synthetic_population {sociome}R Documentation

Create a synthetic population simulating US Census areas

Description

Returns a data set of synthetic individuals based on user-specified US Census areas. The age, sex, race, and ethnicity of each individual is probabilistic, based on the demographics of the areas as reported in a user-specified US Census data set.

Usage

synthetic_population(
  geography,
  state = NULL,
  county = NULL,
  geoid = NULL,
  zcta = NULL,
  year,
  dataset = c("acs5", "acs3", "acs1", "decennial"),
  geometry = FALSE,
  cache_tables = TRUE,
  max_age = 115,
  rate = 0.25,
  key = NULL,
  seed = NULL,
  ...
)

Arguments

geography

A character string denoting the level of US census geography at which you want to create a synthetic population. Required.

state

A character string specifying states whose population you want to synthesize. Defaults to NULL. Can contain full state names, two-letter state abbreviations, or a two-digit FIPS code/GEOID (must be a vector of strings, so use quotation marks and leading zeros if necessary). Must be left as NULL if using the geoid or zcta parameter.

county

A vector of character strings specifying the counties whose population you want to synthesize. Defaults to NULL. If not NULL, the state parameter must have a length of 1. County names and three-digit FIPS codes are accepted (must contain strings, so use quotation marks and leading zeros if necessary). Must be blank if using the geoid parameter.

geoid

A character vector of GEOIDs (use quotation marks and leading zeros). Defaults to NULL. Must be blank if state, county, or zcta is used. Can contain different levels of geography (see details).

zcta

A character vector of ZCTAs or the leading digit(s) of ZCTAs (use quotation marks and leading zeros). Defaults to NULL. Must be blank if state, county, or geoid is used.

Strings under 5 digits long will yield all ZCTAs that begin with those digits.

Requires that geography = "zcta". If geography = "zcta" and zcta = NULL, all ZCTAs in the US will be used.

year, dataset

Specifies the US Census data set on which to base the demographic profile of your synthetic population.

year must be a single integer specifying the year of US Census data to use.The data set used to calculate ADIs and ADI-3s.

dataset must be one of c("acs5", "acs3", "acs1", "decennial"), denoting the 5-, 3-, and 1-year ACS along with the decennial census. Defaults to "acs5".

When dataset = "decennial", year must be in c(1990, 2000, 2010).

Important: data are not always available depending on the level of geography and data set chosen. See https://www.census.gov/programs-surveys/acs/guidance/estimates.html.

geometry

Logical value indicating whether or not shapefile data should be included in the result, making the result an sf object instead of a plain tibble. Defaults to FALSE.

The shapefile data that is returned is somewhat customizable by passing certain arguments along to the tidycensus functions via ....

cache_tables

The plural version of the cache_table argument in tidycensus::get_acs() or tidycensus::get_decennial(). (get_adi() calls the necessary tidycensus function many times in order to return ADIs and ADI-3s, so many tables are cached if TRUE). Defaults to TRUE.

max_age

A single integer representing the largest possible age that can appear in the data set. Simulated age values exceeding this value will be top-coded to this value. Defaults to 115. See details.

rate

A single number, passed to stats::rexp() when synthesizing the ages of the highest age bracket. Defaults to 0.25. See details.

key

Your Census API key as a character string. Obtain one at http://api.census.gov/data/key_signup.html. Defaults to NULL. Not necessary if you have already loaded your key with census_api_key().

seed

Passed onto set.seed(), which is called before probabilistically synthesizing the age values with sample().

...

Additional arguments to be passed onto tidycensus::get_acs() or tidycensus::get_decennial(). These must all be named. Must not match any of the tidycensus formal arguments that sociome needs to set explicitly.

This may be found to be helpful when setting geometry = TRUE, since the tidycensus functions pass ... onto the appropriate tigris function (namely, one of tigris::states(), tigris::counties(), tigris::tracts(), tigris::block_groups(), or tigris::zctas(), according to the the value of geography). This enables the user to somewhat customize the shapefile data obtained.

Details

Returns a tibble or sf object where each row represents a synthetic person. Each person has an age, sex, race, and ethnicity. The probability of what each person's age/sex/race/ethnicity will be is equal to the proportions in their census area as reported in the user-specified US Census data set (e.g., 2010 Decennial Census or 2017 ACS 5-year estimates). The number of rows in the data set will equal the number of people living in the user-specified US Census areas, as reported in the same US Census data set.

Value

If geometry = FALSE, (the default) a tibble. If geometry = TRUE is specified, an sf.

Synthesizing ages from US Census Data

US Census data provides counts of the number of people in different age brackets of varying widths. The age_lo and age_hi columns in the output depict the age bracket of each individual in the synthetic population. There is also an age column that probabilistically generates a non-whole-number age within the age bracket. A uniform distribution (via stats::runif()) guides this age generation for all age brackets except the highest age bracket ("age 85 and over" in the extant ACS and Decennial Census data). An exponential distribution (via stats::rexp()) guides the age generation for this highest age bracket, and the user can specify rate to customize the exponential distribution that is used.

Examples

## Not run: 
# Wrapped in \dontrun{} because all these examples take >5 seconds
# and require a Census API key.

# Synthetic population for Utah, using the 2019 ACS 5-year estimates:
synthetic_population(geography = "state", state = "UT", year = 2019)

# Same, but make it so that survival past age 85 is highly unlikely
# (via rate = 10), and so that 87 is the maximum possible age
synthetic_population(
  geography = "state",
  state = "UT",
  year = 2019,
  max_age = 87,
  rate = 10
)

# Synthetic population of the Delmarva Peninsula at the census tract level,
# using 2000 Decennial Census data
synthetic_population(
  geography = "tract",
  geoid = 
    # This two-digit GEOID is the state of Delaware.
    c("10",
    
    # These five-digit GEOIDs are specific counties in Virginia and Maryland
      "51001", "51131", "24015", "24029", "24035", "24011", "24041", "24019",
      "24045", "24039", "24047"),
  year = 2000,
  dataset = "decennial"
)

## End(Not run)

[Package sociome version 2.2.5 Index]