These functions summarize the weights resulting from a call to optweight(), optweightMV(), or optweight.svy(). summary() produces summary statistics on the distribution of weights, including their range and variability, and the effective sample size of the weighted sample (computed using the formula in McCaffrey, et al., 2004). plot() creates a histogram of the weights.
# S3 method for optweight
summary(object, top = 5L, ignore.s.weights = FALSE, weight.range = TRUE, ...)# S3 method for optweightMV
summary(object, top = 5L, ignore.s.weights = FALSE, weight.range = TRUE, ...)
# S3 method for optweight.svy
summary(object, top = 5L, ignore.s.weights = FALSE, weight.range = TRUE, ...)
# S3 method for summary.optweight
plot(x, ...)
For point treatments (i.e., optweight objects), summary() returns a summary.optweight object with the following
elements:
The range (minimum and maximum) weight for each treatment group.
The units with the greatest weights in each treatment group; how many are included is determined by top.
The square root of the \(L_2\) norm of the estimated weights from the base weights, weighted by the sampling weights (if any): \(\sqrt{\frac{1}{n}\sum_i {s_i(w_i - b_i)^2}}\)
The \(L_1\) norm of the estimated weights from the base weights, weighted by the sampling weights (if any): \(\frac{1}{n}\sum_i {s_i \vert w_i - b_i \vert}\)
The \(L_\infty\) norm (maximum absolute deviation) of the estimated weights from the base weights: \(\max_i {\vert w_i - b_i \vert}\)
The relative entropy between the estimated weights and the base weights, weighted by the sampling weights (if any): \(\frac{1}{n}\sum_i {s_i w_i \log\left(\frac{w_i}{b_i}\right)}\). Only computed if all weights are positive.
The number of units with a weight equal to 0.
The effective sample size for each treatment group before and after weighting.
For multivariate treatments (i.e., optweightMV objects), a list of the above elements for each treatment.
For optweight.svy objects, the above object but with no treatment group divisions.
plot() returns a ggplot object with a histogram displaying the
distribution of the estimated weights. If the estimand is the ATT or ATC,
only the weights for the non-focal group(s) will be displayed (since the
weights for the focal group are all 1). A dotted line is displayed at the
mean of the weights (the mean of the base weights, or 1 if not supplied).
an optweight, optweightMV, or optweight.svy object; the output of a call to optweight(), optweightMV(), or optweight.svy().
integer; how many of the largest and smallest weights to display. Default
is 5. Ignored when weight.range = FALSE.
logical; whether to ignore sampling weights when computing the weight summary. Default is FALSE`.
logical; whether to display statistics about the range of weights and the highest and lowest weights for each group. Default is TRUE.
Additional arguments. For plot(), additional arguments passed to graphics::hist() to determine the number of bins, though ggplot2::geom_histogram() from ggplot2 is actually used to create the plot.
a summary.optweight, summary.optweightMV, or summary.optweight.svy object; the output of a call to summary.optweight(), summary.optweightMV(), or ()summary.optweight.svy.
McCaffrey, D. F., Ridgeway, G., & Morral, A. R. (2004). Propensity Score Estimation With Boosted Regression for Evaluating Causal Effects in Observational Studies. Psychological Methods, 9(4), 403–425. tools:::Rd_expr_doi("10.1037/1082-989X.9.4.403")
plot.optweight() for plotting the values of the dual variables.
if (FALSE) { # rlang::is_installed("cobalt")
library("cobalt")
data("lalonde", package = "cobalt")
#Balancing covariates between treatment groups (binary)
(ow1 <- optweight(treat ~ age + educ + married +
nodegree + re74, data = lalonde,
tols = .001,
estimand = "ATT"))
(s <- summary(ow1))
plot(s, breaks = 12)
}
Run the code above in your browser using DataLab