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

Revista da Escola de Enfermagem da USP

Maria Alice Santos Curado¹  Júlia Teles¹  João Marôco¹ 

关键词: Nursing research;    Data collection;    Measures;    Scales;    Psychometrics;    Investigación en enfermería;    Recolección de datos;    Medidas;    Escalas;    Psicometría;    Pesquisa em enfermagem;    Coleta de dados;    Medidas;    Escalas;    Psicometria;   

DOI  :  10.1590/S0080-623420140000100019

来源: SciELO

【 摘 要 】

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.

【 授权许可】

CC BY   
 All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License