We refer to longitudinal data when the same variables of the same units are measured several times at different moments. The common trait is that the entity under investigation is observed or measured at more than one point in time, possibly regularly, in order to study how it develops over time. The data are collected either prospectively, following subjects forward in time, or retrospectively, by extracting multiple measurements on each unit from historical records. Also data from registers can be referred to as longitudinal data, indeed it is possible to match historical data about the same units once they are available with some degree of regularity.
This theme is due to describe the methods for imputation of missing longitudinal data, that could be performed for all aforementioned types of data. Particular emphasis is focused on the Short Term Statistics context.
To read the entire document, please access the pdf file (link under "Related Documents" on the right-hand-side of this page).
Your feedback is appreciated. Please send your remarks, suggestions for improvement, etc. to email@example.com.