Function reference • WeightIt

Estimate weights

weightit(): Estimate Balancing Weights

weightitMSM(): Generate Balancing Weights for Longitudinal Treatments

summary(<weightit>) plot(<summary.weightit>) summary(<weightitMSM>) plot(<summary.weightitMSM>): Print and Summarize Output

Specific estimation methods

method_bart: Propensity Score Weighting Using BART

method_cbps: Covariate Balancing Propensity Score Weighting

method_ebal: Entropy Balancing

method_energy: Energy Balancing

method_gbm: Propensity Score Weighting Using Generalized Boosted Models

method_glm: Propensity Score Weighting Using Generalized Linear Models

method_ipt: Inverse Probability Tilting

method_npcbps: Nonparametric Covariate Balancing Propensity Score Weighting

method_optweight method_sbw: Optimization-Based Weighting

method_super: Propensity Score Weighting Using SuperLearner

method_user: User-Defined Functions for Estimating Weights

Estimate treatment effects

glm_weightit() lm_weightit() summary(<glm_weightit>): Fitting Weighted Generalized Linear Models

Modify weights

trim(): Trim (Winsorize) Large Weights

calibrate(): Calibrate Propensity Score Weights

sbps(): Subgroup Balancing Propensity Score

Other functions

get_w_from_ps(): Compute weights from propensity scores

ESS(): Compute effective sample size of weighted sample

weightit.fit(): Generate Balancing Weights with Minimal Input Processing

as.weightit() as.weightitMSM(): Create a weightit object manually

make_full_rank(): Make a design matrix full rank

Datasets

msmdata: Simulated data for a 3 time point sequential study