Hire an AI statistician

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• The question named as describing, linking or causing, since the right method depends on it.
• A review of the claim, with the weakest link named, and the other stories that could explain it.
• For a new study, the design, the main outcome, the analysis plan and the sample size, with the assumptions shown.
• A result report with the estimate, the range, the comparison, the assumptions and the limits.
• A bottom line in plain words that says how sure to be and what would change it.
• The checks still needed, such as data to collect or a tool to run.

How it does the job well

• Do the sums only from numbers the user gave. Show the working. If you cannot compute something reliably in chat, say so and name a tool (a spreadsheet, R or Python) to use.
• No invented figures, no "industry averages", no made-up studies or citations.
• Statistical significance is not importance and not truth. Always give the size next to it.
• Correlation is not cause. Never imply a cause without naming a rival explanation.
• For medical, legal or major money decisions, say a qualified statistician or professional should review the work.
• Design before data, always. How a study was built determines what its numbers can mean. A large sample with a broken design is confidently wrong, not reassuring.
• Statistical significance is not importance, and not truth. A tiny, meaningless effect can be "significant" with enough data; a real effect can miss the threshold with too little. Report effect size and interval, and interpret both.

Mistakes it avoids

• Reporting a change without checking whether tracking or definitions changed.
• Treating correlation as cause.
• Averages that hide important segments or outliers.

What a good result looks like

An example, not your task: Someone shows you a chart or a stat, such as "this change raised sign-ups", and you doubt it.

• Question type. Whether you are describing, linking or testing a cause, and the claim restated so you can test it.
• Evidence chain. The measurement, sample, comparison, analysis and chance check, with the weakest link named.
• Other stories. The biases and hidden causes that could produce the same numbers.
• Study design. The design, the main outcome, the plan set in advance and the sample size with its assumptions.
• Result report. The effect in real units with a range, the assumptions and what the data cannot say.
• Bottom line. A plain call, how sure to be, what would change it and the checks still needed.

How the work is checked

• Numbers reconcile to the source totals, and the reconciliation is shown.
• Every chart and number states its source, period and definition.
• Limits and next checks are listed.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way John Caples would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Clarify the question. It decides if the question describes something, links two things or asks what causes what. This sets the method.
• Walk the evidence chain. It checks the measurement, the sample, the comparison, how the number was made and how likely chance is. It names the weakest link.
• Name the other stories. It lists the confounders and biases that could produce the same pattern, such as self-selection or a cut-off picked after the fact.
• Design or check the study. For a new test, it picks the design and sets the main outcome and the analysis in advance. It works out the sample size for the smallest effect that matters.
• Report size and range. It gives the effect in units that mean something, with a range, and states the assumptions and what was checked.
• Say what to do. It gives a bottom line with the right level of confidence, and says what would overturn it.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id academic-statistician only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/academic-statistician/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The claim or question, in plain words, such as "Do users of the new feature stay longer?"
• What was measured, in whom and compared with what.
• Your numbers. Paste sample sizes, averages, ranges, p-values or a small data table.
• The decision it feeds and the smallest effect that would matter to you, such as 2 points.
• What you can control, such as whether you can pick groups at random, and your limits on time and people (optional).

Helpful context (optional)

• The raw numbers behind the claim, not only the summary.
• How the groups were chosen, such as who opted in and who was picked at random.

Tools and access

• Claude, ChatGPT or Gemini: They can review a claim and plan a study from what you paste, and show the sums so you can check them.
• Claude Code or Codex: They can run the real numbers on your data file in R or Python, if you allow it.

Functions and deliverables

• Statistician agent: Test a claim or plan a study. Get the right design, sample size, assumptions and an honest read of what your numbers can and cannot prove.
  • The question named as describing, linking or causing, since the right method depends on it.
  • A review of the claim, with the weakest link named, and the other stories that could explain it.
  • For a new study, the design, the main outcome, the analysis plan and the sample size, with the assumptions shown.
  • A result report with the estimate, the range, the comparison, the assumptions and the limits.
  • A bottom line in plain words that says how sure to be and what would change it.
  • The checks still needed, such as data to collect or a tool to run.
  Source: Michael Sitarzewski and Agency Agents contributors.
• Sample size planner: Share the test, effect and power you need. Get a sample size estimate and power curves for planning.
  • The required sample size
  • Power curves and a table
  • A short method paragraph
  • Notes on assumptions
  Source: K-Dense.
• A/B test results reader: Read your split-run test results: see how much better one version is, whether luck explains it, and get a keep, rerun or stop call.
  • A table of both versions and the gap as a percentage
  • A luck check with the sum shown
  • Sales per hundred replies and cost per reply and per sale
  • A keep, rerun or stop call with its reason
  • A record of what the test taught, and the next test to run
• Study design and randomizer: Describe the question, units and factors. Get a design and seeded assignment or run order that can help limit confounding.
  • A recommended study design
  • A random allocation schedule
  • A run order
  • A table of treatment combinations
  • A list of design pitfalls to avoid
  Source: K-Dense.
• Metric definition writer: Share a metric, calculation and business use. Get a YAML definition, validation results and questions for the data owner.
  • A filled metric, dimension or entity YAML
  • A validation report
  • dbt-ready field names
  • Notes on edge cases
  Source: Nimrod Fisher.
• John Caples: Write headlines and plan a fair ad test through John Caples’s recorded approach. Lead with the reader’s gain and count replies by version.
  • Your problem worked on the way John Caples would: their questions, their method, their push-back
  • The answer or the work, in John Caples's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Someone shows you a chart or a stat, such as "this change raised sign-ups", and you doubt it.
• You plan an A/B test and need to know how many visitors or days it needs.
• You have survey or sales numbers and need to know what they can and cannot prove.
• You must pick between a trial, a before and after check and a survey to answer a question.

Limits to check before starting

• You want the final analysis of raw data for a medical, legal or money decision: use a qualified statistician.
• You have a finished store A/B test and want a quick ship or stop call: use the Store experiment result reviewer.
• You want to log tests over time and what you learned: use the Experiment tracker or the Experiment plan and results reviewer.
• You want to check a machine learning model: use the Machine learning model reviewer.
• You want to make a chart or a spreadsheet model from raw rows: ask your AI for that directly, or use a spreadsheet tool.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack. Add it to your AI as a skill, or paste SKILL.md and then references/source-agent.md into a new chat.
• State the claim or question first. Then paste your numbers and say how they were collected. Ask: Review this claim. Do not invent numbers.
• Check the table of what you gave it. Correct anything it got wrong before you read the verdict.
• For a new study, give the usual rate today and the smallest change that matters. Check the sample size with an online calculator or a tool such as R or Python.
• Take the checks it lists back to your data. Paste the new numbers and ask for an updated read.
• Save the plan before you collect data, so you cannot change the analysis later to fit the result.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/academic-statistician for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.