Data analysis based on SISSREM: Shiny Interactive, Supervised and Systematic report from REpeated Measures data

Longitudinal methods are the procedures of choice for scientists who see their phenomena of interest as dynamic. However, given the difficulty of using linear mixed models (LMM), other simpler approaches are used, but suboptimal and sometimes discouraged by the structure of the data. The objective o...

ver descrição completa

Detalhes bibliográficos
Autor: Hernández Alonso, Pablo
Formato: tesis de maestría
Fecha de publicación:2019
País:España
Recursos:Universitat Oberta de Catalunya (UOC)
Repositorio:O2, repositorio institucional de la UOC
OAI Identifier:oai:openaccess.uoc.edu:10609/98186
Acesso em linha:http://hdl.handle.net/10609/98186
Access Level:acceso abierto
Palavra-chave:repeated measures
linear mixed model
Shiny app
medidas repetidas
modelo lineal mixto
aplicación Shiny
mesures repetides
model lineal mixt
aplicació Shiny
Bioinformatics -- TFM
Bioinformàtica -- TFM
Bioinformática -- TFM
Descrição
Resumo:Longitudinal methods are the procedures of choice for scientists who see their phenomena of interest as dynamic. However, given the difficulty of using linear mixed models (LMM), other simpler approaches are used, but suboptimal and sometimes discouraged by the structure of the data. The objective of this work is to develop a systematic and supervised methodology so that biomedical researchers with low-average level of statistics can perform an analysis of repeated measures. By using R programming language, we have developed a Shiny online application named SISSREM (Shiny Interactive, Supervised and Systematic report from REpeated Measures data). It can: i) instruct the user in the understanding of a LMM analysis for repeated measures with an example database; ii) allow the user to analyze their own data; and iii) allow the user to create an interactive, supervised and systematic report to be exported from the Shiny application. The main core of the application consists of a guided tour through a predetermined analysis with a sample database and the systematic decisions that should be made in an LMM analysis. Therefore, it has been structured in different modules that allow you to explore and process the data, as well as perform the LMM analysis, save data and/or generate a report in .PDF, .HTML or .DOCX format.SISSREM (https://sissrem.shinyapps.io/SISSREM_v1/) is a functional application whose objective is to simplify the use and disseminate the usefulness of LMM in biomedical research.