Experimentation Program Setup — Calculator & TemplatesMo Rahman
Stop relitigating the same statistical arguments every quarter.
For teams running experiments regularly who want a repeatable process instead of a debate every time a number comes back ambiguous.
What you get
A custom sample-size and power calculator built for your metrics and traffic — a working tool, not a spreadsheet template, that your PMs can use without asking anyone
A pre-registration template — hypothesis, primary metric, guardrails, stopping rule, all committed before launch
A readout template your team fills in, with the corrections built into the structure so they can't be quietly skipped
A written decision framework — when to use which correction, when to stop a test, what counts as a real result, what to do with a null
A worked example using one of your own past tests, showing the process end to end
A 60-minute walkthrough call with your team, plus written notes
Who this is for
Teams running at least one experiment a month who keep hitting the same arguments — "can we call it yet," "variant C won, right," "should we look at mobile separately." The tooling settles those in advance rather than case by case.
Turnaround: 2 weeks.
Custom scope available — message me if you need something narrower or broader.
FAQs
Example work
Starting at$800
Duration2 weeks
Tags
Python
SQL
Streamlit
A/B Testing
Data Analyst
Statistician
Conversion Rate Optimization
Experiment Design
Statistical Analysis
Service provided by
Mo Rahman New York, USA
Experimentation Program Setup — Calculator & TemplatesMo Rahman
Starting at$800
Duration2 weeks
Tags
Python
SQL
Streamlit
A/B Testing
Data Analyst
Statistician
Conversion Rate Optimization
Experiment Design
Statistical Analysis
Stop relitigating the same statistical arguments every quarter.
For teams running experiments regularly who want a repeatable process instead of a debate every time a number comes back ambiguous.
What you get
A custom sample-size and power calculator built for your metrics and traffic — a working tool, not a spreadsheet template, that your PMs can use without asking anyone
A pre-registration template — hypothesis, primary metric, guardrails, stopping rule, all committed before launch
A readout template your team fills in, with the corrections built into the structure so they can't be quietly skipped
A written decision framework — when to use which correction, when to stop a test, what counts as a real result, what to do with a null
A worked example using one of your own past tests, showing the process end to end
A 60-minute walkthrough call with your team, plus written notes
Who this is for
Teams running at least one experiment a month who keep hitting the same arguments — "can we call it yet," "variant C won, right," "should we look at mobile separately." The tooling settles those in advance rather than case by case.
Turnaround: 2 weeks.
Custom scope available — message me if you need something narrower or broader.
FAQs
Example work
$800