Chart People

Selected research example

Rogers Park reports with an arrest flag: a fitted celeration reversal

All categories · Arrest: true

City source retrieved November 5, 2026 · scan evaluated November 9, 2026 · celeration turn

Download exact evidence ↓Open these filters in Chicago Data →

Current dashboard records may have been revised. Analyze is a separate action there. Saved-for-review choices stay in this browser and do not endorse a result.

Celeration turns: changes between fitted phases

A factor describes a standardized six-month multiplier, not a count. These turns passed the scan’s volume and magnitude gates; phase selection remains exploratory.

  • Suggested boundary July 2019: ÷1.01 → ÷2.12 per six months; 2.1× change between factors. Adjacent raw phase totals: 1,740 and 591. The fitted slope changes without reversing sign.
  • Suggested boundary July 2020: ÷2.12 → ×1.07 per six months; 2.26× change between factors. Adjacent raw phase totals: 591 and 3,563. The fitted slope signs reverse.

How to read this example

This candidate concerns crime records in Rogers Park whose arrest field was true at retrieval, across all categories. It is not a measure of all arrests made in Rogers Park and does not establish a change in enforcement effectiveness. The selected attribute must remain part of any interpretation of the chart.

The saved model separates the covered series into disjoint phases, including suggested starts in July 2019 and July 2020. The six-month factors are approximately 0.989, 0.471 and 1.066. The middle fitted phase declines; the following fitted phase rises. Comparing those standardized multipliers is the turn signal. It is not the same calculation as comparing two raw annual totals.

The dates were selected through exploratory phase search, not specified before looking at this series. Conditional intervals assume fixed boundaries and independent log residuals; they do not account for all the searched filters. Comparing records without the arrest filter, inspecting category composition and checking revisions would help challenge the pattern before assigning an explanation.

Saved observations and fitted phases

Suggested 3-phase description — exploratory, not confirmed.

Fixed six-log-cycle frame · 120 calendar months · factors per six months. Raw zeros stay zero; confirmed zeros become one only for log-space fitting and diagnostics. Missing coverage remains unavailable.

Monthly crime reports on a standard celeration chartCity of Chicago published records. Fixed six-decade count scale, 120 calendar months, celeration per 6 months. Zero markers are unconnected below the plot. Exact counts and coverage are available in the data table. Analyze: suggested. Suggested 3-phase description — exploratory, not confirmed. See the phase results table for dates, factors and uncertainty.1510501005001,0005,00010,00050,000100,000500,0001,000,000Reports per monthsuggested phase 1: 2016-10–2019-06suggested phase 2: 2019-07–2020-06suggested phase 3: 2020-07–2026-09Oct 2016: 54Nov 2016: 40Dec 2016: 51Jan 2017: 45Feb 2017: 44Mar 2017: 52Apr 2017: 60May 2017: 56Jun 2017: 58Jul 2017: 67Aug 2017: 55Sep 2017: 41Oct 2017: 81Nov 2017: 54Dec 2017: 43Jan 2018: 51Feb 2018: 53Mar 2018: 51Apr 2018: 49May 2018: 39Jun 2018: 57Jul 2018: 73Aug 2018: 66Sep 2018: 60Oct 2018: 62Nov 2018: 39Dec 2018: 52Jan 2019: 48Feb 2019: 46Mar 2019: 65Apr 2019: 41May 2019: 55Jun 2019: 32Jul 2019: 75Aug 2019: 65Sep 2019: 72Oct 2019: 64Nov 2019: 56Dec 2019: 57Jan 2020: 56Feb 2020: 45Mar 2020: 38Apr 2020: 13May 2020: 23Jun 2020: 27Jul 2020: 28Aug 2020: 41Sep 2020: 35Oct 2020: 35Nov 2020: 26Dec 2020: 26Jan 2021: 23Feb 2021: 18Mar 2021: 43Apr 2021: 39May 2021: 40Jun 2021: 38Jul 2021: 19Aug 2021: 28Sep 2021: 23Oct 2021: 42Nov 2021: 28Dec 2021: 37Jan 2022: 22Feb 2022: 37Mar 2022: 27Apr 2022: 49May 2022: 41Jun 2022: 55Jul 2022: 67Aug 2022: 44Sep 2022: 51Oct 2022: 39Nov 2022: 30Dec 2022: 40Jan 2023: 57Feb 2023: 47Mar 2023: 39Apr 2023: 47May 2023: 53Jun 2023: 70Jul 2023: 35Aug 2023: 61Sep 2023: 57Oct 2023: 44Nov 2023: 47Dec 2023: 68Jan 2024: 64Feb 2024: 51Mar 2024: 59Apr 2024: 56May 2024: 58Jun 2024: 46Jul 2024: 48Aug 2024: 51Sep 2024: 65Oct 2024: 54Nov 2024: 55Dec 2024: 47Jan 2025: 75Feb 2025: 65Mar 2025: 61Apr 2025: 59May 2025: 70Jun 2025: 55Jul 2025: 59Aug 2025: 63Sep 2025: 60Oct 2025: 47Nov 2025: 47Dec 2025: 44Jan 2026: 53Feb 2026: 54Mar 2026: 50Apr 2026: 54May 2026: 55Jun 2026: 52Jul 2026: 61Aug 2026: 60Sep 2026: 69ZeroUnknownOct 2016Oct 2017Oct 2018Oct 2019Oct 2020Oct 2021Oct 2022Oct 2023Oct 2024Oct 2025Oct 2026Calendar months

Suggested phases · exploratory · per six months

  1. 1 · Oct 2016–Jun 2019÷1.01Direction uncertain
  2. 2 · Jul 2019–Jun 2020÷2.12Fitted decrease
  3. 3 · Jul 2020–Sep 2026×1.07Fitted increase

Check the evidence

Interpretation and limitations (11)
  • Exploratory description, not a forecast, causal explanation or proof of a change.
  • Approximate 95% factor intervals assume independent, constant-variance log residuals and fixed boundaries. They do not account for boundary search, serial dependence or source revisions.
  • Confirmed zeros are treated as 1 only for fitting and its diagnostics. Raw counts stay zero; low-count results depend on this convention.
  • Independent phase lines may jump at boundaries. Every observation belongs to exactly one phase.
  • Reporting, classifications and seasonality can change. Counts are not population-adjusted; a level shift without a slope change is not the target of this search.
  • Uses dated last-good cached data, not newly verified source counts.
  • Boundary ranges show near-optimal models within 2 BIC units, not confidence intervals. They can be narrow even when the model is uncertain.
  • A phase is at the minimum allowed length; its boundary may be sensitive to that search limit.
  • At least one factor interval includes 1; its direction is uncertain under this approximation.
  • Many dependent filter conditions were searched. No multiple-testing-adjusted significance or causal attribution is claimed.
  • Frequency compares fixed equal-length windows of raw counts, not population risk or a celeration-factor ratio. Reporting, classifications and exposure may have changed.
Phase diagnostics

Intervals assume fixed boundaries and independent log residuals. They are not adjusted for the phase or filter search. Near-optimal boundary ranges are not confidence intervals.

Saved phase results
PhaseStart–endMonthsFactor / six monthsConditional 95% intervalZeros fitted as 1Lag-one residual
1October 2016–June 201933÷1.010.9455–1.0350-0.012
2July 2019–June 202012÷2.120.3356–0.662100.122
3July 2020–September 202675×1.071.050–1.08300.264

Near-optimal boundary range: July 2019–July 2019.

Near-optimal boundary range: July 2020–August 2020.

Exact monthly observations (120 slots)

Newest first. Unknown coverage is not a zero. These are the original saved observations, not fitted or rounded predictions.

Raw monthly reports
MonthRaw countCoverage
September 202669complete
August 202660complete
July 202661complete
June 202652complete
May 202655complete
April 202654complete
March 202650complete
February 202654complete
January 202653complete
December 202544complete
November 202547complete
October 202547complete
September 202560complete
August 202563complete
July 202559complete
June 202555complete
May 202570complete
April 202559complete
March 202561complete
February 202565complete
January 202575complete
December 202447complete
November 202455complete
October 202454complete
September 202465complete
August 202451complete
July 202448complete
June 202446complete
May 202458complete
April 202456complete
March 202459complete
February 202451complete
January 202464complete
December 202368complete
November 202347complete
October 202344complete
September 202357complete
August 202361complete
July 202335complete
June 202370complete
May 202353complete
April 202347complete
March 202339complete
February 202347complete
January 202357complete
December 202240complete
November 202230complete
October 202239complete
September 202251complete
August 202244complete
July 202267complete
June 202255complete
May 202241complete
April 202249complete
March 202227complete
February 202237complete
January 202222complete
December 202137complete
November 202128complete
October 202142complete
September 202123complete
August 202128complete
July 202119complete
June 202138complete
May 202140complete
April 202139complete
March 202143complete
February 202118complete
January 202123complete
December 202026complete
November 202026complete
October 202035complete
September 202035complete
August 202041complete
July 202028complete
June 202027complete
May 202023complete
April 202013complete
March 202038complete
February 202045complete
January 202056complete
December 201957complete
November 201956complete
October 201964complete
September 201972complete
August 201965complete
July 201975complete
June 201932complete
May 201955complete
April 201941complete
March 201965complete
February 201946complete
January 201948complete
December 201852complete
November 201839complete
October 201862complete
September 201860complete
August 201866complete
July 201873complete
June 201857complete
May 201839complete
April 201849complete
March 201851complete
February 201853complete
January 201851complete
December 201743complete
November 201754complete
October 201781complete
September 201741complete
August 201755complete
July 201767complete
June 201758complete
May 201756complete
April 201760complete
March 201752complete
February 201744complete
January 201745complete
December 201651complete
November 201640complete
October 201654complete
Source and reproducibility
Publisher dataset
Crimes — 2001 to Present · City of Chicago
Source retrieved
2026-11-05T21:08:01.557Z
Publisher update
2026-11-05T12:12:19.000Z
Covered months
October 2016–September 2026
Source note
Source ijzp-q8t2. Joint day/category/hour/applicable-flag/ward/status counts; no addresses, coordinates or incident identifiers. Each year's cells reconcile with an independent source total. Reads are not an atomic publisher snapshot. Published crime reports, not population-adjusted rates or final incidence. Prepared daily community-area snapshot; scheduled rebuild at 06:00 America/Chicago. Full supported history is rechecked for corrections. Retrieval timestamps are preserved; this is not a real-time feed. Crime analysis starts January 1, 2002; 2001 is excluded from counts and fitting inputs. Local indexed neighborhood snapshot. Totals are for the loaded area before other filters, not citywide totals. Citywide and unassigned-area views use a separate network-backed scope.
Snapshot
daily-v1:ef0c5e9b-09d5-4a2d-849e-1be6745dbfbb:neighborhood-v2:c95a8c2538e313309dd995335731fcc1
Discovery method
multi-feed-turn-and-frequency-renewal-v2
Analyze method
exploratory-segmented-log10-ols-zero-as-one-v3
Search plan
a3ffccedeb8d8ce18a30df3636839f775af1e5188e55a1f685695133135c6e35
Evidence run
755c7b92f5dd053cb2b1074d43762aa43de536adb3046f37846a50492788f3d1

Challenge the pattern

Check unfiltered totals, comparable communities, source revisions and administrative definitions before treating this candidate as evidence of a real-world explanation. Only explicitly documented follow-ups above have been performed; no others are implied by the ranking. Browse the other crime reports candidates or review the complete screening method.