Analysis of variables that are not directly observable: influence on decision-making during the research process

• Autor(a) principal: Curado,Maria Alice Santos
• Data de Publicação: 2014
• Outros Autores: Teles,Júlia, Marôco,João
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Revista da Escola de Enfermagem da USP (Online)
• Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0080-62342014000100146
• topic: Nursing research; Data collection; Measures; Scales; Psychometrics

The sample dimension, types of variables, format used for measurement, and construction of instruments to collect valid and reliable data must be considered during the research process. In the social and health sciences, and more specifically in nursing, data-collection instruments are usually composed of latent variables or variables that cannot be directly observed. Such facts emphasize the importance of deciding how to measure study variables (using an ordinal scale or a Likert or Likert-type scale). Psychometric scales are examples of instruments that are affected by the type of variables that comprise them, which could cause problems with measurement and statistical analysis (parametric tests versus non-parametric tests). Hence, investigators using these variables must rely on suppositions based on simulation studies or recommendations based on scientific evidence in order to make the best decisions.