Augmented inverse probability weighting
Set up, run, and review this analysis in Lifescio.
Supported analysis
The app fits logistic treatment propensity and separate outcome models by treatment group: linear for continuous outcomes and logistic for binary outcomes. Predicted outcomes are augmented by inverse-probability-weighted residuals. Bootstrap intervals refit these models.
Supported scope: This is a parametric ATE workflow, without machine-learning cross-fitting. Check overlap and effective sample size. Both nuisance models can be wrong, and bootstrap intervals can be unreliable in small or separated samples.
Prepare data and configure the analysis
Provide treatment 0/1, outcome, and numeric baseline confounders. The workflow targets the average treatment effect. It fits a logistic propensity model and separate outcome models in the two arms: logistic models when every outcome is 0 or 1, otherwise linear regression.
Every confounder enters the models, and each arm needs more observations than its outcome-model coefficients. This implementation is parametric and does not use cross-fitting. It uses 200 bootstrap resamples internally; unlike the weighting form, this form does not expose a bootstrap-count input.
Input reference (1 fields)
Enter your data and prespecified choices. Ranges include both limits. For table fields, use cell editing, Paste data, or Import CSV / TSV. Review whether the first imported row contains headings and map the source columns before applying the import. Empty numeric cells are not treated as zero. Open file is for an exported Lifescio analysis JSON file, not a spreadsheet.
| Input | Format | Allowed range | Guidance |
|---|---|---|---|
| Treatment, outcome and confounders | Table | — | Treatment is 0/1. Continuous or binary outcome. Remaining columns are baseline numeric confounders. Columns in order: Treatment; Outcome; Age; Covariate. |
Run and review
- Give the analysis a descriptive name and review every example value. Record units, data preparation, and planning assumptions in Reproducibility & notes. For simulations, record the seed and replication or sampling settings.
- Choose Run analysis. Resolve input errors before interpreting output. In the connected app, a run uses a saved input revision; local preview runs need the page to stay open.
- Review Diagnostics for method limitations, warnings, and available numerical checks. A completed run means computation finished; it does not establish that the assumptions fit your study.
- Use the Result table selector to inspect each output. Editing inputs does not recalculate existing results: an earlier-input notice means you need to run again to obtain matching results.
Understand the outputs
Treatment effect reports the augmented mean difference, bootstrap standard error, and percentile 95% limits. The nuisance models are refitted in each bootstrap sample. Covariate balance and Overlap and weights use inverse-probability weights as diagnostics; they do not show the full augmented estimating equation.
A small effective N or large maximum weight is still relevant despite outcome augmentation. Interpret a binary-outcome estimate as an absolute risk difference. The supported model and bootstrap choices should accompany any exported result.
Troubleshooting and common mistakes
A near-separation error concerns the propensity model. Too few observations per arm concerns the outcome models. Check redundant covariates, sparse treatment groups, and outcome coding before reducing a scientifically necessary adjustment set.
Many failed bootstrap fits or implausibly extreme effects warrant investigation of overlap and model support. Double robustness does not make such instability harmless. Clustered data, flexible cross-fitted learners, and longitudinal interventions need methods outside this workflow.
After correcting inputs, run again and check that the results belong to the new input snapshot. Increasing simulation draws improves numerical precision only; it does not repair invalid data or an unsuitable model.
Save, compare, and export
In the connected app, Save analysis retains the inputs in your account. Run history lets you inspect earlier runs, each with the input revision it used. In local preview, Save analysis downloads an input file instead; download results before leaving the page.
Use Result + inputs for a JSON archive containing the completed result and its inputs, Download CSV for the selected result table, PDF report for a report, and a chart's SVG button for its figure. Table displays round to three decimals; CSV and JSON exports retain calculation precision. Use those values when assessing a result near a decision boundary.
To reopen an archive, select the matching analysis method and choose Open file. Imported inputs start a new draft; a result archive can also display its retained result. It does not attach itself to an existing account analysis or recompute the result. Save or run the imported draft when you want a new account record.