Purpose of the prompt
The prompt covers field, laboratory and computational experiments. It stresses specifying the analysis plan in advance and avoiding later decisions that inflate results.
When to use it?
After choosing the experimental method and before collecting data or running experiments.
Full prompt text
Text in square brackets [ ] is a variable you replace with your research details, or fill it in from “Customise the prompt” below.
You are an expert in experimental design and statistics in [Specific field]. Hypothesis or experimental question: [Hypothesis or question] Type of experiment: [Type of experiment] Resources and constraints: [Resources and constraints] Design the experiment, including: 1. The independent variable and its levels, the dependent variable and how it is measured, and the possible control and confounding variables. 2. The design (between-groups, within-groups, factorial, ...) with justification. 3. Randomisation and blinding where they apply. 4. Sample size: the method (statistical power analysis) and the inputs needed (expected effect size, α, power), without inventing an effect size; suggest where I can obtain it. 5. The procedures step by step. 6. The pre-specified analysis plan: the main test, handling missing values and outliers, correction for multiple comparisons. 7. Threats to validity and how to control them. 8. Ethical considerations. 9. In computational experiments: random seeds, data splitting, number of repetitions and baselines. Academic integrity rules (mandatory): - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed]. - Do not claim to have read a study or file whose text I have not given you. - Clearly separate what comes from the material I provided from your own conclusions and suggestions. - If you are missing essential information, ask me for it before continuing instead of assuming it. Write the answer in [Answer language].You are an expert in experimental design and statistics in [Specific field]. Hypothesis or experimental question: [Hypothesis or question] Type of experiment: [Type of experiment] Resources and constraints: [Resources and constraints] Design the experiment, including: 1. The independent variable and its levels, the dependent variable and how it is measured, and the possible control and confounding variables. 2. The design (between-groups, within-groups, factorial, ...) with justification. 3. Randomisation and blinding where they apply. 4. Sample size: the method (statistical power analysis) and the inputs needed (expected effect size, α, power), without inventing an effect size; suggest where I can obtain it. 5. The procedures step by step. 6. The pre-specified analysis plan: the main test, handling missing values and outliers, correction for multiple comparisons. 7. Threats to validity and how to control them. 8. Ethical considerations. 9. In computational experiments: random seeds, data splitting, number of repetitions and baselines. Academic integrity rules (mandatory): - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed]. - Do not claim to have read a study or file whose text I have not given you. - Clearly separate what comes from the material I provided from your own conclusions and suggestions. - If you are missing essential information, ask me for it before continuing instead of assuming it. Write the answer in [Answer language]. You are an expert in experimental design and statistics in {{field}}. Hypothesis or experimental question: {{hypothesis}} Type of experiment: {{kind}} Resources and constraints: {{constraints}} Design the experiment, including: 1. The independent variable and its levels, the dependent variable and how it is measured, and the possible control and confounding variables. 2. The design (between-groups, within-groups, factorial, ...) with justification. 3. Randomisation and blinding where they apply. 4. Sample size: the method (statistical power analysis) and the inputs needed (expected effect size, α, power), without inventing an effect size; suggest where I can obtain it. 5. The procedures step by step. 6. The pre-specified analysis plan: the main test, handling missing values and outliers, correction for multiple comparisons. 7. Threats to validity and how to control them. 8. Ethical considerations. 9. In computational experiments: random seeds, data splitting, number of repetitions and baselines. Academic integrity rules (mandatory): - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed]. - Do not claim to have read a study or file whose text I have not given you. - Clearly separate what comes from the material I provided from your own conclusions and suggestions. - If you are missing essential information, ask me for it before continuing instead of assuming it. Write the answer in {{lang}}.
Customise the prompt
Fill in only what suits you. The line of an empty optional field is removed from the final text, and empty required fields stay in brackets for you to complete later.
Preview of the customised prompt
You are an expert in experimental design and statistics in [Specific field]. Hypothesis or experimental question: [Hypothesis or question] Type of experiment: [Type of experiment] Resources and constraints: [Resources and constraints] Design the experiment, including: 1. The independent variable and its levels, the dependent variable and how it is measured, and the possible control and confounding variables. 2. The design (between-groups, within-groups, factorial, ...) with justification. 3. Randomisation and blinding where they apply. 4. Sample size: the method (statistical power analysis) and the inputs needed (expected effect size, α, power), without inventing an effect size; suggest where I can obtain it. 5. The procedures step by step. 6. The pre-specified analysis plan: the main test, handling missing values and outliers, correction for multiple comparisons. 7. Threats to validity and how to control them. 8. Ethical considerations. 9. In computational experiments: random seeds, data splitting, number of repetitions and baselines. Academic integrity rules (mandatory): - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed]. - Do not claim to have read a study or file whose text I have not given you. - Clearly separate what comes from the material I provided from your own conclusions and suggestions. - If you are missing essential information, ask me for it before continuing instead of assuming it. Write the answer in [Answer language].
Variables you can customise
- [Specific field]
- Required
- [Hypothesis or question]
- Required
- [Type of experiment]
- Optional, choose from: Experiment with human participants, Laboratory experiment, Computational experiment (machine learning or simulation), Field or educational experiment, default value: Experiment with human participants
- [Resources and constraints]
- Optional
- [Answer language]
- Optional, choose from: Arabic, English, Arabic with English terms in parentheses, default value: Arabic with English terms in parentheses
Usage example
Example input
Expected output
How to use it
- Actually calculate the sample size with software such as G*Power or JASP after setting the effect size.
- Pre-register the analysis plan if possible (OSF).
Tips for better results
- Ask for two effect size scenarios (conservative and optimistic) to estimate the range.
Limitations and warnings
- It does not calculate the sample size precisely; it only sets out the method and the inputs.
Suggested tools for using this prompt
Tools from the directory of research and academic publishing tools that are actually linked to this prompt's task, with the reason each tool is suggested.
Open-source statistics software with an easy graphical interface that supports classical and Bayesian analyses.
Research function: Running statistical analyses by clicking, without programming, with results that update immediately.
Why it is suggested: To run the planned statistical analysis after collecting the data.
A free, open statistical spreadsheet built on R that works by clicking and shows the R syntax of every analysis.
Research function: Running statistical analyses in a spreadsheet interface, saving the data, analyses and results in one file.
Why it is suggested: A free alternative for statistical analysis with a graphical interface.
A general AI assistant from OpenAI used for brainstorming, drafting and summarising.
Research function: General text chat that helps you generate and organise ideas and improve your wording.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
A general AI assistant from Anthropic used for analysis, drafting, summarising and working with documents.
Research function: General text chat that helps you analyse texts, organise ideas and improve your wording.
Why it is suggested: A general language model where you can paste the prompt directly and continue the conversation to improve the result.
A hosted Jupyter Notebook service from Google that runs in the browser with no setup and offers computing resources, including GPUs.
Research function: Writing and running Python code in notebooks saved to Google Drive.
Why it is suggested: To run computational experiments or simulate sample size in Python.
In research workflows
Similar prompts
Selecting and Justifying a Research Methodology
Compares the possible methods for your research questions, recommends the most suitable one with a scientific justification, and reveals the weak points a committee may ask about.
Choosing the Right Statistical Test
Identifies the right statistical test for your question, variable types and design, with its assumptions, how to check them, the non-parametric alternative and how to report it.
Designing Rigorous ML Experiments (Leakage-Aware)
Designs an experimental protocol for machine learning or deep learning: data splitting, baselines, metrics, tuning, repetition and statistical tests, with a systematic check for data leakage.
اختيار تصميم دراسة مختلط
قارن التصاميم الكمية والنوعية والمختلطة وفق السؤال والموارد، واقترح تسلسل الدمج.
