RDSmoothnessBound: Lower bound on smoothness constant M in sharp RD designs

In kolesarm/RDHonest: Honest Inference in Regression Discontinuity Designs

Lower bound on smoothness constant M in sharp RD designs

Description

Estimate a lower bound on the smoothness constant M and provide a lower confidence interval for it, using method described in supplement to Kolesár and Rothe (2018).

Usage

RDSmoothnessBound(
  object,
  s,
  separate = FALSE,
  multiple = TRUE,
  alpha = 0.05,
  sclass = "H"
)

Arguments

object	An object of class "RDResults", typically a result of a call to RDHonest.
s	Number of support points that curvature estimates should average over.
separate	If TRUE, report estimates separately for data above and below cutoff. If FALSE, report pooled estimates.
multiple	If TRUE, use multiple curvature estimates. If FALSE, only use a single curvature estimate using observations closest to the cutoff.
alpha	determines confidence level 1-alpha.
sclass	Smoothness class, either "T" for Taylor or "H" for Hölder class.

Value

Returns a data frame wit the following columns:

estimate

Point estimate for lower bounds for M.

conf.low

Lower endpoint for a one-sided confidence interval for M

The data frame has a single row if separate==FALSE; otherwise it has two rows, corresponding to smoothness bound estimates and confidence intervals below and above the cutoff, respectively.

References

Michal Kolesár and Christoph Rothe. Inference in regression discontinuity designs with a discrete running variable. American Economic Review, 108(8):2277—-2304, August 2018. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1257/aer.20160945")}

Examples

## Subset data to increase speed
r <- RDHonest(log(earnings)~yearat14, data=cghs,
              subset=abs(yearat14-1947)<10,
              cutoff=1947, M=0.04, h=3)
RDSmoothnessBound(r, s=2)

kolesarm/RDHonest documentation built on April 14, 2024, 3:27 a.m.