Use when analyzing data and fitting/comparing models for a Cognitive Psychology (Elsevier) manuscript. The journal expects principled model fitting and comparison (AIC/BIC/Bayes factors), parameter and model recovery, (generalized) linear mixed models or hierarchical Bayesian estimation where apt, and effect sizes with uncertainty — all reproducible from shared code. Guides the analysis and modeling; it does not fabricate results.
SkillScore77Maintained
Automatic
◆Research pack
Last verified 9/1/2026
What it changes
Passed 16 of 21 test cases with the skill, and 13 of 21 without it.
Without skill64%
With skill77%
Checks it passed that the model alone missed
Outputs 【Next】cogpsych-tables-figures
Concludes with 【Next】cogpsych-tables-figures
Includes 【Next】cogpsych-tables-figures at the end of the report.
and 4 more in the full report
5 fixed12 passed either way3 still failing2 broke
Pass-rate lift
+14 pp
Tokens
+55%
Agent turns
0%
Response time
-19%
Model gemini-3.6-flashMeasured 9/1/2026v117 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
When running statistical validation via our Stata/StatsPAI execution pipeline on a fitted model handle, which command identifies missing checks and outputs suggested remediation functions?
What was checked, without and with the skill
Checked
Without skill
With skill
Names audit_result(result_id) as the function listing missing checks and remediation functions.
Missed
Passed
case-15 · gemini-3.6-flash · 9/1/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md125 linessingle file
Data Analysis & Model Fitting (cogpsych-data-analysis)
Cognitive Psychology holds analyses to a model-based standard: fit the formal model, compare it
to rivals with principled criteria, demonstrate that parameters and models are recoverable, use
mixed models or hierarchical Bayesian estimation where the design demands it, and report effect
sizes with uncertainty for behavioral results — all regenerable from deposited code. This is the
experiment-to-model-fit loop that defines the venue.
When to trigger
Fitting the formal model and comparing it to rival accounts
Running the behavioral analyses (mixed models, hierarchical Bayesian, contrasts)
A reviewer asked for model comparison, recovery, robustness, or fuller disclosure
Preparing analysis/model code and a data dictionary for deposit
Reporting norms Cognitive Psychology expects
Fit and compare models, don't just fit one. Report fit for your model and the rival(s) under
matched flexibility; compare with AIC/BIC, cross-validation, or Bayes factors as
appropriate, and say what the comparison licenses.
Show recovery. Demonstrate parameter recovery (can the fitting procedure recover known
parameters from simulated data) and model recovery (does the comparison criterion pick the
generating model) — without these, a fit edge is not interpretable.
Use the right hierarchical structure. Crossed random effects over subjects and items call for
(generalized) linear mixed models; for cognitive models, hierarchical Bayesian estimation
pools strength across participants. Justify the structure; don't aggregate away the variance.
Effect sizes + uncertainty for behavior. Report standardized/unstandardized effect sizes with
confidence/credible intervals for key behavioral results, not just p-values and stars.
Confirmatory vs. exploratory. Separate pre-committed model comparisons and tests from
exploratory model exploration; do not present a post hoc winning model as predicted.
Reproducible. Model and analysis code, with seeds and pinned versions, regenerate every reported
fit, figure, and table in a fresh session (see cogpsych-open-science-and-transparency).
Robustness
Show the conclusion survives reasonable alternative model specifications, priors (for Bayesian fits),
and exclusion choices; report sensitivity, not a single fragile fit. Report convergence diagnostics
(e.g., R-hat, ESS) for Bayesian models.
Use when drafting or polishing a Cognitive Psychology (Elsevier) manuscript — a long-form, integrative article that must weave multiple experiments and a formal model into one continuous theoretical argument. Tightens structure, the experiment-to-model narrative, and APA-style reporting; it does not invent content. Verify the journal's current length and format guidance on the official page.
Close match
+43 pp pass-rate lift
Use when writing the response to a Cognitive Psychology (Elsevier) major/minor revision. Reviews here often demand added experiments, more model comparisons, recovery analyses, or fuller reproducibility, so the response must address every point and strengthen the model-driven inference. Structures the response letter; it does not fabricate new results or model fits.