Hierarchical Bayesian Markov Switching Models with Application to Predicting Spawning Success of Shovelnose Sturgeon

Abstract

The timing of spawning in fish is tightly linked to environmental factors; however, these factors are not very well understood for many species. Specifically, little information is available to guide recruitment efforts for endangered species such as the sturgeon. Therefore, we propose a Bayesian hierarchical model for predicting the success of spawning of the shovelnose sturgeon which uses both biological and behavioural (longitudinal) data. In particular, we use data that were produced from a tracking study that was conducted in the Lower Missouri River. The data that were produced from this study consist of biological variables associated with readiness to spawn along with longitudinal behavioural data collected by using telemetry and archival data storage tags. These high frequency data are complex both biologically and in the underlying behavioural process. To accommodate such complexity we developed a hierarchical linear regression model that uses an eigenvalue predictor, derived from the transition probability matrix of a two-state Markov switching model with generalized auto-regressive conditional heteroscedastic dynamics. Finally, to minimize the computational burden that is associated with estimation of this model, a parallel computing approach is proposed. Copyright (c) Journal compilation 2009 Royal Statistical Society.

Using stochastic volatility models to analyse weekly ozone averages in Mexico City

“…A literature review of these SV models in ecology is given by Holan et al (2009) with applications to predicting spawning of shovelnose sturgeon. In here we use SV models to study the behaviour of ozone pollution data.…”

Objective classification of latent behavioral states in bio‐logging data using multivariate‐normal hidden Markov models

“…Given the problems of using AIC and automatic model selection in HMMs, careful consideration and examination of both the estimated state distributions and pseudo-residuals should be undertaken for log-likelihood curves that do not exhibit a sharp bend. Alternative Bayesian methods such as Markov chain Monte Carlo (MCMC) could also be employed to estimate posterior probability distributions, and potentially utilize Bayesian P values for assessing goodness of fit (Holan et al 2009). MCMC sampling can be more computationally intensive, but if the numerical likelihood estimation approach that we suggest here does not provide clear indications for model selection, then these alternative methods should be considered.…”

“…Hidden Markov modeling has had a long history in the field of signal processing, particularly for voice recognition (Gales and Young 2007), but its popularity as a tool for examining ecological data has increased in recent years. Examples of such models applied to ecological problems include the foraging behavior of mouse lemurs (Schliehe-Diecks et al 2012), the spawning success of shovelnose sturgeon (Holan et al 2009), atsea behavior of Manx Shearwater (Dean et al 2012), and diving behavior in Macaroni Penguins (Hart et al 2010). HMMs assume that observations will depend on a finite number of underlying unobservable states (MacDonald and Zucchini 2009).…”

“…We examined the effect of covariate information by incorporating it directly into the parameters of the matrix of state-switching transition probabilities. This approach is similar to that described in Holan et al (2009), where a hierarchical Markov switching model was fitted to behavioral data captured using bio-logging devices to predict spawning of shovelnose sturgeon using covariate biological data. Our study was motivated by a need to more objectively quantify the behavior of tropical tuna, in the context of providing scientific advice for the management of an important natural resource, namely tuna fisheries in the Western and Central Pacific Ocean.…”

Research Tools to Investigate Movements, Migrations, and Life History of Sturgeons (Acipenseridae), with an Emphasis on Marine-Oriented Populations

“…The study by [81] used a combination of archival tags, radio tags, and sophisticated data analysis to determine if mature Shovelnose Sturgeon spawned successfully following tagging. The radio tags were used mainly to relocate individual sturgeon (whose state of gonadal development had been determined) bearing the digital storage tags that recorded temperature and depth.…”