Article Text

PDF
SP0186 Modelling Longitudinal Data
  1. S. Ramiro1,2
  1. 1Rheumatology, Hospital Garcia de Orta, Almada, Portugal
  2. 2Clinical Immunology & Rheumatology, ARC, Amsterdam, Netherlands

Abstract

Longitudinal studies are increasingly used in rheumatology, especially in long-term cohorts, and are a source of important information that helps us drawing meaningful conclusions. Longitudinal studies are defined as studies in which the same outcome variable is repeatedly measured over time in the same patient. They can be applied in any field and be used to address different types of research questions. Examples of longitudinal studies are the registries that have been created during the last decade (several of them based on patients using biologicals, others broader) that aim at investigating disease and/or treatment outcomes over time. Questions like: 'Does disease activity lead to structural damage?' or 'Does functional disability result from high disease activity?' can be appropriately addressed with a longitudinal study.

Longitudinal studies allow us to investigate the development or the course of a variable over time if analyzed appropriately, and may provide insight into the longitudinal relationship between several variables over time. Appropriate analysis means that adjustment for correlated data takes place in order to avoid spurious relationships. Correlated data are data collected within the same patient. Furthermore, in longitudinal analysis, all data collected for a given patient over time are used. Due to this efficient data usage, this type of analysis has more analytical power. Longitudinal analysis is nowadays increasingly frequent and widespread, and it is important that researchers and clinicians learn about the principles of longitudinal data analysis in order to be able to interpret articles appropriately.

In this presentation, longitudinal analysis will be discussed, its advantages as well as its challenges. Several examples of longitudinal data analysis will be presented, and the strengths of longitudinal analysis will be discussed.

Disclosure of Interest None declared

DOI 10.1136/annrheumdis-2014-eular.6157

Statistics from Altmetric.com

Request permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.