Generalized Additive Models for Gigadata: Modeling the U.K. Black Smoke Network Daily Data

Wood, Simon N.; Li, Zheyuan; Shaddick, Gavin; Augustin, Nicole

doi:10.1080/01621459.2016.1195744

Cited by 160 publications

(150 citation statements)

References 53 publications

Supporting

Mentioning

132

Contrasting

Order By: Relevance

“…), and (3) new dimension reduction and estimation techniques facilitate efficient implementation for large data sets (Wood et al . , ). For comparison with our mechanistic Bayesian hierarchical model, we implemented a GAM that can be formally written as follows:

\begin{matrix} y_{i} \sim Bernoulli (p_{i}) \\ g false(p_{i} false) = {boldx}_{i} β + {normalη}_{t} + {normalη}_{normals}, \end{matrix}

where, as before,

y_{i}

is equal to 1 if the i th deer is CWD‐positive and 0 otherwise.…”

Section: Methodsmentioning

confidence: 99%

“…Guisan et al 2002;Wood & Augustin 2002). We compared a GAM to our hierarchical model because (1) the linear structure of the GAM is easy to interpret for statistical inference, (2) basis functions can be used to explicitly model the spatial and temporal process (Hefley et al 2017b), and (3) new dimension reduction and estimation techniques facilitate efficient implementation for large data sets (Wood et al 2015(Wood et al , 2017. For comparison with our mechanistic Bayesian hierarchical model, we implemented a GAM that can be formally written as follows:…”

Section: Comparison With Generalised Additive Modelsmentioning

confidence: 99%

See 1 more Smart Citation

When mechanism matters: Bayesian forecasting using models of ecological diffusion

et al. 2017

View full text Add to dashboard Cite

Ecological diffusion is a theory that can be used to understand and forecast spatio-temporal processes such as dispersal, invasion, and the spread of disease. Hierarchical Bayesian modelling provides a framework to make statistical inference and probabilistic forecasts, using mechanistic ecological models. To illustrate, we show how hierarchical Bayesian models of ecological diffusion can be implemented for large data sets that are distributed densely across space and time. The hierarchical Bayesian approach is used to understand and forecast the growth and geographic spread in the prevalence of chronic wasting disease in white-tailed deer (Odocoileus virginianus). We compare statistical inference and forecasts from our hierarchical Bayesian model to phenomenological regression-based methods that are commonly used to analyse spatial occurrence data. The mechanistic statistical model based on ecological diffusion led to important ecological insights, obviated a commonly ignored type of collinearity, and was the most accurate method for forecasting.

show abstract

\begin{matrix} y_{i} \sim Bernoulli (p_{i}) \\ g false(p_{i} false) = {boldx}_{i} β + {normalη}_{t} + {normalη}_{normals}, \end{matrix}

where, as before,

y_{i}

is equal to 1 if the i th deer is CWD‐positive and 0 otherwise.…”

Section: Methodsmentioning

confidence: 99%

Section: Comparison With Generalised Additive Modelsmentioning

confidence: 99%

When mechanism matters: Bayesian forecasting using models of ecological diffusion

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Thus, currently, the high computational cost of fitting such large models precludes us from taking advantage of mixed models. Nevertheless, recent progress with similarly large models (Wood, Li, Shaddick, & Augustin, 2017) shows that the combination of LMMs with deconvolution modeling might be computationally feasible in future implementations.…”

Section: Outlook: Integration With Linear Mixed Modelsmentioning

confidence: 99%

Unfold: An integrated toolbox for overlap correction, non-linear modeling, and regression-based EEG analysis

Ehinger

Dimigen

2018

Preprint

View full text Add to dashboard Cite

Electrophysiological research with event-related brain potentials (ERPs) is increasingly moving from simple, strictly orthogonal stimulation paradigms towards more complex, quasiexperimental designs and naturalistic situations that involve fast, multisensory stimulation and complex motor behavior. As a result, electrophysiological responses from subsequent events overlap with each other. In addition, the recorded neural activity is often modulated by numerous covariates, which influence the measured responses in a linear or nonlinear fashion.Examples of paradigms where systematic temporal overlap variations and low-level confounds between conditions cannot be avoided include combined EEG/eye-tracking experiments during natural vision, fast multisensory stimulation experiment, or mobile brain/body imaging studies.However, even "traditional", highly controlled ERP datasets often contain a hidden mix of overlapping activity (e.g. from stimulus onsets, involuntary microsaccades, or button presses) and, it is helpful or even necessary to disentangle these components for a correct interpretation of the results. In this paper, we introduce unfold, a powerful, yet easy-to-use MATLAB toolbox for regression-based EEG analyses that combines the existing concepts of massive univariate modeling ("regression ERPs"), linear deconvolution modeling, and generalized additive modeling into one coherent and flexible analysis framework. The toolbox is modular, compatible with EEGLAB and can handle even large datasets efficiently. It also includes advanced options for regularization and the use of temporal basis functions (e.g. Fourier sets).We illustrate the advantages of this approach for simulated data as well as data from a standard face recognition experiment. In addition to traditional and non-conventional EEG/ERP designs,

show abstract

“…In the long term, it will be promising to integrate deconvolution with mixed-effects modeling (Ehinger, 2019), but this will require large computational resources (because the EEG data of all participants has to be fitted simultaneously) as well as new algorithms for estimating sparse mixed-effects models (e.g. Wood, Li, Shaddick, & Augustin, 2017).…”

Section: Integrating Deconvolution With Linear Mixed Modelsmentioning

confidence: 99%

Analyzing combined eye-tracking/EEG experiments with (non)linear deconvolution models

Dimigen¹,

Ehinger

2019

Preprint

View full text Add to dashboard Cite

Fixation-related potentials (FRPs), neural responses aligned to saccade offsets, are a promising tool to study the dynamics of attention and cognition under natural viewing conditions. In the past, four methodological problems have complicated the analysis of such combined eye-tracking/EEG experiments: (i) the synchronization of data streams, (ii) the removal of ocular artifacts, (iii) the condition-specific temporal overlap between the brain responses evoked by consecutive fixations, (iv) and the fact that numerous low-level stimulus and saccade properties also influence the post-saccadic neural responses. While effective solutions exist for the first two problems, the latter ones are only beginning to be addressed. In the current paper, we present and review a unified framework for FRP analysis that allows us to deconvolve overlapping potentials and control for linear and nonlinear confounds on theFRPs. An open software implementation is provided for all procedures. We then demonstrate the advantages of this approach for data from three commonly studied paradigms: face perception, scene viewing, and natural sentence reading. First, for a traditional ERP face recognition experiment, we show how deconvolution can separate stimulus-ERPs from overlapping muscle and brain potentials produced by small (micro)saccades on the face.Second, in scene viewing, we isolate multiple non-linear influences of saccade parameters on the FRP. Finally, for a natural sentence reading experiment using the boundary paradigm, we show how it is possible to study the neural correlates of parafoveal preview after removing spurious overlap effects caused by the associated difference in average fixation time. Our results suggest a principal way of measuring reliable fixation-related brain potentials during natural vision.

show abstract

Generalized Additive Models for Gigadata: Modeling the U.K. Black Smoke Network Daily Data

Cited by 160 publications

References 53 publications

When mechanism matters: Bayesian forecasting using models of ecological diffusion

When mechanism matters: Bayesian forecasting using models of ecological diffusion

Unfold: An integrated toolbox for overlap correction, non-linear modeling, and regression-based EEG analysis

Analyzing combined eye-tracking/EEG experiments with (non)linear deconvolution models

Contact Info

Product

Resources

About