plot.fect: Plot Method for 'fect' Objects

In xuyiqing/fect: Fixed Effects Counterfactual Estimators

Plot Method for 'fect' Objects

Description

Visualizes results from a fect estimation.

Usage

## S3 method for class 'fect'
plot(
    x,
    type = NULL,
    loo = FALSE,
    highlight = NULL,
    plot.ci = NULL,
    show.points = NULL,
    show.group = NULL,
    bound = NULL,
    vis = NULL,
    count = TRUE,
    proportion = 0.3,
    pre.periods = NULL,
    f.threshold = NULL,
    tost.threshold = NULL,
    effect.bound.ratio = FALSE,
    stats = NULL,
    stats.labs = NULL,
    raw = "none",
    main = NULL,
    xlim = NULL,
    ylim = NULL,
    xlab = NULL,
    ylab = NULL,
    xangle = NULL,
    yangle = NULL,
    xbreaks = NULL,
    ybreaks = NULL,
    xticklabels = NULL,
    yticklabels = NULL,
    gridOff = FALSE,
    legendOff = FALSE,
    legend.pos = NULL,
    legend.nrow = NULL,
    legend.labs = NULL,
    stats.pos = NULL,
    show.stats = TRUE,
    theme.bw = TRUE,
    nfactors = NULL,
    include.FE = TRUE,
    id = NULL,
    cex.main = NULL,
    cex.main.sub = NULL,
    cex.axis = NULL,
    cex.lab = NULL,
    cex.legend = NULL,
    cex.text = NULL,
    axis.adjust = FALSE,
    axis.lab = "both",
    axis.lab.gap = c(0, 0),
    shade.post = FALSE,
    start0 = FALSE,
    return.test = FALSE,
    balance = NULL,
    weight = NULL,
    line.color = NULL,
    line.width = c(1.2, 0.5),
    lcolor = NULL,
    lwidth = NULL,
    ...
)

Arguments

x	A fitted fect object.
type	Plot type: "gap", "equiv", "status", "exit", "factors", "loadings", "calendar", "box", or "counterfactual".
loo	Logical; if TRUE, use leave-one-out for equivalence tests.
highlight	Logical; if TRUE, highlight certain periods (e.g., placebo).
plot.ci	Specifies the confidence interval to be plotted. Options include: "0.9", "0.95", or "none". Default depends on the context.
show.points	Logical; if TRUE, shows point estimates on the plot.
show.group	Optional; specify a subgroup to plot.
bound	Which bounds to display in bounding/equivalence tests: "none", "min", "equiv", or "both".
vis	Controls line display for placebo/carryover tests: "connected" or "none".
count	Logical; if TRUE, shows a histogram of observation counts.
proportion	Restrict plotted time points to those with at least this fraction of the max units.
pre.periods	Specifies pre-treatment periods used for bounding.
f.threshold	F-test threshold in equivalence checks.
tost.threshold	Threshold for TOST-based checks.
effect.bound.ratio	If TRUE, shows the ratio of ATT to the minimal bound.
stats	Specifies which statistics to display: e.g., "F.p", "equiv.p".
stats.labs	Custom labels for the displayed statistics.
raw	For "counterfactual" plot: "none", "band", or "all".
main	Main plot title.
xlim	Specifies x-axis limits.
ylim	Specifies y-axis limits.
xlab	x-axis label.
ylab	y-axis label.
xangle	Angle (in degrees) for x-axis labels.
yangle	Angle (in degrees) for y-axis labels.
xbreaks	Positions of major ticks on the x-axis.
ybreaks	Positions of major ticks on the y-axis.
xticklabels	Labels for the x-axis ticks.
yticklabels	Labels for the y-axis ticks.
gridOff	Logical; if TRUE, removes grid lines.
legendOff	Logical; if TRUE, hides the legend.
legend.pos	Position of the legend.
legend.nrow	Number of rows in the legend.
legend.labs	Custom legend labels.
stats.pos	(x,y) coordinates for displaying text of test statistics.
show.stats	Logical; if TRUE, displays test statistics on the plot.
theme.bw	Logical; if TRUE, uses a black-and-white ggplot2 theme.
nfactors	Number of factors to plot when type is "factors" or "loadings".
include.FE	Logical; if TRUE, includes fixed effects as additional "factors".
id	When specified, plots only the chosen unit(s).
cex.main	Font size of the main title.
cex.main.sub	Font size of a possible subtitle.
cex.axis	Font size of axis tick labels.
cex.lab	Font size of axis labels.
cex.legend	Font size of legend text.
cex.text	Font size for text annotations.
axis.adjust	If TRUE, attempts to adjust axis labels for large data.
axis.lab	Controls axis labeling in "status" plots. Could be "both", "time", "unit", or "off".
axis.lab.gap	Gap spacing for axis labels in "status" plots.
shade.post	If TRUE, shades post-treatment periods in certain plots.
start0	If TRUE, re-indexes the first post-treatment period as 0.
return.test	If return.test=TRUE, returns test statistics along with the plot.
balance	Logical; if TRUE, uses a "balance sample" from the fect object.
weight	Logical; if TRUE, applies weighting from the fect object.
line.color	Color for main plot lines.
line.width	A numeric vector specifying line widths for different line types.
lcolor	Color for reference lines (e.g., 0 line, vertical lines).
lwidth	Line width for reference lines.
...	Additional graphical parameters passed to internal plotting routines.

Details

plot.fect generates various visualizations for objects estimated via fect. Depending on the selected type, it can show treatment-effect dynamics, equivalence test outcomes, factor/loadings for factor models, or raw vs. counterfactual trajectories.

Value

p	A ggplot2 object containing the requested plot.
test.out	If return.test=TRUE, includes relevant test statistics (F-tests, equivalence p-values, etc.).

Author(s)

Licheng Liu, Ye Wang, Yiqing Xu, Ziyi Liu

References

Xu, Y. (2017). Generalized Synthetic Control Method: Causal Inference with Interactive Fixed Effects Models. Political Analysis, 25(1), 57–76.

Examples

library(fect)
data(fect)
out.fect <- fect(Y ~ D + X1 + X2, data = simdata, index = c("id","time"), 
  method = "fe", force = "two-way", se = TRUE, parallel = TRUE, nboots = 200)
plot(out.fect, main = "Estimated ATT (FEct)", ylab = "Effect of D on Y")

xuyiqing/fect documentation built on April 12, 2025, 9:50 p.m.