Overview

This vignette documents the mrm_otis_*(), mrm_tps_*(), and mrm_siu_*() empirical callables. Each function is a one-line entry point to a verified analysis used in the MRM empirical paper (Ruhela 2026, in preparation). Every example below runs on the small reference samples bundled with the package, so the vignette is network-free.

For the full datasets:

OTIS 192 morie_load_dataset("otisb01") (downloads via CKAN on first call; subsequent calls hit the local SQLite cache)
TPS 192 morie_fetch_tps("Assault") (ArcGIS REST)
SIU 192 morie_fetch_siu() (on-demand scrape of public reports)

See vignette("mrm-dataset-fetchers") for the dataset side.

library(morie)
b01 <- morie_sample("otis_b01")
b09 <- morie_sample("otis_b09")
tps <- morie_sample("tps_assault")

OTIS suite

Placement-count concentration on `b09`

The b09 long-format file publishes per (fiscal year 0d7 placement-count band 0d7 gender) counts of individuals in segregation. The callable expands the banded counts using midpoints and returns Hill-MLE Pareto exponent, Gini coefficient, mean placements per individual, and the top-k% concentration share.

mrm_otis_placement_concentration(b09)
#>     year n_individuals n_placements mean_per_individual   gini hill_alpha
#> 1   2023         12647        55421            4.382146 0.5331     2.0174
#> 2   2024         10881        47123            4.330760 0.5862     2.1599
#> 3   2025          9608        46893            4.880620 0.6057     2.0880
#> 4 pooled         33136       149437            4.509808 0.5748     2.0814
#>   top_pct_share
#> 1        0.2932
#> 2        0.3351
#> 3        0.3215
#> 4        0.3180

The values are computed within fiscal year: OTIS UniqueIndividual_ID has format YYYY-XXXXX-SG and is randomly reassigned every fiscal year, so cross-year tracking is invalid by design.

Segregation-duration KM on `b01`

NumberConsecutiveDays_Segregation is the duration in days of each placement (no censoring 014 all durations are observed). The callable reports the per-stratum mean, median, q25, and the fraction above the UN Mandela 15-day cutoff.

mrm_otis_seg_duration_km(b01)
#>   stratum    n mean_days median_days q25_days pct_above_mandela
#> 1  pooled 1000      3.03           2        3               0.7
#>   median_among_above_mandela
#> 1                         54
mrm_otis_seg_duration_km(b01, group_cols = "MentalHealth_Alert")
#>   stratum   n mean_days median_days q25_days pct_above_mandela
#> 1      No 499      2.76           2        3               0.6
#> 2     Yes 501      3.29           2        4               0.8
#>   median_among_above_mandela
#> 1                       54.0
#> 2                       41.5

This callable replaces the misreading of YYYY-XXXXX-SG as a persistent person identifier, which produces a spurious cross-year “time-to-readmission” artifact.

Mortification co-occurrence (alert columns)

The three b01 alert flags (MentalHealth_Alert, SuicideRisk_Alert, SuicideWatch_Alert) co-occur to a degree well above independence. The substantive figure is MentalHealth \u00d7 SuicideRisk Cramer’s V.

mrm_otis_mortification_cooccurrence(b01)
#>              alert_a            alert_b    n   chi2 df   p_value cramers_v
#> 1 MentalHealth_Alert  SuicideRisk_Alert 1000  33.25  1  8.12e-09    0.1823
#> 2 MentalHealth_Alert SuicideWatch_Alert 1000  12.09  1  5.08e-04    0.1099
#> 3  SuicideRisk_Alert SuicideWatch_Alert 1000 470.37  1 2.66e-104    0.6858

Region locality

Ontario provincial seg/RC placement is overwhelmingly locality-preserving 014 over 95% of placements remain within the same region in the full b01.

# (Region columns are present only in the full b01, not the bundled
# sample; uncomment after morie_load_dataset("otisb01") or
# morie_fetch_tps(...) if needed.)
res <- mrm_otis_region_locality(b01)
print(res$table)
cat("diagonal share:", res$diagonal_share, "  V:", res$cramers_v, "\n")

Mandela classification

mrm_classify_mandela() shipped in v0.1.14 and remains the canonical Mandela classifier in v0.2.0. It supports three operationalisations:

mrm_classify_mandela(b01, denominator = "row")           # per-placement
#>     year denominator n_mandela        rate  pct n_broader_rc rate_broader
#> 1   2023         362         0 0.000000000 0.00            0  0.000000000
#> 2   2024         337         3 0.008902077 0.89            3  0.008902077
#> 3   2025         301         4 0.013289037 1.33            4  0.013289037
#> 4 pooled        1000         7 0.007000000 0.70            7  0.007000000
mrm_classify_mandela(b01, denominator = "individual_any") # per-person
#>     year denominator n_mandela        rate  pct n_broader_rc rate_broader
#> 1   2023         354         0 0.000000000 0.00            0  0.000000000
#> 2   2024         329         3 0.009118541 0.91            3  0.009118541
#> 3   2025         289         4 0.013840830 1.38            4  0.013840830
#> 4 pooled         972         7 0.007201646 0.72            7  0.007201646
mrm_classify_mandela(b01, denominator = "individual_cumulative")
#>     year denominator n_mandela        rate  pct n_broader_rc rate_broader
#> 1   2023         354         0 0.000000000 0.00            0  0.000000000
#> 2   2024         329         3 0.009118541 0.91            3  0.009118541
#> 3   2025         289         5 0.017301038 1.73            5  0.017301038
#> 4 pooled         972         8 0.008230453 0.82            8  0.008230453

The provincial-canonical 12.5/16.5/20.6 % torture rates from c11 require the c11 aggregate (loaded via morie_sample("otis_c11")); see the MRM empirical paper 0a76.

TPS suite

Levy-flight Hill exponent on inter-event step lengths

Treats consecutive events in chronological order as a single stream and computes the haversine inter-event step length (km). Returns the Hill-MLE exponent restricted to steps above min_step_km.

mrm_tps_levy_scaling(tps)
#> $n_events
#> [1] 1000
#> 
#> $n_steps_tail
#> [1] 995
#> 
#> $min_step_km
#> [1] 0.5
#> 
#> $hill_alpha
#> [1] 1.3043

Moran’s I + DBSCAN clustering

Grids the WGS84 extent into a coarse raster, counts events per cell, and computes the global Moran’s I via a rook-contiguity matrix. Also runs DBSCAN on the raw lat/long points (rescaled to km) for cluster counts.

mrm_tps_moran_clustering(tps, grid_resolution = 20L)
#> $morans_I
#> [1] -0.000138
#> 
#> $morans_z
#> [1] 0.67
#> 
#> $dbscan_n_clusters
#> [1] 21
#> 
#> $dbscan_n_noise
#> [1] 730
#> 
#> $dbscan_largest
#> [1] 82

For the high-precision computation on the full 254,378-event Assault file, use the morie Python tps_spatial_advanced pipeline; the R version is for quick interactive auditing.

Neighbourhood inter-event recurrence

For each HOOD_158 neighbourhood, sorts events chronologically and computes the gap (in days) between consecutive events.

head(mrm_tps_neighbourhood_recurrence_km(tps))
#>   hood n_events n_gaps mean_gap_days median_gap_days p25_gap_days p75_gap_days
#> 1  001       17     16        267.06           213.5       101.00       356.75
#> 2  002       12     11        447.91           360.0        74.00       606.00
#> 3  003        5      4        887.75           869.0       557.75      1199.00
#> 4  004        3      2       1781.00          1781.0      1065.50      2496.50
#> 5  005        4      3        776.00           676.0       537.00       965.00
#> 6  006        5      4        845.00           731.0       289.50      1286.50

Hawkes manifest loader

mrm_tps_load_hawkes_refit(path) reads paper_hawkes_refit.json (the per-category Hawkes refit table from the MRM empirical paper 0a77.1-7.2) and returns it as a tidy data.frame. Skipped here because the JSON is in the MOIRAIS data manifest, not bundled with the package.

SIU suite

The SIU callables operate on the SIU.csv file produced by morie_fetch_siu() (an on-demand scraper of the public Director’s Reports). The scraped corpus is not shipped, but the callables themselves do not depend on shipped data.

siu_path <- morie_fetch_siu()
siu <- read.csv(siu_path)
res <- mrm_siu_case_to_decision_km(siu)
print(res$pooled)
head(res$by_service[order(-res$by_service$n),])
mrm_siu_per_service_rate(siu)
mrm_siu_outcome_classifier(siu)

The verified pooled median in our test snapshot is 120 days from incident to Director’s decision (n = 1,711 cases). Per-service medians cluster tightly around 120, indicating a system-wide processing cadence rather than a per-jurisdiction effect.

References

MRM theoretical paper 014 Ruhela (2026), MRM: Multilevel Reconciliation Methodology — A Multi-Source Statistical Foundation for Canadian Carceral, Police, and Oversight Data, Zenodo 10.5281/zenodo.20096075.
MRM empirical paper 014 Ruhela (2026), Solitary Confinement, Self-Excitation, and Institutional Churn: Empirical Applications of MRM to Canadian Carceral and Police Data, Zenodo 10.5281/zenodo.20175689.
OTIS data dictionary 014 data.ontario.ca/dataset/data-on-inmates-in-ontario.
Toronto Police Open Data 014 data.torontopolice.on.ca/.
SIU public Director’s Reports 014 siu.on.ca/en/case_directors_reports.php.

MRM empirical callables (OTIS / TPS / SIU)