Skip to contents

The 3,107-county analysis table used in Nonconvex Geographically Weighted Regression for Local Variable Selection. The 91 columns retain the study's estimates, 90 percent margins of error, controlled-MOE flags, identifiers, projected coordinates and saved spatial folds.

Usage

data(acs2020_2024_counties)

Format

A data frame with 3,107 rows and 91 columns:

fips

Five-character county FIPS identifier; leading zeros retained. .

county_name

Census county or county-equivalent name. .

state_fips

Two-character state FIPS identifier. .

state_abbreviation

Two-letter postal abbreviation. .

state_name

State name. .

county_fips

Three-character within-state county FIPS identifier. .

easting_m

Easting of a point on the county surface after projection to NAD83 / Conus Albers (EPSG:5070); not longitude or latitude. metres.

northing_m

Northing of a point on the county surface after projection to NAD83 / Conus Albers (EPSG:5070); not longitude or latitude. metres.

spatial_fold

Saved spatial fold from k-means on standardized projected coordinates; seed 20260907, nstart 100. Fold labels must be reused for the paper analysis. 1 to 5.

median_household_income_2024

Original county median household income estimate, before the natural logarithm. 2024 inflation-adjusted US dollars.

log_median_household_income_2024

Natural logarithm of median_household_income_2024. Estimate!!INCOME AND BENEFITS (IN 2024 INFLATION-ADJUSTED DOLLARS)!!Total households!!Median household income (dollars) natural log of dollar value.

bachelors_or_higher_pct

Percent!!EDUCATIONAL ATTAINMENT!!Population 25 years and over!!Bachelor's degree or higher percent.

disability_pct

Percent!!DISABILITY STATUS OF THE CIVILIAN NONINSTITUTIONALIZED POPULATION!!Total Civilian Noninstitutionalized Population!!With a disability percent.

foreign_born_pct

Percent!!PLACE OF BIRTH!!Total population!!Foreign-born percent.

limited_english_pct

Percent!!LANGUAGE SPOKEN AT HOME!!Population 5 years and over!!Language other than English!!Speak English less than "very well" percent.

broadband_subscription_pct

Percent!!COMPUTERS AND INTERNET USE!!Total households!!With a broadband Internet subscription percent.

under_18_pct

Percent!!SEX AND AGE!!Total population!!Under 18 years percent.

age_65_plus_pct

Percent!!SEX AND AGE!!Total population!!65 years and over percent.

hispanic_latino_pct

Percent!!HISPANIC OR LATINO AND RACE!!Total population!!Hispanic or Latino (of any race) percent.

black_non_hispanic_pct

Percent!!HISPANIC OR LATINO AND RACE!!Total population!!Not Hispanic or Latino!!Black or African American alone percent.

labor_force_participation_pct

Percent!!EMPLOYMENT STATUS!!Population 16 years and over!!In labor force percent.

unemployment_pct

Percent!!EMPLOYMENT STATUS!!Population 16 years and over!!In labor force!!Civilian labor force!!Unemployed percent.

management_business_science_arts_occupation_pct

Percent!!OCCUPATION!!Civilian employed population 16 years and over!!Management, business, science, and arts occupations percent.

service_occupation_pct

Percent!!OCCUPATION!!Civilian employed population 16 years and over!!Service occupations percent.

natural_resources_construction_maintenance_occupation_pct

Percent!!OCCUPATION!!Civilian employed population 16 years and over!!Natural resources, construction, and maintenance occupations percent.

production_transport_material_moving_occupation_pct

Percent!!OCCUPATION!!Civilian employed population 16 years and over!!Production, transportation, and material moving occupations percent.

agriculture_forestry_fishing_mining_industry_pct

Percent!!INDUSTRY!!Civilian employed population 16 years and over!!Agriculture, forestry, fishing and hunting, and mining percent.

manufacturing_industry_pct

Percent!!INDUSTRY!!Civilian employed population 16 years and over!!Manufacturing percent.

professional_scientific_management_admin_waste_industry_pct

Percent!!INDUSTRY!!Civilian employed population 16 years and over!!Professional, scientific, and management, and administrative and waste management services percent.

self_employed_nonincorporated_pct

Percent!!CLASS OF WORKER!!Civilian employed population 16 years and over!!Self-employed in own not incorporated business workers percent.

work_from_home_pct

Percent!!COMMUTING TO WORK!!Workers 16 years and over!!Worked from home percent.

mean_commute_minutes

Estimate!!COMMUTING TO WORK!!Workers 16 years and over!!Mean travel time to work (minutes) minutes.

vacant_housing_pct

Percent!!HOUSING OCCUPANCY!!Total housing units!!Vacant housing units percent.

mobile_home_pct

Percent!!UNITS IN STRUCTURE!!Total housing units!!Mobile home percent.

renter_occupied_pct

Percent!!HOUSING TENURE!!Occupied housing units!!Renter-occupied percent.

no_vehicle_pct

Percent!!VEHICLES AVAILABLE!!Occupied housing units!!No vehicles available percent.

severe_crowding_pct

Percent!!OCCUPANTS PER ROOM!!Occupied housing units!!1.51 or more percent.

log_median_household_income_2024__moe90

Census 90% margin of error for log_median_household_income_2024. Despite the log-response prefix, this is the original income MOE in dollars; it has NOT been log-transformed. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. 2024 inflation-adjusted US dollars.

bachelors_or_higher_pct__moe90

Census 90% margin of error for bachelors_or_higher_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

disability_pct__moe90

Census 90% margin of error for disability_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

foreign_born_pct__moe90

Census 90% margin of error for foreign_born_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

limited_english_pct__moe90

Census 90% margin of error for limited_english_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

broadband_subscription_pct__moe90

Census 90% margin of error for broadband_subscription_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

under_18_pct__moe90

Census 90% margin of error for under_18_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

age_65_plus_pct__moe90

Census 90% margin of error for age_65_plus_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

hispanic_latino_pct__moe90

Census 90% margin of error for hispanic_latino_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

black_non_hispanic_pct__moe90

Census 90% margin of error for black_non_hispanic_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

labor_force_participation_pct__moe90

Census 90% margin of error for labor_force_participation_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

unemployment_pct__moe90

Census 90% margin of error for unemployment_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

management_business_science_arts_occupation_pct__moe90

Census 90% margin of error for management_business_science_arts_occupation_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

service_occupation_pct__moe90

Census 90% margin of error for service_occupation_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

natural_resources_construction_maintenance_occupation_pct__moe90

Census 90% margin of error for natural_resources_construction_maintenance_occupation_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

production_transport_material_moving_occupation_pct__moe90

Census 90% margin of error for production_transport_material_moving_occupation_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

agriculture_forestry_fishing_mining_industry_pct__moe90

Census 90% margin of error for agriculture_forestry_fishing_mining_industry_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

manufacturing_industry_pct__moe90

Census 90% margin of error for manufacturing_industry_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

professional_scientific_management_admin_waste_industry_pct__moe90

Census 90% margin of error for professional_scientific_management_admin_waste_industry_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

self_employed_nonincorporated_pct__moe90

Census 90% margin of error for self_employed_nonincorporated_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

work_from_home_pct__moe90

Census 90% margin of error for work_from_home_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

mean_commute_minutes__moe90

Census 90% margin of error for mean_commute_minutes. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. minutes.

vacant_housing_pct__moe90

Census 90% margin of error for vacant_housing_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

mobile_home_pct__moe90

Census 90% margin of error for mobile_home_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

renter_occupied_pct__moe90

Census 90% margin of error for renter_occupied_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

no_vehicle_pct__moe90

Census 90% margin of error for no_vehicle_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

severe_crowding_pct__moe90

Census 90% margin of error for severe_crowding_pct. Controlled MOE sentinel -555555555 is represented by zero with its companion flag. percentage points.

log_median_household_income_2024__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

bachelors_or_higher_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

disability_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

foreign_born_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

limited_english_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

broadband_subscription_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

under_18_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

age_65_plus_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

hispanic_latino_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

black_non_hispanic_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

labor_force_participation_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

unemployment_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

management_business_science_arts_occupation_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

service_occupation_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

natural_resources_construction_maintenance_occupation_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

production_transport_material_moving_occupation_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

agriculture_forestry_fishing_mining_industry_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

manufacturing_industry_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

professional_scientific_management_admin_waste_industry_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

self_employed_nonincorporated_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

work_from_home_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

mean_commute_minutes__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

vacant_housing_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

mobile_home_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

renter_occupied_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

no_vehicle_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

severe_crowding_pct__moe90_controlled

TRUE when the corresponding Census MOE was a controlled-estimate sentinel (-555555555) and was stored as zero; FALSE otherwise. TRUE/FALSE.

Details

This is a single cross-sectional table with one row per county. The 2024 ACS five-year product contains Census Bureau period estimates based on survey data collected during 2020–2024. The analysis uses these published estimates directly: separate annual observations are neither stacked nor arithmetically averaged. The 2024 suffix in the retained income column names identifies the ACS product and the inflation-adjustment year, not a single-year observation. The legacy dataset name acs2024_counties remains available for compatibility.

The domain is the contiguous 48 states and the District of Columbia. Of 3,109 eligible geographic records, De Baca County, New Mexico (35011), lacks a median household income estimate, and Loving County, Texas (48301), lacks a mean commute estimate. These two records were excluded under the study's complete-case estimate policy. Alaska, Hawaii and territories are outside the domain. No estimate is imputed, winsorized or standardized in this data object.

The response is the natural logarithm of income in 2024 inflation-adjusted dollars. Predictors remain in their original units. Percentage estimates use the populations stated in the Census labels; they do not all share the same denominator. County associations do not identify individual-level or causal effects.

A Census controlled-estimate MOE sentinel (-555555555) is stored as zero and marked by a logical companion column. Other unavailable MOEs were treated as missing without automatic sample exclusion; this released table contains no missing values. In particular, log_median_household_income_2024__moe90 retains the original dollar-scale income MOE. It is not an MOE on the log scale and must not be used as one.

The spatial folds use projected representative points, seed 20260907 and 100 k-means starts. Coordinates are metres in EPSG:5070 and are not geographic longitude/latitude. Polygon geometry and the common diagnostic graph are provided in the separate reproduction bundle, not in this data frame.

The machine-readable 91-column dictionary and provenance record are installed under system.file("extdata", package = "gwrs"). Preparation code and the public source snapshot are included in the repository's reproduction bundle.

Source

U.S. Census Bureau, 2020–2024 American Community Survey five-year Data Profiles, downloaded 7 September 2026: https://api.census.gov/data/2024/acs/acs5/profile.html. County and state cartographic boundaries: https://www.census.gov/geographies/mapping-files/time-series/geo/cartographic-boundary.html.

References

U.S. Census Bureau. 2020–2024 American Community Survey five-year Data Profiles.

Yuzbasi, B. (2026). Nonconvex Geographically Weighted Regression for Local Variable Selection. Manuscript.

For work using this prepared dataset, please acknowledge the Census source, the accompanying paper and gwrs. Use citation("gwrs") for package citation information.

Examples

data(acs2020_2024_counties)
dim(acs2020_2024_counties)
head(acs2020_2024_counties[, c("fips", "county_name",
                         "median_household_income_2024", "spatial_fold")])
dictionary <- read.csv(system.file("extdata", "acs2020_2024_counties_dictionary.csv",
                                   package = "gwrs"))
head(dictionary)