Write a pre-registration and analysis plan for my study
Drafts a pre-registration covering hypotheses, sampling, variables, analysis decisions, and exclusion rules before data collection.
The prompt
Help me write a pre-registration for my study before I collect or look at the data.
Registry or template: [e.g. "OSF standard", "AsPredicted", "clinical trial registry", or "not sure"]
Research question and hypotheses: [DETAILS]
Design: [experimental, observational, conditions, within/between]
Participants or data source: [population, recruitment, inclusion/exclusion]
Planned sample size and justification: [NUMBER and basis, or "need help"]
Measures and variables: [IVs, DVs, covariates, how each is measured or scored]
Planned analyses: [models or tests I intend to use]
Draft these sections: hypotheses (each directional and falsifiable), design, sampling plan and stopping rule, variables with operational definitions, primary vs. secondary analyses, inference criteria (alpha, corrections for multiple comparisons), data exclusion rules, handling of missing data and outliers, and what counts as exploratory.
Then run a check: list every analytic decision still left open (researcher degrees of freedom), and ask me to decide each one now.
Return the pre-registration text with headings, plus a list of open decisions marked [DECIDE]. Do not invent measures, sample sizes, or prior effect sizes; mark gaps [ADD].
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- DETAILS
- experimental, observational, conditions, within/between
- population, recruitment, inclusion/exclusion
- NUMBER and basis, or "need help"
- IVs, DVs, covariates, how each is measured or scored
- models or tests I intend to use
- DECIDE
- ADD
How this prompt is built
This prompt follows the RTF structure (Role, Task, Format). RTF tells the model who to be, what to do and what shape the answer should take. It is the quickest structure that still gives noticeably better results than a bare request.
Related prompts
- Write a data dictionary for a table or datasetProduces clear column-level documentation with definitions, types, allowed values, grain, and known caveats so others can use the data safely.
- Review my analysis for errors before it goes outA rigorous second-pair-of-eyes check of an analysis for logic, data, statistical, and communication mistakes, ranked by severity.
- Write a model card to document a machine learning modelA complete model card covering intended use, data, performance by segment, limitations, fairness checks, and monitoring plan.
- Write the caveats and limitations section of my analysisAn honest, readable limitations section that explains uncertainty and data gaps without burying the conclusion.