Prompt lesson · 22 prompts
Experimental Design prompts for Research Associates
22 ready-to-use prompts from our AI for Research Associates course. Copy one, fill in the {{placeholders}}, and paste it into ChatGPT, Claude, Gemini or any other AI.
Apply the Taguchi Method for Robust Experiments
Use this when you need to understand, plan, or apply the Taguchi method to optimize product or process parameters.
Role You are a seasoned quality engineering instructor specializing in the Taguchi method for robust design of experiments. Your goal is to guide the user through understanding, planning, and executing a Taguchi experiment.
Context you provide
- {{field}}: The area of application (e.g., "manufacturing of automotive parts")
- {{product}}: The specific product or process to optimize (e.g., "injection molding process")
- {{factors}}: Any known factors or parameters to consider (optional)
- {{objectives}}: The performance metric to improve (e.g., "reduce defect rate")
Instructions
- If essential context ({{field}}, {{product}}, {{objectives}}) is missing, ask for it before proceeding.
- Explain the basics of the Taguchi method and its relevance to {{field}}.
- Help identify key factors and levels relevant to {{product}} and {{objectives}}.
- Guide the selection of an appropriate orthogonal array (e.g., L9, L18) based on the number of factors and levels.
- Show how to set up the experiment matrix and analyze results (signal-to-noise ratio, mean response).
- Provide a step-by-step plan to conduct the experiment and interpret outcomes.
Output format Deliver a structured guide with sections: 1) Overview of Taguchi method for {{field}}, 2) Factor & Level Identification (with suggestions), 3) Recommended Orthogonal Array and why, 4) Experiment Setup Matrix, 5) Analysis Steps (including SNR calculations), 6) Expected challenges and tips.
Guardrails
- Do not provide generic statistical advice unrelated to the Taguchi method.
- Clearly indicate when a choice (e.g., array selection) depends on user-specific constraints.
- Avoid overcomplicating; keep explanations accessible for someone new to the method.
Example {{field}} = "electronics cooling", {{product}} = "heatsink design", {{factors}} = "fin thickness, fin height, material", {{objectives}} = "maximize heat dissipation"
Open this prompt Learning · Intermediate
Bayesian Experimental Design Explanation
Use this when you need to understand and apply Bayesian methods to design experiments in your research.
Role — You are a senior statistician specializing in Bayesian methods. Your goal is to explain Bayesian experimental design clearly, compare it to traditional approaches, and provide practical guidance for implementation.
Context you provide
- {{field}} — The research field (e.g., clinical trials, A/B testing, ecology, materials science).
- {{research_area}} — Specific topic or question (e.g., "effect of a new drug on blood pressure").
- {{prior_information}} — Any existing knowledge or data that could inform the design (e.g., previous pilot study results).
- {{design_goal}} — What you want to optimize: sample size, power, resource allocation, or adaptive features.
Instructions
- Ask for any missing context before proceeding.
- Explain Bayesian experimental design in non-technical terms, highlighting how it differs from frequentist methods.
- Show how prior information can be incorporated into the design, with examples relevant to the {{field}}.
- Discuss how to optimize sample sizes and resource allocation using Bayesian methods, including adaptive designs if appropriate.
- Summarize advantages (e.g., flexibility, handling small samples) and limitations (e.g., computational complexity, prior sensitivity).
Output format
- A structured explanation with sections: overview, key differences, incorporation of priors, optimization, and pros/cons.
- Use bullet points and tables where helpful.
- Include a concrete example calculation or simulation outline.
Guardrails
- Do not claim Bayesian methods are always superior; present balanced pros and cons.
- Do not provide specific statistical software code unless asked.
- Flag any assumptions about the user's statistical background (e.g., assume familiarity with basic probability).
Example
- {{field}}: "clinical trials"
- {{research_area}}: "testing a new vaccine efficacy"
- {{prior_information}}: "previous phase 1 trial showed 70% efficacy in 30 subjects"
- {{design_goal}}: "minimize number of subjects while achieving 80% power"
Open this prompt Learning · Advanced
Conduct Literature Review
Use this when you need to summarize, synthesize, or find relevant research papers on a specific topic.
Open this prompt Research · Intermediate
Control Group Design Planning
Use this when you need to design a control group for a study, ensuring representativeness, minimizing bias, and addressing ethical considerations.
Open this prompt Planning · Advanced
Create Latin Square Design
Use this when you need to design an experiment with multiple treatments while controlling for two or more sources of variation.
Open this prompt Planning · Advanced
Design Randomized Control Trials
Use this when you need to design a randomized control trial, including randomization methods and sample size calculations.
Open this prompt Planning · Advanced
Designing a Randomization Procedure for Research
Use this when you need to design a fair randomization process for assigning participants to groups in a research study.
Open this prompt Planning · Intermediate
Determine Sample Size for Studies
Use this when you need to calculate the sample size required for a study to achieve statistical significance.
Open this prompt Analysis · Intermediate
Ethical Considerations in Research Design
Use this when you need to identify and address ethical issues in your experimental design, including privacy, consent, and bias.
Open this prompt Research · Advanced
Explore Quasi-Experimental Designs
Use this when you need to understand, select, or apply quasi-experimental designs to study causal relationships in real-world settings.
Open this prompt Learning · Intermediate
Factorial ANOVA Experiment Design
Use this when you need to design a factorial ANOVA experiment, including factor selection, randomization, and interaction considerations.
Open this prompt Planning · Advanced
Factorial Design Optimization
Use this when you need to optimize a factorial design by selecting factor combinations that maximize efficiency and informativeness.
Open this prompt Writing · Advanced
Fractional Factorial Design Planning
Use this when you need to design a fractional factorial experiment to study main effects and interactions efficiently, especially with many factors.
Open this prompt Planning · Advanced
Generate Research Hypotheses
Use this when you need to brainstorm and refine hypotheses for your research study.
Open this prompt Research · Intermediate
Optimize Experiments with RSM
Use this when you need to design and analyze experiments using response surface methodology to optimize process parameters.
Open this prompt Planning · Advanced
Pilot Study Design
Use this when you need to design a small-scale pilot study to validate a research procedure before running the full study.
Open this prompt Planning · Advanced
Plan Sequential Adaptive Experiments
Use this when you need to design an adaptive experiment that can be modified based on interim results.
Open this prompt Planning · Advanced
Plan Split-Plot Experiments
Use this when you need to design an experiment that involves both hard-to-change and easy-to-change factors, requiring a split-plot structure.
Open this prompt Planning · Advanced
Select Data Collection Method
Use this when you need to choose and justify a data collection method for your research, ensuring integrity and ethical standards.
Open this prompt Decisions · Intermediate
Select Optimal Design Criteria
Use this when you need to choose and apply optimal design criteria for your experiment to maximize efficiency and information gain.
Open this prompt Planning · Advanced
Statistical Analysis Plan
Use this when you need a detailed plan for statistical tests in a research study, including handling confounders and biases.
Open this prompt Planning · Intermediate
Variable Identification
Use this when you need to clearly define independent and dependent variables in a research study and understand their relationship.
Open this prompt Analysis · Beginner