summary.SumStat: Summarize a SumStat object.

View source: R/summary_SumStat.R

summary.SumStatR Documentation

Summarize a SumStat object.

Description

summary.SumStat is used to summarize results obtained from function SumStat. The output includes effective sample sizes and tables for balance statistics.

Usage

## S3 method for class 'SumStat'
summary(object, weighted.var = TRUE, metric = "ASD", ...)

Arguments

object

a SumStat object obtained with the SumStat function.

weighted.var

logical. Indicate whether the propensity score weighted variance should be used in calculating the balance metrics. Default is TRUE.

metric

a chatacter indicating the type of balance metrics. "ASD" refers to the pairwise absolute standardized difference and "PSD" refers to the population standardized difference. Default is "ASD".

...

further arguments passed to or from other methods.

Details

For metric, the two options "ASD" and "PSD" are defined in Li and Li (2019) for the general family of balancing weights. Similar definitions are also given in McCaffrey et al. (2013) for inverse probability weighting. weighted.var specifies whether weighted or unweighted variance should be used in calculating ASD or PSD. An example of weighted variance with two treatment groups is given in Austin and Stuart (2015). For more than two treatment groups, the maximum of ASD (across all pairs of treatments) and maximum of PSD (across all treatments) are calcualted, as explained in Li and Li (2019).

Value

A list of tables containing effective sample sizes and balance statistics on covariates for specified propensity score weighting schemes.

effective.sample.size

a table of effective sample sizes. This serves as a conservative measure to characterize the variance inflation or precision loss due to weighting, see Li and Li (2019).

unweighted

A table summarizing mean, variance by treatment groups, and standardized mean difference.

IPW

If "IPW" is specified, this is a data table summarizing mean, variance by treatment groups, and standardized mean difference under inverse probability of treatment weighting.

treated

If "treated" is specified, this is a data table summarizing mean, variance by treatment groups, and standardized mean difference under the ATT weights.

overlap

If "overlap" is specified, this is a data table summarizing mean, variance by treatment groups, and standardized mean difference under the (generalized) overlap weights.

matching

If "matching" is specified, this is a data table summarizing mean, variance by treatment groups, and standardized mean difference under the (generalized) matching weights.

entropy

If "entropy" is specified, this is a data table summarizing mean, variance by treatment groups, and standardized mean difference under the (generalized) entropy weights.

References

Crump, R. K., Hotz, V. J., Imbens, G. W., Mitnik, O. A. (2009). Dealing with limited overlap in estimation of average treatment effects. Biometrika, 96(1), 187-199.

Li, L., Greene, T. (2013). A weighting analogue to pair matching in propensity score analysis. The International Journal of Biostatistics, 9(2), 215-234.

Austin, P.C. and Stuart, E.A. (2015). Moving towards best practice when using inverse probability of treatment weighting (IPTW) using the propensity score to estimate causal treatment effects in observational studies. Statistics in Medicine, 34(28), 3661-3679.

Li, F., Li, F. (2019). Propensity score weighting for causal inference with multiple treatments. The Annals of Applied Statistics, 13(4), 2389-2415.

Zhou, Y., Matsouaka, R. A., Thomas, L. (2020). Propensity score weighting under limited overlap and model misspecification. Statistical Methods in Medical Research (Online)

Examples

## For examples, run: example(SumStat).

PSweight documentation built on May 29, 2024, 3:55 a.m.