plot.matched.set: Plot the distribution of the sizes of matched sets.

In PanelMatch: Matching Methods for Causal Inference with Time-Series Cross-Sectional Data

Plot the distribution of the sizes of matched sets.

Description

A plot method for creating a histogram of the distribution of the sizes of matched sets. This method accepts all standard optional hist arguments via the ... argument. By default, empty matched sets (treated units that could not be matched with any control units) are noted as a vertical bar at x = 0 and not included in the regular histogram. See the include.empty.sets argument for more information about this.

Usage

## S3 method for class 'matched.set'
plot(
  x,
  ...,
  border = NA,
  col = "grey",
  ylab = "Frequency of Size",
  xlab = "Matched Set Size",
  lwd = NULL,
  main = "Distribution of Matched Set Sizes",
  freq = TRUE,
  include.empty.sets = FALSE
)

Arguments

x	a matched.set object
...	optional arguments to be passed to hist()
border	default is NA. This is the same argument as the standard argument for hist()
col	default is "grey". This is the same argument as the standard argument for hist()
ylab	default is "Frequency of Size". This is the same argument as the standard argument for hist()
xlab	default is "Matched Set Size". This is the same argument as the standard argument for hist()
lwd	default is NULL. This is the same argument as the standard argument for hist()
main	default is "Distribution of Matched Set Sizes". This is the same argument as the standard argument for hist
freq	default is TRUE. See freq argument in hist() function for more.
include.empty.sets	logical value indicating whether or not empty sets should be included in the histogram. default is FALSE. If FALSE, then empty sets will be noted as a separate vertical bar at x = 0. If TRUE, empty sets will be included as normal sets.

Examples

dem.sub <- dem[dem[, "wbcode2"] <= 100, ]
# create subset of data for simplicity
PM.results <- PanelMatch(lag = 4, time.id = "year", unit.id = "wbcode2",
                         treatment = "dem", refinement.method = "ps.match",
                         data = dem, match.missing = TRUE,
                         covs.formula = ~ I(lag(tradewb, 1:4)) + I(lag(y, 1:4)),
                         size.match = 5, qoi = "att",
                         outcome.var = "y", lead = 0:4, forbid.treatment.reversal = FALSE)
plot(PM.results$att)
plot(PM.results$att, include.empty.sets = TRUE)

PanelMatch documentation built on June 22, 2024, 10:32 a.m.