What is the primary use of the stc-methodology skill?

It is used to conduct Simulated Treatment Comparisons (STC), which are regression-based methods for adjusting population differences when performing indirect treatment comparisons in clinical research.

Does this skill follow official regulatory guidelines?

Yes, it is strictly aligned with the NICE DSU Technical Support Document 18 (TSD 18) for population-adjusted indirect comparisons.

Can this skill help with Bayesian statistical modeling?

Yes, it provides specific guidance on Bayesian STC implementation, including prior selection for treatment effects, covariate effects, and interactions.

When should I choose STC over MAIC?

STC is preferred when you have high confidence in your outcome model specification, wish to use continuous covariates naturally, or when MAIC results in a very low Effective Sample Size (ESS).

STC Methodology for Biostatistics

Name: STC Methodology for Biostatistics
Author: choxos

bychoxos

数据科学与机器学习

Guides the implementation and review of Simulated Treatment Comparisons (STC) using NICE DSU TSD 18 compliant methodologies.

关于

The stc-methodology skill provides deep domain expertise for conducting population-adjusted indirect treatment comparisons (ITC). It enables Claude to assist with complex outcome regression modeling, the selection of clinical and statistical effect modifiers, and the technical nuances of covariate centering. Designed for biostatisticians and health economics researchers, this skill ensures that STC analyses—whether frequentist or Bayesian—are performed with the rigor required by health technology assessment (HTA) bodies like NICE, offering a clear framework for choosing between STC and MAIC approaches.

主要功能

0 GitHub stars
NICE DSU TSD 18 compliant methodological guidance
Comprehensive comparison framework between STC and MAIC
Standardized reporting checklists for results and methods
Step-by-step guidance for Bayesian STC and prior selection
Automated strategies for effect modifier selection and centering

使用场景

Conducting anchored or unanchored Simulated Treatment Comparisons
Reviewing biostatistical code and results for HTA submissions
Selecting and justifying effect modifiers based on IPD and AgD data

关于

主要功能

0 GitHub stars
NICE DSU TSD 18 compliant methodological guidance
Comprehensive comparison framework between STC and MAIC
Standardized reporting checklists for results and methods
Step-by-step guidance for Bayesian STC and prior selection
Automated strategies for effect modifier selection and centering

使用场景

Conducting anchored or unanchored Simulated Treatment Comparisons
Reviewing biostatistical code and results for HTA submissions
Selecting and justifying effect modifiers based on IPD and AgD data