Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/127186
Title: La influencia del tamaño muestral en la selección de pruebas paramétricas o no paramétricas: estudio comparativo mediante simulación de Monte Carlo
Author: Jiménez Miranda, Verónica
Tutor: Fernández Martínez, Daniel  
Others: Maceira, Marc  
Abstract: The selection of the statistical test is one of the most important steps of the inferential statistical analysis. In scientific literature, there are several proposals intended to help researchers to choose the most appropriate statistical test based on the study design. Regarding the selection of a parametric or non-parametric test, the majority of proposals are almost exclusively based on the normality of data, since sample size is a little treated or mentioned aspect. Based on this issue, the aim of the present work is to study the role that sample size plays when selecting one of these methods. For this purpose, the statistical power of the t-test and the Mann¿Whitney U test was compared using several sample sizes and the most frequent probability distributions observed in the biomedical field. The results show that sample size can influence the performance of statistical tests and that normality of data should not be the only selection criteria, since there are some discrepancies that indicate that other kind of factors can play a role. Therefore, it is concluded that more studies are needed and new lines of investigation are proposed in order to improve the present one.
Keywords: Mann¿Whitney U test
student's t-test
statistical power
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 5-Jan-2021
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 
vjimenezmiTFM0121memoria.pdfMemoria del TFM6,09 MBAdobe PDFThumbnail
View/Open