MétaCan
Menu
Back to cohort
Record W4307523682 · doi:10.31234/osf.io/vhgfk

On the testing of equivalent variables: Perfect correlations and correlational topology

2022· preprint· en· W4307523682 on OpenAlexafffund
Joshua P. Starr, Carl F. Falk

Bibliographic record

Venuenot available
Typepreprint
Languageen
FieldPsychology
TopicMental Health Research Topics
Canadian institutionsMcGill University
FundersFonds de Recherche du Québec - SantéNatural Sciences and Engineering Research Council of Canada
KeywordsMathematicsNull hypothesisCorrelationRedundancy (engineering)Topology (electrical circuits)Sample size determinationSample (material)Network topologyStatistical hypothesis testingEquivalence (formal languages)Partial correlationStatisticsComputer scienceDiscrete mathematicsCombinatorics

Abstract

fetched live from OpenAlex

When two variables effectively represent the same variable, redundancy may spur statistical complications. For example, in a psychological network model, the partial associations between that variable and other variables in the network may become distorted. The networktools R package contains the goldbricker function to screen for redundant variables, whereby difference-based null hypothesis testing is used to determine whether two variables have the same zero-order correlations with other variables (same topology). But this approach has logical drawbacks, does not directly consider whether two variables are highly correlated, and has never been formally evaluated. We adapted two equivalence testing (ET) approaches – one that tests topology and one that tests the correlation between two variables directly – and evaluated their performance relative to goldbricker in three simulation studies. In a third study, we introduce a latent variable modeling approach that considers variables to be less than perfectly reliable. While goldbricker had good ability to flag variables with redundant topology, it had high false positive rates at small sample sizes and exhibited a tendency to not flag pairs with trivial differences in topology at large sample sizes. The ET-based approaches maintained better false positive rates and a more desirable pattern of results at larger sample sizes. An empirical example with data from the Patient Reported Outcomes Measurement Information System is provided. We argue that there are better alternatives to goldbricker, and tradeoffs between ET and the latent variable modeling approach are critically discussed.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.182
metaresearch head score (Gemma)0.647
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.182
Threshold uncertainty score0.961

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.1820.647
Meta-epidemiology (narrow)0.0030.002
Meta-epidemiology (broad)0.0040.005
Bibliometrics0.0070.008
Science and technology studies0.0040.023
Scholarly communication0.0070.017
Open science0.0050.012
Research integrity0.0050.008
Insufficient payload (model declined to judge)0.0080.001

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 head0.207
GPT teacher head0.445
Teacher spread0.238 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
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

Citations6
Published2022
Admission routes2
Has abstractyes

Explore more

Same topicMental Health Research TopicsFrench-language works237,207