In most research works, the word parametric analysis have been used for correlation between two variables. Whereas the variables could have failed in test of normality and homogeneity, can it also be called parametric analysis?
if the normality test and associated parametric assumptions are not fulfilled, should bi-variant analysis be termed as parametric?
It sounds like your question is about when to use the terms "parametric" and "nonparametric".
The first thing I would say is that it's not necessary to use them at all. It is best to simply state which test is used (e.g. "Pearson correlation") and which assumptions of the analysis were confirmed (e.g. homoscedasticity). There can be some confusion about the terms "parametric" and "nonparametric".. (See, for example: https://stats.stackexchange.com/questions/142101/why-is-pearson-parametric-and-spearman-non-parametric )
To your specific question, the terms "parametric" and "nonparametric" attach themselves to the test, not the data. So, a t-test is always parametric, no matter what data is fed in to it. It always assumes that the data follow a certain distribution, whether or not the data in fact follow this distribution.
Dear Ikenna,
There are two forms of bivariate correlation analysis: Pearson's parametric correlation and Spearman's rank nonparametric correlation. The important assumptions for using the former are: 1. Independent readings, 2. Linear relationship, and 3. Homoscedasticity (the variance of the dependent variable is independent of the value of the independent variable). The normality assumption is not as important as these three.
It sounds like your question is about when to use the terms "parametric" and "nonparametric".
The first thing I would say is that it's not necessary to use them at all. It is best to simply state which test is used (e.g. "Pearson correlation") and which assumptions of the analysis were confirmed (e.g. homoscedasticity). There can be some confusion about the terms "parametric" and "nonparametric".. (See, for example: https://stats.stackexchange.com/questions/142101/why-is-pearson-parametric-and-spearman-non-parametric )
To your specific question, the terms "parametric" and "nonparametric" attach themselves to the test, not the data. So, a t-test is always parametric, no matter what data is fed in to it. It always assumes that the data follow a certain distribution, whether or not the data in fact follow this distribution.
Hello, spearman correlation does not require for the variables to be continous nor normally distributed.
- Badges
- Science topic