psdata_bin_retrospective_sp {PSweight} | R Documentation |
Retrospective Superpopulation Dataset for PSweight Analysis
Description
A simulated dataset representing the retrospective superpopulation (i.e. the full dataset) for propensity score weighting analysis under a retrospective design. In this design, the sampling probability is influenced by both covariates and treatment assignment.
Usage
data(psdata_bin_retrospective_sp)
Format
A data frame with 1500 rows and 10 variables:
- Y
Outcome variable.
- trt
Binary treatment indicator (coded as 1 and 2).
- cov1, cov2, cov3, cov4, cov5, cov6
Pre-treatment covariates.
- sampling_prob
Sampling probability computed as a function of covariates and treatment (e.g., with an additional term depending on
trt
).- survey_weight
Survey weight computed as the inverse of
sampling_prob
.- sample_indicator
Indicator variable (0/1) denoting whether an observation was selected into the sample.
Details
In the retrospective design, the sampling probability is determined by both covariates and treatment assignment. This dataset represents the full superpopulation in which the sampling mechanism is retrospective.
Examples
data(psdata_bin_retrospective_sp)
head(psdata_bin_retrospective_sp)