A non-parametric test for the non normal distribution of the weights of female rats
2009
Raza, I. (National Agricultural Research Centre, Islamabad (Pakistan). Social Sciences Inst.) | Masood, M.A. (National Agricultural Research Centre, Islamabad (Pakistan). Social Sciences Inst.) | Ahmed, I. (National Agricultural Research Centre, Islamabad (Pakistan). Vertebrate Pest Management Programme)
This study accentuates the use of non-parametric statistical methods in the field of biological sciences and highlights some advantages of non-parametric methods over the traditional parametric methods. Parametric methods are not always powerful because they make rigid assumptions about the distribution of data. In many cases the distribution of data is not known due to which the assumption of normality is infringed. Non-parametric methods are called robust statistical methods as they are distribution free methods and do not make stringent assumptions about the distribution of data. Data on the weights of 15 female rats were taken from Vertebrates Pest Management Programme (VPMP), NARC, Islamabad. The analysis was obtained using MINITAB software version 13.2. Ryan - Joiner test similar to Shapiro - Wilk test and Box plot technique were used to examine the normality of data and both techniques depicted that the data were not normal. One sample Sign-test (non-parametric test) was used as a substitute for one sample t- test to determine whether the median weight of the sample of the weights of 15 female rats is less than the hypothesized value of median (Mo = 221) using level of significance, alpha = 0.05. P-value of 0.02 gave sufficient evidence to reject the null hypothesis (M = 221) and conclude that there is a significant difference among the weights of female rats.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par National Agricultural Research Centre
Découvrez la collection de ce fournisseur de données dans AGRIS
