agree or not?

What is a nonparametric test? What is a parametric analysis?

Parametric tests assume underlying statistical distributions inthe data. Therefore, several conditions of validity must be met sothat the result of a parametric analysis is reliable. The student’st-test for two independent samples is safe only if each samplefollows a normal distribution and if sample variances arehomogeneous. Nonparametric tests do not rely on any delivery. Theycan thus be applied even if parametric conditions of validity arenot met. Parametric tests often have nonparametric equivalents. Youwill find different parametric tests with their equivalents whenthey exist in this grid. 3.

what is the difference between a nonparametric test and adistribution-free test?

While nonparametric tests don’t assume that your data follow anormal distribution, they do have other assumptions that can behard to meet. For nonparametric tests that compare groups, a commonassumption is that the data for all groups must have the samespread dispersion. If your groups have a different spread, thenonparametric tests might not provide valid results. On the otherhand, if you use the 2-sample t-test or One-Way ANOVA, you cansimply go to the Options sub dialog and uncheck Assume equalvariances. Voilà, you’re good to go even when the groups havedifferent spreads.