Package {sdc.redistribute}

Title: Redistribute Values Between Geographic Areas
Version: 0.1.0
Description: Estimate attribute values for one set of polygons from values measured on a different, misaligned set. Provides area-weighted areal interpolation and a dasymetric method that distributes values across a point layer (such as parcel centroids). Count (extensive) measures are total-preserving; rate (intensive) measures use area-weighted means.
License: MIT + file LICENSE
Encoding: UTF-8
Language: en-US
Depends: R (≥ 4.1)
Imports: sf
Suggests: testthat (≥ 3.0.0), knitr, rmarkdown, areal, spelling, covr
Config/testthat/edition: 3
RoxygenNote: 7.3.2
URL: https://dads2busy.github.io/sdc.redistribute/, https://github.com/dads2busy/sdc.redistribute
BugReports: https://github.com/dads2busy/sdc.redistribute/issues
VignetteBuilder: knitr
LazyData: true
NeedsCompilation: no
Packaged: 2026-06-10 17:46:32 UTC; ads7fg
Author: Aaron Schroeder ORCID iD [aut, cre]
Maintainer: Aaron Schroeder <ads7fg@virginia.edu>
Repository: CRAN
Date/Publication: 2026-06-18 13:30:02 UTC

sdc.redistribute: Redistribute Values Between Geographic Areas

Description

Estimate attribute values for one set of polygons from values measured on a different, misaligned set. Provides area-weighted areal interpolation and a dasymetric method that distributes values across a point layer (such as parcel centroids). Count (extensive) measures are total-preserving; rate (intensive) measures use area-weighted means.

Author(s)

Maintainer: Aaron Schroeder ads7fg@virginia.edu (ORCID)

See Also

Useful links:

Area-weighted redistribution between polygon layers

Description

Area-weighted redistribution between polygon layers

Usage

redistribute_direct(
  source,
  target,
  extensive = NULL,
  intensive = NULL,
  preserve_totals = TRUE,
  suffix = NULL
)

Arguments

source

An sf polygon layer carrying the values to redistribute.

target

An sf polygon layer to estimate values for.

extensive

Character vector of count column names in source to redistribute as totals (area-share weighted, optionally rescaled to preserve the source total).

intensive

Character vector of rate/density column names in source to redistribute as area-weighted means.

preserve_totals

Logical; if TRUE (default) extensive results are rescaled so each target column sums to the source total.

suffix

Optional string appended to each new column name.

Details

Extensive measures (counts) are redistributed by each intersection's share of the source polygon area and, when preserve_totals = TRUE, rescaled so the target totals match the source totals. Intensive measures (rates/densities) are area-weighted means: the sum of each source value times the intersection's share of the target polygon area (the standard areal-weighting intensive estimator). This equals a true area-weighted mean when the target is fully covered by the source and treats any uncovered part of a target as contributing zero. NA source values are omitted from the weighted sums. Targets that no source polygon covers receive 0 for extensive measures and NA for intensive measures. If target already has a column named like a redistributed measure, it is overwritten; pass suffix to keep both.

Value

The target layer (an sf object) with one new column per redistributed measure.

Examples

src <- sf::st_sf(pop = 100, geometry = sf::st_sfc(
  sf::st_polygon(list(rbind(c(0,0), c(2,0), c(2,2), c(0,2), c(0,0)))),
  crs = 3857))
tgt <- sf::st_sf(id = c("A", "B"), geometry = sf::st_sfc(
  sf::st_polygon(list(rbind(c(0,0), c(1,0), c(1,2), c(0,2), c(0,0)))),
  sf::st_polygon(list(rbind(c(1,0), c(2,0), c(2,2), c(1,2), c(1,0)))),
  crs = 3857))
redistribute_direct(src, tgt, extensive = "pop")

Dasymetric redistribution via a point layer

Description

Distributes each source value across the points (e.g. parcel centroids) that fall inside it, then reaggregates the point-level values to target polygons. With weights = NULL the value is split evenly across points; otherwise it is split in proportion to a points column (the extension point for household-size or unit-count weighting).

Usage

redistribute_parcels(
  source,
  target,
  points,
  extensive = NULL,
  weights = NULL,
  suffix = NULL
)

Arguments

source

An sf polygon layer carrying the values to redistribute.

target

An sf polygon layer to estimate values for.

points

An sf point layer (e.g. parcel centroids).

extensive

Character vector of count column names in source.

weights

Optional name of a numeric column in points to weight by.

suffix

Optional string appended to each new column name.

Details

Each source value is split across the points inside that source polygon in proportion to weights (equally when weights = NULL), then summed within each target polygon. A source polygon that contains no points contributes nothing to any target (its value cannot be placed). If the total weight of a source's points is zero, that source likewise contributes nothing. If target already has a column named like a redistributed measure, it is overwritten; pass suffix to keep both.

Value

The target layer (an sf object) with one new column per measure.

Examples

src <- sf::st_sf(pop = 100, geometry = sf::st_sfc(
  sf::st_polygon(list(rbind(c(0,0), c(2,0), c(2,2), c(0,2), c(0,0)))),
  crs = 3857))
tgt <- sf::st_sf(id = c("A", "B"), geometry = sf::st_sfc(
  sf::st_polygon(list(rbind(c(0,0), c(1,0), c(1,2), c(0,2), c(0,0)))),
  sf::st_polygon(list(rbind(c(1,0), c(2,0), c(2,2), c(1,2), c(1,0)))),
  crs = 3857))
pts <- sf::st_sf(geometry = sf::st_sfc(
  sf::st_point(c(0.5, 1)), sf::st_point(c(1.5, 1)), crs = 3857))
redistribute_parcels(src, tgt, pts, extensive = "pop")

Synthetic example geographies

Description

A small, self-contained set of sf layers used in examples and vignettes.

Usage

sdc_example

Format

A named list with three sf elements:

source

Two source polygons (tract, pop).

target

Three target polygons (nbhd).

parcels

Parcel centroid points (units).