Hypothesis tests make it possible to compare one or more samples, and to validate or invalidate a hypothesis.
Adjustment tests identify the law that our data follows.
Used to test the differences in the variances between samples, they allow in particular to ensure the conditions of use of the hypothesis tests.
The Fisher-Snedecor test makes it possible to compare the variance of 2 samples.
The analysis of the variance allows to study the average of K samples.
The McNemar test allows to compare 2 populations that can only take 0 or 1:0 values being the non presence of a character, with 1 being the presence of a character.
The test is used to compare sample average with paired data.
The student test allows to identify differences on average or proportional parameters.
The χ2 test tests the adequacy of a data distribution with expected law or other data distributions.
Cochran’s Q is a generalization of the McNemar test and allows to process more than 2 sets of matched data.
The normal probability Plot is probably the simplest test of normality. Everyone will be able to use it to determine the “normality” of its data.
The Wilcoxon – Mann Whitney test allows you to compare performance levels.
The Kruskal and Wallis test is a non-parametric test for comparing more than 2 samples on data that can be averages, frequencies, or variances.
The Wilcoxon test is not to be confused with the Wilcoxon-Mann Whitney test. Even if they are similar, this one is suitable for matched data.
The Block Anova allows you to study more than 2 paired samples.
The Friedman test is a generalization of the Wilcoxon test for more than 2 samples.
The Spearman Rho allows to detect a correlation or not between variable.
Called the Kendall rank correlation coefficient, it is a non-parametric correlation measure. It is used to determine a relationship between two sets of data.
The main interest of the Kolmogorov Smirnov test is to process ordinal data.
The Durbin Watson Test is used as part of a regression study to determine whether the data is independent.
Very many, these are tests that allow to identify the samples that differ among the X that we tested beforehand.
It allows us to test whether our data follow a diverse law, especially the normal law.
The Shapiro Wilk test is effective at validating normality when we have less than 50 data.
The Lilliefors test is a variation of the Kolmogorov Smirnov test to test normality
The Brown Forsythe test is the best test to compare the variance of 2 or more samples.