sample-size-basic

What This Skill Does

The sample-size-basic skill serves as an essential utility for researchers, biostatisticians, and clinical trial coordinators. It automates the often tedious process of power analysis and sample size estimation, allowing users to determine the minimum number of participants required to detect a statistically significant effect. By taking user-defined parameters such as significance level, power, and expected effect size, the tool performs the necessary statistical calculations internally to provide a clear, actionable sample size for clinical study protocols.

Installation

To integrate this skill into your OpenClaw environment, execute the following command in your terminal: clawhub install openclaw/skills/skills/aipoch-ai/sample-size-basic Ensure you have completed the prerequisite Python environment setup as defined in the requirements.txt file provided within the source repository.

Use Cases

• Grant Writing: Quickly provide robust statistical justification for study size in competitive funding applications.
• Protocol Design: Evaluate the feasibility of a clinical trial by determining if the required subject recruitment numbers are achievable within the desired timeframe.
• Educational Labs: Facilitate statistics courses by allowing students to observe how varying parameters like alpha and power influence the final sample size requirement.
• Preliminary Research: Design pilot studies with mathematically grounded estimates to optimize resources before embarking on large-scale investigations.

Example Prompts

1. "Calculate the sample size for a two-sample t-test with an alpha of 0.05, power of 0.80, and a Cohen's d effect size of 0.5."
2. "Determine the total subjects needed for a chi-square test where the baseline rate is 0.25, looking for an effect size of 0.1."
3. "I need to run a study with 90% power and 0.05 significance for a proportion test. What is the required sample size per group?"

Tips & Limitations

• Statistical Assumptions: Always review the statistical assumptions associated with the test type chosen (e.g., normality for t-tests). This tool assumes standard parametric distributions unless otherwise specified.
• Data Integrity: Ensure the effect size provided is grounded in preliminary data or literature reviews to maintain the validity of your study.
• Limitations: This is a basic estimator. For complex longitudinal data or multi-center trial designs with covariate adjustments, please consult with a professional statistician. The tool does not perform post-hoc power analysis; it is strictly for planning purposes.