 in theNZ-CES), previously referred to as the Lateglacial climate reversal, as defined at Kaipo bog in eastern North Island, New Zealand, using both Bacon and OxCal P_Sequence modelling with the IntCal09 data set. The ca1200-yr-long cool episode, indicated by a lithostratigraphic change in the Kaipo peat sequence to grey mudwith lowered carbon content, and a high-resolution pollen-derived cooling signal, began 13,739±125cal.yrBP and ended 12,550±140cal.yrBP (mid-point ages of the 95% highest posterior density regions, Bacon modelling). The OxCal modelling, generating almost identical ages, confirmed these ages. The Lateglacial cool episode (ca 13.8-12.6cal.kaBP) thus overlaps a large part of the entire Antarctic Cold Reversal chronozone (ca 14.1-12.4cal.kaBP or ca 14.6-12.8cal.kaBP), and an early part of the Greenland Stadial-1 (Younger Dryas) chronozone (ca 12.9-11.7cal.kaBP). The timing of the Lateglacial cool episode at Kaipo is broadly consistent with the latitudinal patterns in the Antarctic Cold Reversal signal suggested for the New Zealand archipelago from marine and terrestrial records, and with records from southern South America. © 2012 Elsevier Ltd.