From asr-skills
Guides analysis and reporting for ASR manuscripts to meet masked review standards across quantitative, demographic, comparative-historical, and computational sociology.
How this skill is triggered — by the user, by Claude, or both
Slash command
/asr-skills:asr-data-analysisThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
ASR reviewers are methodologically demanding across very different traditions. Whether your evidence
ASR reviewers are methodologically demanding across very different traditions. Whether your evidence
is regression coefficients, life tables, archival sequences, or coded fieldnotes, the analysis must be
transparent, well-documented, and reproducible to the extent your data allow. Design decisions live in
asr-research-design.
renv.lock, requirements.txt, recorded ssc/net installs).As the ASA's flagship, ASR draws referees who police analysis on each tradition's terms while asking one disciplinary question — does the evidence warrant a claim that speaks to general sociological theory? Use this table to pre-empt the masked reviewer.
| Reviewer probe | Clears the ASR bar | Triggers a revision flag |
|---|---|---|
| "Just a significant coefficient?" | magnitude + interval tied to a mechanism | stars-only, no interpretation |
| "Survives a reasonable confounder?" | sensitivity bound reported | one preferred spec, no probing |
| "Weighted and clustered right?" | design-respecting SEs | default SEs on a complex sample |
| "Where is disconfirming evidence?" | negative cases / null subgroups | only confirming evidence |
| "Heterogeneity real or mined?" | pre-specified or MHT-adjusted | one fished interaction theorized post hoc |
A hypothetical ASR study links employer credit-checking to a Black-white callback gap using administrative hiring records across 1,200 firms.
Main effect: callback gap 8.0 pp (95% CI 5.1–10.9) under firm + occupation FE
Mechanism: gap concentrated in customer-facing roles (11.2 pp) vs back-office (2.3 pp)
Sensitivity: a confounder must be ~1.7× the strongest covariate to nullify
Negative case: no gap where state law bans the practice (0.4 pp, CI −2.0–2.8) → boundary evidence
Reproducible: one master script, seed=2026, renv.lock pinned
The intervals carry the claim, the role contrast names a portable mechanism (statistical discrimination via screening signals), and the law-ban null is reported as evidence, not buried.
【Main result】magnitude + interval (quant) OR evidence chain (qual)
【Identification/grounding check】(per research-design) result
【Robustness / negative cases】what held
【Heterogeneity】pre-specified? MHT-adjusted? (quant)
【Reproducible】master script + seeds + pinned versions OR documented codebook? [Y/N]
【Next】asr-tables-figures
../../resources/external_tools.md — estimation, demography, networks, and text-as-data packages../../resources/official-source-map.md — ASA data-sharing normsnpx claudepluginhub brycewang-stanford/awesome-journal-skills --plugin asr-skillsProvides guidance for planning and auditing data analysis in American Journal of Sociology manuscripts, covering uncertainty, robustness, and triangulation across quantitative and qualitative methods.
Guides analysis and reporting for APSR manuscripts to survive expert double-anonymous review. Covers honest uncertainty, robustness, heterogeneity, and reproducibility.
Guides rigorous data analysis and reporting for Social Forces manuscripts, covering uncertainty, robustness, triangulation, and reproducibility for quantitative, demographic, network, or computational work.