An Online Meta-Level Adaptive Design Framework with Targeted Learning Inference: Applicati

A research framework and associated data for evaluating and selecting among candidate adaptive designs in clinical trials and online experiments. The work, authored by Wenxin Zhang, proposes a novel meta-level adaptive design framework and Targeted Maximum Likelihood Estimators for causal estimands. The dataset, last updated in April 2026, includes supplementary materials, code, and simulation data related to the framework's application for evaluating surrogate outcomes to accelerate treatment effect detection.

Use Cases

• Evaluating the utility of surrogate outcomes for accelerating treatment effect detection based on the framework's application example.
• Comparing candidate adaptive designs in real-time based on the proposed meta-level selection framework.
• Applying Targeted Maximum Likelihood Estimation for causal estimands in adaptive-design data without parametric assumptions.
• Simulating adaptive experiments where randomization probabilities are updated using surrogate markers.

Strengths

• Dataset is licensed under CC-BY-4.0, permitting broad reuse with attribution.
• Includes multiple file formats such as R code, CSV data, and PDF documentation, suggesting a complete research artifact.
• Last updated timestamp (2026-04-28 15:16:31) is precisely recorded.

Limitations

• Row count and specific column definitions are unknown, limiting suitability assessment for direct analysis.
• Description metadata focuses on the methodological framework; actual data content and structure require manual inspection after download.
• The 1.5 MB size suggests a small dataset, potentially limiting the scale of included simulation data.

Provenance

Source

figshare

Collection Method

Likely contains simulation data and code supporting the described research framework.

Freshness

Last updated 2026-04-28 15:16:31.