proc_cost_boot: Bootstrap standard errors for expected procurement cost

In qdfauction: Nonparametric Quantile Density Estimation and Structural Analysis of First-Price Auctions

Bootstrap standard errors for expected procurement cost

Description

Bootstrap standard errors for expected procurement cost

Usage

proc_cost_boot(
  bids,
  r = Inf,
  v0,
  B = 499,
  method = "bernstein",
  bandwidth = "sqrt",
  family = "independence",
  resample = c("auctions", "blocks"),
  L = "auto",
  ...
)

Arguments

bids	L \times n matrix of bids (one row per auction), or a vector with n given.
r	Price ceiling(s); Inf for no ceiling.
v0	Buyer's outside option.
B	Bootstrap replications.
method	First-stage quantile density estimator, passed to proc_values.
bandwidth	First-stage bandwidth rule or numeric bandwidth. Whatever is given, the bandwidth is selected once on the full sample and held fixed in every bootstrap refit.
family	Dependence specification: "independence", "frank" or "nonparametric" (see proc_values).
resample	"auctions" (i.i.d. auction bootstrap, default) or "blocks" (moving-block bootstrap over consecutive auctions; use when the same firms bid repeatedly over time and the rows are in time order).
L	Block length for "blocks": "auto" (the rule of block_length_auto, applied with winner = "min") or an integer. L = 1 is the i.i.d. auction bootstrap.
...	Passed to fpa_values (method, bandwidth, family, theta, eta, ...). family must be "independence", "frank" or "nonparametric".

Value

List: r, estimate, se, ci90, boot, h, resample, L.

qdfauction documentation built on Nov. 10, 2026, 5:07 p.m.