The Research Library of Graduate School of UIN Jakarta - Efforts to improve academic and research understanding of data analysis, The Research Library of Graduate School of UIN Jakarta, in collaboration with the Institute of Qualitative and Quantitative (IQQ), held a workshop titled "Enhance Your Data Analysis Skills with Partial Least Squares Structural Equation Modeling (PLS-SEM)" at the 3rd floor of the Graduate School Research Library. The event was attended by dozens of postgraduate students and research practitioners.

The workshop featured Dr. Riris Aishah Prasetyowati, SE., MM., an expert in management and data analysis, who shared her knowledge in an accessible and practical manner. She emphasized the importance of accurate data analysis in research and introduced PLS-SEM as a popular method. PLS-SEM is a variance-based approach used to examine relationships between latent variables. Unlike covariance-based SEM methods, PLS-SEM is known for its flexibility and effectiveness in analyzing relationships between variables in social, economic, and business research.

Dr. Riris explained the basic concepts of PLS-SEM in an easy-to-understand approach, ensuring participants could master the technique without a complex statistical background. She highlighted the ease with which PLS-SEM allows for in-depth analysis of variable relationships, even with small or non-normally distributed data sets.

She also emphasized the importance of understanding the 'Outer Model' and 'Inner Model'. The Outer Model focuses on the validity and reliability of indicators for latent variables, while the Inner Model highlights causal relationships between latent variables in the structural model.

One interesting aspect of the PLS-SEM approach is its ability to test intervening variables or mediators. Dr. Riris provided examples of how a mediation variable can clarify the influence between independent and dependent variables.

Using the SmartPLS software, participants were guided through modeling from the initial stages to result interpretation. The Bootstrapping technique in SmartPLS was also taught to ensure the significance of path relationships between variables.

As part of comprehensive learning, Dr. Riris presented real-world case studies, such as in social sciences. Using actual data, participants were guided to formulate hypotheses, build models, and interpret PLS-SEM analysis results.

In this workshop, participants not only learned theory but were also taught to critically process and interpret research results. Dr. Riris emphasized the importance of R-squared values, path coefficients, and indirect effects in drawing valid conclusions.

Ultimately, with an easy and practical approach, Dr. Riris successfully transformed the complex understanding of PLS-SEM into a more comprehensible analysis method. Participants gained new insights and skills in conducting more in-depth and applicable data analysis. With this understanding and delivery, it is hoped that participants can use this method to improve the quality of research and data-driven decision-making.