MétaCan
Menu
Back to cohort
Record W7133021682

Bayesian Inference of Complex Latent Variable Models

2023· dissertation· W7133021682 on OpenAlexaboutno aff
K. Rai

Bibliographic record

VenueTSpace · 2023
Typedissertation
Language
FieldComputer Science
TopicData Analysis with R
Canadian institutionsnot available
Fundersnot available
KeywordsCovarianceStability (learning theory)Standard deviationRange (aeronautics)Transformation (genetics)IsotropySkewBayesian inference
DOInot available

Abstract

fetched live from OpenAlex

This thesis contains three separate chapters motivated by research questions related to public health. The first contribution is in the second chapter, which introduces a novel parameter transformation of anisotropic covariance functions. This transfor- mation relates the anisotropic ratio with the polar radius, and the anisotropic angle with the polar angle. It resolves an issue with the standard parameterization where the anisotropic angle has no meaning in the special case of isotropy, and provides a firmer mathematical framework in which to view isotropic covariance functions as a special case of the anisotropic covariance functions. It also proposes a transformation of the standard deviation and range parameters that renders them approximately orthogonal. The third chapter models the time-varying effect of air pollution. There is increasing interest in modeling air pollution effects as time-varying, and the contribution of this chapter is in proposing two posterior statistics that summarizes its trend over time – stability and momentum. Stability is the standard deviation of== tthis effect over time, and momentum is the proportion of its pairs of differences that are positive. The fourth chapter proposes a model that decomposes daily COVID-19 mortality into the sum of (scaled) skew normal curves. COVID-19 mortality has been heavily studied in recent years, and the contribution of this model is in providing the evolution of these curves and their parameters over a multi-year period. The model has interpretable parameters, including a shape parameter, which quantifies the degree of asymmetry of each skew normal curve. In addition to the methodological developments listed above, the models in chapters three and four provide results that (pending peer review) may be of interest to practitioners. The trend detection model is fit to daily air pollution and mortality data in census divisions across Canada, and finds one region with an increasing trend and one with a decreasing trend. The skew normal model provides a decomposition of daily COVID-19 mortality into skew normal curves in six regions, and the relation of these curves to COVID-19 waves may be of independent interest. Moreover, both of these models can be applied to any health outcome of interest.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.902
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.004
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0040.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0010.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.081
GPT teacher head0.362
Teacher spread0.281 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueTSpaceSame topicData Analysis with RFrench-language works237,207