Skill Myself Up Library Workshop Materials: Analysis and Visualization Tools

Code-free Data Science and Analytics Series (CDSAS)
*Please note that digital badging is not yet available for this series.

Free and Open-Source (FOSS) code-free tools like jamovi and Orange offer graphical user interfaces (GUIs) with drag-and-drop functionality, simplifying data integration, preparation, and wrangling without requiring SQL. These tools also democratise data science exploration and provide access to advanced analytics capabilities for students and research scientists without programming skills.

In this four-part workshop series, you will enhance your data science and analytics skills to support your research needs without spending hours learning to code.
 

1. Code-free Statistical Data Discovery and Analysis with jamovi
   In this workshop, you will learn how to perform Exploratory Data Analysis (EDA), traditional Null Hypothesis Significance Testing (NHST), Bayesian inference, and Modern Statistics methods using jamovi, a free and open-source statistical software. Designed for users with minimal coding experience, jamovi offers a user-friendly, point-and-click interface.  It serves as an alternative to commercial software such as SPSS and JMP Pro, providing a simplified graphical interface built on the R statistical language, which gives access to a wide range of statistical functions.
    
2. Code-free Explanatory Model Building with jamovi
   This workshop demonstrates how jamovi enhances explanatory model building through real-time results visualization, an intuitive user interface with dynamic output, and tools for model development and evaluation. Features such as hierarchical regression blocks and model comparison statistics allow users to understand and refine models, choose appropriate variables based on theoretical and statistical criteria, and assess model fit using residual plots, all without writing code.
    
3. Code-free Machine Learning with Orange Data Mining Tool
   The CRISP-DM (Cross Industry Standard Process for Data Mining) framework consists of six iterative phases: Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment.  This workshop uses a case study approach to demonstrate how the CRISP-DM methodology can be implemented with Orange, a code-free data mining tool. You will learn how to navigate through the entire data mining process using Orange's visual programming environment without writing a single line of code.
    
4. Code-free Predictive Modelling with Orange Data Mining Tool
   Orange offers a visual, component-based interface for building predictive models. Users can easily create workflows using widgets for data preprocessing, model training, and evaluation.  This workshop introduces core machine learning methods available in Orange, including algorithms like Random Forest, Logistic Regression, and Support Vector Machines (SVM), as well as ensemble techniques such as bagging, boosting, and stacking. Through a real-world business case, you will learn how to build robust predictive models using Orange’s comprehensive suite of tools without writing a single line of code.

This workshop series was designed by Assoc Prof. Kam Tin Seong, School of Computing and Information Systems. If you have any questions, you may contact Prof. Kam at tskam@smu.edu.sg or the library at library@smu.edu.sg.

Please refer to the related materials and recording (if available) for this workshop below.