ABSTRACT

What is 'non-parametric'? All of the statistics we have considered up until now have been based on the assumption that the populations involved were normally distributed. Accordingly, we used such parameters as the mean and the standard deviation in calculations of Z, which assumed normality. Fortunately, a great many medical and biological phenomena are normally distributed. However, sometimes very little knowledge about the nature of the population is available and we cannot simply go ahead and assume that it is normal. In such cases we use non-parametric or distribution-free methods.