Information from the 2010 US Census

1 | ```
data("CENSUS")
``` |

A data frame with 3534 observations on the following 39 variables.

`ResponseRate`

a numeric vector, 0-100 representing the percentage of households in a block group that mailed in the form

`Area`

a numeric vector, land area in square miles

`Urban`

a numeric vector, percentage of block group in Urbanized area (50000 or greater)

`Suburban`

a numeric vector, percentage of block group in an Urban Cluster area (2500 to 49999)

`Rural`

a numeric vector, percentage of block group in an Urban Cluster area (2500 to 49999)

`Male`

a numeric vector, percentage of males

`AgeLess5`

a numeric vector, percentage of individuals aged less than 5 years old

`Age5to17`

a numeric vector

`Age18to24`

a numeric vector

`Age25to44`

a numeric vector

`Age45to64`

a numeric vector

`Age65plus`

a numeric vector

`Hispanics`

a numeric vector, percentage of individuals who identify as Hispanic

`Whites`

a numeric vector, percentage of individuals who identify as white (alone)

`Blacks`

a numeric vector

`NativeAmericans`

a numeric vector

`Asians`

a numeric vector

`Hawaiians`

a numeric vector

`Other`

a numeric vector, percentage of individuals who identify as another ethnicity

`RelatedHH`

a numeric vector, percentage of households where at least 2 members are related by birth, marriage, or adoption; same-sex couple households with no relatives of the householder present are not included

`MarriedHH`

a numeric vector, percentage of households in which the householder and his or her spouse are listed as members of the same household; does not include same-sex married couples

`NoSpouseHH`

a numeric vector, percentage of households with no spousal relationship present

`FemaleHH`

a numeric vector, percentage of households with a female householder and no husband of householder present

`AloneHH`

a numeric vector, percentage of households where householder is living alone

`WithKidHH`

a numeric vector, percentage of households which have at least one person under the age of 18

`MedianHHIncomeBlock`

a numeric vector, median income of households in the block group (from American Community Survey)

`MedianHHIncomeCity`

a numeric vector, median income of households in the tract

`OccupiedUnits`

a numeric vector, percentage of housing units that are occupied

`RentingHH`

a numeric vector, percentage of housing units occupied by renters

`HomeownerHH`

a numeric vector, percentage of housing units occupied by the owner

`MobileHomeUnits`

a numeric vector, percentage of housing units that are mobile homes (from American Community Survey)

`CrowdedUnits`

a numeric vector, percentage of housing units with more than 1 person per room on average

`NoPhoneUnits`

a numeric vector, percentage of housing units without a landline

`NoPlumbingUnits`

a numeric vector, percentage of housing units without active plumbing

`NewUnits`

a numeric vector, percentage of housing units constructed in 2010 or later

`Population`

a numeric vector, number of people in the block group

`NumHH`

a numeric vector, number of households in the block group

`NumUnits`

a numeric vector, number of housing units in the block group

`logMedianHouseValue`

a numeric vector, the logarithm of the median home value in the block group

The goal is to predict `ResponseRate`

from the other predictors. `ResponseRate`

is the percentage of households in a block group that mailed in the census forms. A block group is on average about 40 blocks, each typically bounded by streets, roads, or water. The number of block groups per county in the US is typically between about 5 and 165 with a median of about 20.

See http://www.census.gov/research/data/planning_database/2014/docs/PDB_Block_2014-11-20a.pdf for variable definitions.

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

All documentation is copyright its authors; we didn't write any of that.