Experiential learning of R-CRAN statistical program by using a generative AI model (Chat GPT) 2400-ZU2WW084
The primary objective of this course is to acquaint students with advanced statistical software, necessitating coding proficiency. We will concentrate on three key areas: i) setting up an efficient work environment, ii) organizing various data types, and iii) data visualization. Participants will gain essential knowledge in R programming language to effectively utilize R packages and independently create applications using these resources. Moreover, the course offers insights into IT skills and practical examples of data analysis applications, motivating students to apply these techniques in their respective fields. The curriculum is structured into four distinct segments.
R-cran programming will be taught through experimental methods. Following a brief introduction, students are encouraged to actively engage with generative AI technologies, like ChatGPT, for coding purposes.
• Block 1: Introduction Using his experience, the lecturer will present a minimal introduction to the R environment, i.e. the basic elements necessary to perform analytical tasks. This block makes strong use of the Pareto principle in its teaching approach. Giving students a basic set of tools allows them to move directly to using generative AI to create their own codes.
• Block 2: Overview This module explores the software's capabilities for analyzing a range of statistical data.
• Block 3: Mastering The focus shifts to enhancing skills and introducing advanced techniques for data cleaning and preparation.
• Block 4: Collaboration Groups will undertake projects involving data cleaning and preparation. Participants are expected to share their datasets and insights on managing such data.
Type of course
Course coordinators
Learning outcomes
KNOWLEDGE
Student:
• understands the methodologies of quantitative social and economic research
• knows the methodology of experimental research in social sciences
• knows the basic methods of valuing non-market goods
• knows the concept of time value of money
SKILLS
Student:
• becomes proficient in the R-CRAN computational environment.
• is able to statistically analyze the obtained data
• acquires the ability to integrate R-CRAN with AI functionalities.
• is able to find the relationship between the obtained results and economic theory
ATTITUDES
Student:
• is able to combine economic knowledge with professional work and other areas of social sciences.
• understands the need to have "scientific curiosity"
• demonstrates competence in collaborative work and engaging
Assessment criteria
During these classes, the principle of learning-by-doing will be used very intensively. The first part of the classes will consist in presenting the theory and the case study, the second part will consist in repeating the analyses on other data.
Minimal knowledge of Excel will be sufficient to start the class.
R-cran coding will be taught in an experimental way. After minimal introduction, students are expected to actively use the capabilities of generative AI (Chat GPT) to create their own codes.
Attendance at classes is mandatory. The basis for the assessment is:
• activity during classes: students are to prepare a report on their work and post it on the Moodle platform by the end of the day (40% of the grade)
• presenting a research report, which can be prepared in a group of up to 3 people (60% of the assessment)
Bibliography
This course will be based on your own materials and ultimately these materials will take the form of a textbook/script. Online textbooks (mainly in English) will be used, such as:
• Introduction to Research Methods, Eric van Holm [https://bookdown.org/ejvanholm/Textbook/]
• Wickham, H., & Grolemund, G. (2016). R for data science.
Additional information
Additional information (registration calendar, class conductors, localization and schedules of classes), might be available in the USOSweb system: