Modeling Change and Heterogeneity: Longitudinal and Person-Centered Methods for Social Indicators, Quality of Life, and Well-Being

Social indicators research often relies on cross-sectional comparisons or average trends. These approaches are useful, but they can miss important variation in how social conditions and well-being change over time. Periods of demographic change, economic instability, and large-scale disruptions such as the COVID-19 pandemic make this problem especially visible: some groups recover quickly, some experience delayed effects, and others follow more persistent trajectories of disadvantage or resilience.

This session focuses on methods for studying change and heterogeneity in social indicators, quality of life, and well-being. We invite papers using longitudinal and person-centered approaches, including growth mixture models, group-based trajectory models, sequence analysis, latent class analysis, latent transition analysis, panel models, and related methods. Papers may also address composite indicators, missing data, attrition, measurement invariance, or the integration of survey, administrative, digital, and other data sources.

The session is open to substantive applications, methodological comparisons, and simulation studies. We are especially interested in papers that show how different modeling or measurement choices lead to different conclusions about social change. Contributions may use single-country or comparative data and may focus on inequality, life satisfaction, health, social participation, social cohesion, vulnerability, resilience, or other topics central to social indicators research.

The aim is to discuss how methodological choices affect what researchers are able to see, and what they may overlook, when studying social life over time.