Crim tables figures

Tables & Figures (crim-tables-figures)

Exhibits are where an expert reviewer checks whether the crime result is real. Criminology has its own signature figures — the age–crime curve, trajectory-group plots, survival curves, and crime maps — and each must earn its place and stand on its own.

When to trigger

• Designing the main results table/figure or a key descriptive exhibit
• Deciding what belongs in the article vs. an online appendix/supplement
• A reviewer found an exhibit unclear, mislabeled, or non-self-contained
• Presenting a trajectory model, survival analysis, or spatial pattern

Principles

1. Self-contained. A reader should understand each exhibit from its title, axis/column labels, and note alone. State the crime measure, units (counts vs. rates per 100k), sample, N, and time window.
2. Figures over dense tables for effects. Coefficient/forest plots, predicted counts/rate-ratio plots, and marginal-effects plots beat a wall of coefficients. Always show intervals.
3. Show the curve, not just the coefficient. Age–crime curves, trajectory-group plots (with group shares and CIs), and Kaplan–Meier / cumulative-incidence recidivism curves communicate the criminological story directly.
4. Maps when place is the point. Hot-spot / kernel-density / choropleth maps for spatial variation; label the unit (block, tract, agency) and the rate denominator; avoid misleading raw-count maps.
5. Accessible. Colorblind-safe palettes; legible in grayscale; no chartjunk or 3D. Reviewers parse fast.
6. Reproducible. Each exhibit is generated by the master script; numbers match the deposited package exactly (see crim-data-and-transparency).

Criminology-specific exhibits

• Trajectory plots: show group shares, posterior-probability summary, and CIs — not just mean lines.
• Survival/recidivism: report at-risk counts, censoring, and competing risks where relevant.
• For qualitative work: timelines, life-history charts, evidence tables linking claims to sources.

Execution bridge (StatsPAI / Stata MCP)

Generate exhibits from the fitted result, not by retyping numbers (the usual source of body-vs-supplement drift). Full map: execution-with-mcp. Criminology is observational — place/person panels where selection is pervasive; foreground DiD/IV/RDD and the selection objection.

• Tables: etable (multi-model columns) or did_summary_to_latex straight from the result_id.
• Figures: plot_from_result / enhanced_event_study_plot / event_study_table — axis units and the SE/clustering note baked in.
• Every note names the estimator + clustering and states the effect size in interpretable units.

See a full fitted-result → exhibit chain in the JF execution walkthrough.

Anti-patterns

• Maps or tables of raw crime counts where rates are needed (population not held constant)
• Trajectory plots that hide group shares or classification quality
• Reporting significance stars with no effect size or interval
• Cramming every robustness check into the main text instead of a supplement
• Exhibit numbers/values that don't match the deposited code output

Exhibit choice for the signature crime objects (decision table)

Each criminology figure carries a known probe; pick the exhibit that answers it.

Criminological object	Exhibit	The probe it must survive
Age–crime curve	line plot, offending rate by age	rate denominator, cohort vs. period
Developmental paths	trajectory plot w/ group shares + CIs	groups reified? AvePP shown?
Recidivism timing	Kaplan–Meier / cumulative incidence	censoring and competing risks shown?
Spatial concentration	hot-spot / choropleth, rate-based	raw counts masquerading as risk?
Treatment effect	coefficient/forest plot w/ intervals	uncertainty visible, not stars?

Worked micro-example: fixing a misleading hot-spot map (illustrative)

A draft maps raw burglary counts and the downtown tract glows red. A referee reads it as a risk claim it does not support — downtown has 5x the nighttime population (illustrative). The fix: switch to a rate per 1,000 ambient population, use a colorblind-safe sequential palette, label the unit and denominator in the note, and move the raw-count version to the supplement. Now the exhibit shows concentration of risk, the object the routine-activity argument claims.

Exhibit pass for Criminology

Treat this skill as an executable review pass, not a prose hint. First lock the crime/justice process, measurement validity, research design, and policy consequence; then judge whether the current manuscript answers the venue's real reader: criminology reviewers who expect theory-linked crime, justice, or harm mechanisms plus transparent measurement.

• Do the pass: For every table or figure, state the estimand or object, sample or case base, uncertainty display, and one sentence the exhibit proves for the venue audience.
• Return a ledger: give claim / evidence / risk / manuscript location rows, so the next agent can edit rather than rediscover the issue.
• Sibling guard: compare against Justice Quarterly for applied justice, Journal of Quantitative Criminology for methods focus, Social Problems for broader sociological framing; if a sibling owns the contribution, recommend re-routing before polishing format.
• Stop condition: do not give submission-ready advice until the pack's resources/official-source-map.md has been checked for volatile rules and the manuscript has one concrete fix for the largest venue-specific risk.

Output format

【Main exhibit】what it shows + why a figure/table/map
【Crime metric】counts vs. rates + denominator stated? [Y/N]
【Self-contained?】title + labels + note + N/units/time present? [Y/N]
【Accessible?】grayscale-legible + colorblind-safe? [Y/N]
【Main text vs supplement】split decided
【Reproducible?】generated by master script, matches package? [Y/N]
【Next】crim-writing-style

Supplementary resources

• ../../resources/external_tools.md — plotting, mapping, trajectory, and survival packages
• ../../resources/official-source-map.md — formatting and double-spacing expectations