Ellison-Glaeser agglomeration and Duranton-Overman K-density

EllisonGlaeser: Ellison and Glaeser (1997) gamma, raw concentration G, plant Herfindahl H and the null z-statistic, as REAT::ellison.a. CoagglomerationIndex: Ellison-Glaeser coagglomeration of a group of industries. DurantonOverman: kernel density of bilateral distances with reflection at zero, Silverman bandwidth, and local counterfactual bands from Philox redraws among sites. Region employment vectors follow the sorted region labels.

Usage

EllisonGlaeser(plant_emp, plant_region, region_emp = NULL)

CoagglomerationIndex(plant_emp, plant_industry, plant_region, region_emp)

DurantonOverman(
  coords,
  r,
  sites = NULL,
  n_sim = 0,
  bandwidth = NULL,
  level = 0.05,
  seed = 1
)

Arguments

plant_emp

Plant employment.

plant_region

Plant region labels.

region_emp

Aggregate employment by sorted region label.

plant_industry

Plant industry labels.

coords

Two-column coordinates of the industry's establishments.

r

Distances at which to evaluate the density.

sites

Candidate locations for the counterfactual.

n_sim

Number of counterfactual draws.

bandwidth

Kernel bandwidth (default Silverman's rule).

level

Two-sided band level.

seed

Philox seed.

Value

List.

References

Ellison, G. and Glaeser, E. L. (1997). Geographic concentration in U.S. manufacturing industries: a dartboard approach. Journal of Political Economy 105, 889-927.

Duranton, G. and Overman, H. G. (2005). Testing for localization using micro-geographic data. Review of Economic Studies 72, 1077-1106.

Examples

EllisonGlaeser(c(10, 20, 30, 40), c("a", "a", "b", "c"), c(100, 100, 100))$gamma
#> [1] -0.4142857
DurantonOverman(rbind(c(0, 0), c(1, 0), c(0, 1)), c(0, 1), bandwidth = 0.5)$K
#> [1] 0.1537184 0.7208127