Then, with a better idea of possibilities and a better understanding of the methods, students can turn to the supervisor to validate their findings.  
 
Disclaimer

The AI Prompt Library presents examples to UM students and staff  on how to make better use of Generative AI (GenAI) in the educational process. Maastricht University does not recommend the use of any specific GenAI tool. However, you are strongly advised to opt-out of allowing your content to be used to (further) train the GenAI tool of your choice. This can usually be done in Settings.

Given that all information entered into an AI tool will be stored and can be reused by the GenAI tool provider as they deem fit, one should not feed:  UM- data, confidential information and trade secrets; personal data and sensitive data relating to you or other people; Copyrighted materials (such as books, academic articles e.t.c.), but also materials for which the UM is the copyright holder, such as educational materials including coursebooks, syllabi, ppt, e.t.c.

Certain GenAI practices in education may not be allowed or encouraged within your faculty’s policy framework and/or rules and regulations. Please check first, any relevant rules on the use of GenAI in education, applicable to you, and defined at activity, course/module, study programme and faculty level.

GenAI can only be employed for high-risk practices under strict conditions set out in the EU AI Act. UM currently refrains from employing GenAI in relation to student assessment, selection and admission procedures, monitoring and detection of prohibited behaviour during exams, pending further thorough investigation of the conditions.

Learn more about responsible use of Generative AI

The prompt

Copy the example prompt in the box below and paste it into an LLM of your choice.

Assume the role of a researcher experienced in quantitative analysis.   
Your task is to help me select an appropriate statistical method for my master’s thesis.  

Context:  

To be able to help me identify the appropriate statistical method, you must gather information about my study.   

First, reply “I am happy to help you identify an appropriate statistical method for your master thesis. To be able to do so, I must learn more about your study. I will ask you a series of questions. Please reply in as much detail as possible. Let me know when you are ready”. Wait until I reply. Do not proceed until I reply.   

Then, ask “What is your field of study (e.g. business, psychology)? What is the general topic?” Wait until I reply. Do not proceed until I reply. Save my reply to context on my study.  

Then, ask “What is the primary research question you are trying to answer? What are the hypotheses you aim to test?” Wait until I reply. Do not proceed until I reply. Save my reply to context on my study.   

Then, ask “What types of variables are involved in your study (e.g., continuous, categorical, ordinal)? How many variables are you studying, and what are they?” Wait until I reply. Do not proceed until I reply. Save my reply to context on my study.  

Then, ask “How is your data collected? (e.g., surveys, experiments, secondary data sources)? Is the data cross-sectional (collected at one point in time) or longitudinal (collected over several time points)? What is the size of your dataset?” Wait until I reply. Do not proceed until I reply. Save my reply to context on my study.  

Then, ask “Are the observations in your data independent of each other, or are there dependencies (e.g., measurements from the same subject or spatial dependencies)?” Wait until I reply. Do not proceed until I reply. Save my reply to context on my study.  

Then, ask “Are you looking at differences between groups, associations between variables, or the prediction of outcomes based on other variables? Do you have any preconceived notions about the direction or strength of relationships between variables?” Wait until I reply. Do not proceed until I reply. Save my reply to context on my study.  

Instructions:  

Based on the context gathered through questions and with your expert knowledge in statistics, suggest what statistical method(s) I should use. Focus on the most common methods, such as Linear Regression, Logistic Regression, One-way ANOVA, Two-way ANOVA, Structural Equation Modeling (SEM), Chi-square Test, Independent t-test, Paired t-test, Pearson correlation, Spearman’s rank correlation, Multivariate Analysis of Variance (MANOVA), Factor Analysis, Cluster Analysis, Time Series Analysis.  

Provide a concise, general explanation of the method. The explanation must be short and to the point.   

Provide detailed reasoning for why you suggest this is the most suitable method for my analysis. In your arguments, refer to my answers to your questions.   

Ask me if I have any questions. If I do, help me understand the statistical method and how it fits my data and hypothesis.  

 The AI Prompt Library © 2024 by Maastricht University is licensed under CC BY-SA 4.0 .
 In case of any questions, please contact the University Library.