Part 1: Long and wide data structures

Introduce the main longitudinal data structures (long and wide), the key differences between them, and how to move from one to the other.

Part 2: The implications of data structures for management and visualisation

Review the implications of long vs wide data structures for data management and visualisation, including implications for recoding variables, generating new variables, and visualising change over time.

Part 3: Examples (and tools) using the Millennium Cohort Study

Illustrate tools to manage and visualise longitudinal data using Stata and data from the UK Millennium Cohort Study, including transition matrices, histograms, box and violin plots, spaghetti plots, and lasagne plots.

Darío Moreno Agostino, Senior Research Fellow

Darío is a Senior Research Fellow in Population Mental Health. His research interests include the study of social and generational inequalities in mental health and healthy ageing outcomes.

Nicolás Libuy, Senior Research Fellow

Nicolás is a Senior Research Fellow working on a broad range of topics focusing on public health, education, labour and socio-economic conditions. His research uses administrative data linked with longitudinal studies to explore causal associations over the life course.