This lecture will discuss basic and advanced multilevel analyses, using random coefficient modeling (RCM) in R.  The lecture will start by laying out a foundation for analyzing two-level models in RCM, where the dependent variable is at the lower level (Level 1), and predictors are at both the lower level (Level 1) and a higher-level unit (Level 2). 

By the end of this workshop, participants will gain an understanding of the importance of computational modeling for effective theory development and how to take the next steps in developing computational models for their own theories of interest.

This session will explore more advanced uses of LLMs, including automated qualitative coding and use of LLM embeddings in natural language models.

This applied module engages researchers in the practice of doing advanced qualitative analysis. Focused on interpretive analysis, it focuses on practices of coding and analysis with particular attention paid to the advanced analytic processes that facilitate novel theorizing.

This workshop will address five areas researchers should consider when exploring the potential for AI to assist with research and analysis: (1) recognizing potential errors and limitations in AI-generated outputs, (2) using AI to generate and refine research ideas, (3) developing research design and measurement using AI, (4) applying AI’s capabilities to data analysis and interpretation, and (5) writing alongside AI.

The goal of the session is to conduct analysis and interpret the results in line with the various tests performed and a hypothetical research question that could be explored with the data.

In this session, we focus on the assumptions that make causal inference possible and on the ways those same assumptions constrain it.