mcp-statistical-analysis

Survival analysis on clinical datasets supports Kaplan-Meier curves, log-rank tests, and Cox proportional hazards regression. It processes CSV inputs to estimate treatment effects, generating hazard ratios, confidence intervals, p-values, and summary plots.

Propensity score matching estimates treatment effects in observational studies by calculating propensity scores, applying matching or IPTW, and computing ATE/ATT. It includes covariate balance assessment to ensure valid treatment effect estimation from CSV data.

ROC analysis evaluates diagnostic test performance by calculating AUC values, performing calibration checks, and comparing metrics across models. It processes clinical datasets to measure classification accuracy and diagnostic performance.

Power and sample size calculations inform clinical study design planning by determining feasibility. It evaluates statistical power requirements to ensure adequate sample sizes for detecting significant effects in clinical research scenarios.

The statistical analysis toolkit operates with no external dependencies. It runs end-to-end advanced statistical analyses including survival analysis, propensity scoring, ROC evaluation, and power calculations entirely on CSV inputs.

Cox proportional hazards regression generates hazard ratios, confidence intervals, and p-values from clinical datasets. It produces summary plots and statistical outputs to support treatment effect estimation in survival comparisons.