- Home
- Skills
- Research & Analysis
- sample-size-power-analysis-skill
Sample Size Power Analysis Skill
Calculate and justify statistically significant sample sizes for surveys, experiments, and complex regressions.
Free
Works with the AI Agents you already use
sample-size-power-analysis-skill
Example session with this skill installed
Use $sample-size-power-analysis to calculate the required N for a multiple regression with 6 predictors, alpha 0.05, and power 0.80, then write the justification paragraph.
- Read your context and instructions
- Compiled the sample-size-power-analysis-
I have calculated the required sample size for your multiple regression model and drafted a formal justification paragraph based on established statistical standards.
Power Analysis Report
| Parameter | Value | Note |
|---|---|---|
| Test Family | Multiple Regression (Fixed Model) | |
| Number of Predictors | 6 | |
| Effect Size ($f^2$) | 0.15 | Medium effect (Cohen) |
| Alpha ($\alpha$) | 0.05 | Type I error rate |
| Power ($1-\beta$) | 0.80 | Standard threshold |
| Required N | 98 | Based on Green (1991) / G*Power |
Sample Size Justification
A power analysis was conducted to determine the minimum sample size required for a multiple regression analysis with 6 predictors. Following the heuristic recommendations of Green (1991), which suggests a minimum N > 50 + 8k (where k is the number of predictors) for testing individual predictors, a sample of 98 participants is required. Specifically, assuming a medium effect size ($f^2$ = 0.15), an alpha of 0.05, and a power of 0.80, the calculation indicates that 98 participants are necessary to reliably detect significant effects. To account for a projected 10% attrition rate, the study aims to recruit at least 110 participants.
Next steps
- Install the
requirements.txtdependencies to run the localsample_size.pyscript for variations. - Adjust the effect size parameter if your pilot data suggests a smaller anticipated effect.
- Include the justification paragraph in the "Participants" or "Methodology" section of your manuscript.
Connects securely to your tools. The creator never sees your data.
About this skill
Calculating sample size manually leads to underpowered studies and rejected papers. This skill provides the mathematical rigor needed to justify participant counts for surveys and experiments using established statistical frameworks.
What it does
- Power Analysis determines the relationship between effect size, alpha, power, and sample size to solve for the missing variable.
- Multi-Method Support covers t-tests, ANOVA, correlation, chi-square, and multiple regression using Green (1991) standards.
- Complex Modeling calculates requirements for EFA/CFA via Comrey and Lee, as well as SEM and mediation analysis.
- Survey Sampling applies Cochran and Krejcie & Morgan formulas for descriptive study population estimates.
- Justification Writing generates formal methodology paragraphs with authoritative citations for peer-reviewed journals.
- Sensitivity Analysis performs post-hoc checks to identify the smallest effect size a study can reliably detect.
How it works
- Identify Analysis Type by specifying your study design like a two-group experiment or a 5-predictor regression.
- Define Parameters by providing known values for power, significance levels, or expected effect sizes from literature.
- Execute Calculation using the validated Python script to generate precise N requirements.
- Draft Justification using templates to produce a report ready for an Ethics Committee or a manuscript.
Frameworks & tools
The skill includes a Python-based command-line calculator validated against G*Power benchmarks. It utilizes methodology from Cochran, Green (1991), Comrey & Lee, and Fritz & MacKinnon.
Why this beats prompting it yourself
LLMs often hallucinate statistical formulas or confuse sample size conventions between different test families. This skill uses a validated Python engine and a library of 11 methodology documents to ensure your N justification is mathematically sound and citeable.
Use cases
- Determine the responses needed for a descriptive survey of a specific population.
- Calculate sample size for a multiple regression model with a set number of predictors.
- Write a formal sample size justification for a grant proposal or IRB submission.
- Perform a sensitivity analysis to see if a completed study was sufficiently powered.
Known limitations
The Python calculator requires a local environment with requirements.txt installed. Users must have a basic understanding of their intended statistical test family to select the right mode.
Requires Python environment for calculator script. User must specify the statistical test family (e.g., ANOVA, Regression) for accurate results.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
2 uses
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 24 days ago
- Free with an Agensi account
Requires