Guided tour
Sample data · no sign-up
UnitTrack · Disclosure-controlled report
Gas — Rural Co-op
Prairie Gas Co-op (synthetic)
Generated 2026-07-27 20:51 ·
Grouped by census tract · k = 15
Residual re-identification risk
worst case 0% · None
0/53
Census tract groups published
0.0%
of meter reads in published output
53
groups withheld by disclosure control
15/15 rule
≥15 contributors; no single customer over 15%
Contents
Disclosure control & data provenance
Grouping the dataset into 53 census tract groups, 0 were safe to publish and 53 were withheld under the rules below. Across 1440 meter reads, 0.0% of records and 0.0% of total total consumption remain in the published output, with worst-case re-identification risk of 0% (None).
Data quality & reliability
1440
Loaded reads
0 rejected & quarantined
4.4%
Estimated reads
utility estimate flag
0.3%
Negative usage
rollovers / net metering
206
High outliers
Tukey 1.5·IQR (1977)
Anomalies are flagged, not dropped; rows failing validation are quarantined as rejected. 24 reads (1.7%) lack coordinates and are excluded from spatial views.
Methods & authorities
-
Minimum-count (k-anonymity) — 53 groups withheld
(triggered by your minimum group size k = 15).
Sweeney, k-anonymity (2002); ESSnet/Eurostat SDC Handbook (Hundepool et al.) — minimum-frequency / threshold rule · Meets/exceeds: CA CPUC D.14-05-016 ("15/15"); IL 220 ILCS 33
-
PII handling — identifiers are excluded from the analytic
path; only disclosure-controlled aggregates are reported.
NIST SP 800-122; NISTIR 8053
Published results
| Census tract | Total consumption (therms) | Contributors | Status |
|---|---|---|---|
| Tract 23.25 | * | — | Withheld |
| Tract 10 | * | — | Withheld |
| Tract 23.04 | * | — | Withheld |
| Tract 13.11 | * | — | Withheld |
| Tract 9.02 | * | — | Withheld |
| Tract 14.03 | * | — | Withheld |
| Tract 4.01 | * | — | Withheld |
| Tract 23.15 | * | — | Withheld |
| (no location) | * | — | Withheld |
| Tract 23.27 | * | — | Withheld |
| Tract 8.04 | * | — | Withheld |
| Tract 23.20 | * | — | Withheld |
| Tract 8.01 | * | — | Withheld |
| Tract 11.01 | * | — | Withheld |
| Tract 16.05 | * | — | Withheld |
| Tract 24.48 | * | — | Withheld |
| Tract 13.09 | * | — | Withheld |
| Tract 14.01 | * | — | Withheld |
| Tract 23.07 | * | — | Withheld |
| Tract 23.16 | * | — | Withheld |
| Tract 11.02 | * | — | Withheld |
| Tract 13.12 | * | — | Withheld |
| Tract 23.13 | * | — | Withheld |
| Tract 21.09 | * | — | Withheld |
| Tract 6.01 | * | — | Withheld |
| Tract 23.23 | * | — | Withheld |
| Tract 3.08 | * | — | Withheld |
| Tract 7 | * | — | Withheld |
| Tract 23.14 | * | — | Withheld |
| Tract 12 | * | — | Withheld |
| Tract 16.03 | * | — | Withheld |
| Tract 3.07 | * | — | Withheld |
| Tract 3.09 | * | — | Withheld |
| (outside area) | * | — | Withheld |
| Tract 20.03 | * | — | Withheld |
| Tract 21.11 | * | — | Withheld |
| Tract 16.02 | * | — | Withheld |
| Tract 24.11 | * | — | Withheld |
| Tract 11.03 | * | — | Withheld |
| Tract 19.11 | * | — | Withheld |
| Tract 24.47 | * | — | Withheld |
| Tract 9.01 | * | — | Withheld |
| Tract 24.03 | * | — | Withheld |
| Tract 23.10 | * | — | Withheld |
| Tract 9800 | * | — | Withheld |
| Tract 8.03 | * | — | Withheld |
| Tract 23.22 | * | — | Withheld |
| Tract 19.10 | * | — | Withheld |
| Tract 24.44 | * | — | Withheld |
| Tract 21.07 | * | — | Withheld |
| Tract 13.07 | * | — | Withheld |
| Tract 16.04 | * | — | Withheld |
| Tract 4.02 | * | — | Withheld |
Consumption profile
Total consumption by census tract — published groups (therms)
Consumption distribution & inequality
0.927
Gini coefficient
Gini 1912; Lorenz 1905
6.954
Coefficient of variation
std ÷ mean
1509
Median use / account (therms/yr)
across 120 accounts
19
High outliers
Tukey 1.5·IQR
Lorenz curve — cumulative use vs. cumulative accounts
Percentiles (therms/yr)
| 10th | withheld |
| 25th | 968 |
| Median | 1509 |
| 75th | 2802 |
| 90th | withheld |
Outer percentiles withheld (tail-coding; ESSnet SDC Handbook; NIST SP 800-188).
Customer class × month
Total consumption — class (rows) × month (columns); blanks were suppressed (therms)
Weather & seasonality
38.2%
Weather-sensitive (heating-driven)
ASHRAE G14; PRISM
100.0% / 0.0%
Heating / cooling split
of weather-driven use
—
Weather-normalized annual
restated at normal year
0.587
Model fit (R²)
degree-day regression
E = 1353 + 4.1457·HDD · base 65°F · 11 months
Seasonal use — 71.8% above winter baseline, peak Apr
Average monthly consumption vs. winter baseline (therms)
Winter-baseline (minimum-month) method. Standard seasonal decomposition.
Benchmarking — Energy Use Intensity
71.0
Median EUI (kBtu/ft²/yr)
EPA ENERGY STAR; DOE/EIA CBECS
115
Buildings benchmarked
floor area & ≥ 2 months
1 kWh = 3.412 kBtu; 1 therm = 100 kBtu (EIA)
reference constants v2024.1
EUI distribution across buildings (published classes)
By customer class (site EUI, kBtu/ft²/yr)
| Class | Bldgs | p25 | Median | p75 | vs nat'l |
|---|---|---|---|---|---|
| RESIDENTIAL | 100 | 43.1 | 69.7 | 113.1 | 232% |
| COMMERCIAL | 15 | 32.4 | 77.1 | 199.5 | 110% |
| INDUSTRIAL | 5 | * | * | * | * |
Within-dataset EUI percentiles vs. class peers. “vs nat'l” is coarse all-fuel context (CBECS 2018 / RECS 2020), not the ENERGY STAR 1–100 score. Small classes withheld.
Energy burden & equity
Every census tract was suppressed — no tract had at least 15 accounts with an ACS median income on record.
Explore burden live →Measurement & verification (IPMVP Option C)
Baseline model fit on 5 months before Jul 2023; savings measured over the following 6 reporting months. Synthetic demo with no intervention — avoided energy near 0% is the method working correctly.
13.2%
Avoided energy
1377 therms/meter
10399
Adjusted baseline (CBL)
therms/meter expected
9022
Reporting actual
therms/meter metered
0.613
Baseline fit (R²)
degree-day model
Reporting period: metered actual vs. adjusted baseline (therms/meter)
IPMVP Option C (EVO 10000-1:2016); ASHRAE Guideline 14; base-65°F degree days (US EIA / NOAA).
Differential privacy — an alternative release
An alternative to suppression: instead of hiding small groups, calibrated Laplace noise is added to each count (ε = 1.0, scale b = 1.0) so no individual's presence can be inferred while totals stay useful. Mean absolute error ±1.0 across 30 groups.
True vs. differentially private counts by geography
Laplace mechanism, ε-differential privacy. Dwork, McSherry, Nissim & Smith (2006); Dwork & Roth (2014); US Census Bureau 2020 DAS.
Appendix — policy & citations
Disclosure-control settings
| Governing standard | 15/15 rule |
| Minimum group size (k) | 15 |
| Dominance (top-n ≤ p) | 1 ≤ 0.15 |
| Min accounts for models | 15 |
| Grouping | Census tract |
Standards & sources cited
- k-anonymity — Sweeney (2002); ESSnet/Eurostat SDC Handbook
- (n,k)-dominance — ESSnet SDC Handbook §4.2; CPUC 15/15
- Inequality — Gini (1912); Lorenz (1905)
- Spatial — Moran (1950); Cliff & Ord (1973)
- Weather / M&V — ASHRAE Guideline 14; IPMVP Option C; PRISM
- Benchmarking — EPA ENERGY STAR; DOE/EIA CBECS/RECS
- Load — NREL UMP; BPA M&V Peak Demand
- Burden — ACEEE; US Census ACS
- Differential privacy — Dwork et al. (2006); US Census 2020 DAS
- PII — NIST SP 800-122; NISTIR 8053; NIST SP 800-188
- Methods & Formulas — every rule & analysis with its formula-as-implemented and primary citation
Synthetic sample data — for demonstration, not distribution. Generated by UnitTrack, a Polish Clover Solutions product · 2026-07-27 20:51.