91Ó°ÊÓ

Statistical tests can be divided into two main categories: parametric and non-parametric. Non-parametric tests are particularly useful when data doesn't meet the assumptions of parametric tests, such as normal distribution. These tests are ideal for data that's ordinal, or when the sample size is small.
In non-parametric tests, rank is often more important than the actual data points. This means the test focuses on the order and relative position of the data rather than raw scores.
Non-parametric tests include the Wilcoxon Test and Kruskal-Wallis Test, among others. They are flexible methods that make minimal assumptions about the data. This makes them powerful tools in situations where parametric tests would not be appropriate.

The Wilcoxon Test is a non-parametric test used to compare two related samples. It is often used as an alternative to the paired t-test when the data does not meet the normal distribution requirement.
This test is especially useful for small sample sizes or when the data is measured at an ordinal level. The Wilcoxon Test ranks the differences between pairs of data. These ranks help determine whether the median differences are significantly different from zero.
There are two main types of Wilcoxon Tests: the Wilcoxon Signed-Rank Test for paired data and the Wilcoxon Rank-Sum Test for independent samples.

• Wilcoxon Signed-Rank Test: Suitable for repeated measures or matched-pairs data.
• Wilcoxon Rank-Sum Test: Used for independent samples to compare medians.

This test is a robust method for handling non-normally distributed data.

The Kruskal-Wallis Test is a non-parametric method for comparing more than two groups. It's the equivalent of the one-way ANOVA but doesn’t require a normal distribution.
This test is useful when dealing with ordinal data or when the assumptions of ANOVA cannot be met. The Kruskal-Wallis Test ranks all data points across groups, treating them as a single sample.
Much like its parametric counterpart, it tests the hypothesis that all groups have similar distributions. The test statistic is based on ranks and may require a post-hoc test to identify where differences lie if the test is significant.
In summary, the Kruskal-Wallis Test provides a flexible approach for analyzing data without strict assumptions, making it perfect for various datasets.

A t-test is a fundamental method for comparing the means of two groups. It assumes a normal distribution of the data and that variances between groups are equal.
There are different types of t-tests: the independent t-test (also called two-sample t-test), paired t-test, and one-sample t-test.

• Independent t-test: Compares means between two independent groups, such as the scores of two different classes.
• Paired t-test: Used for related groups, such as pre-test and post-test scores of the same participants.
• One-sample t-test: Compares the mean of a single sample with a known value.

The t-test helps determine whether differences between group means are statistically significant.

ANOVA, short for Analysis of Variance, is a parametric test that extends the idea of the t-test to more than two groups. It is used to compare the means of three or more groups to see if there is a significant difference among them.
Assumptions for ANOVA include that the data follows a normal distribution, and the variances among groups are equal. ANOVA can be classified into different types, including one-way and two-way ANOVA.

• One-way ANOVA: Tests for differences in means among groups based on one independent variable.
• Two-way ANOVA: Examines interactions between two independent variables and their effect on the dependent variable.

If the ANOVA shows significant results, post-hoc tests like Tukey's Test help identify which specific groups differ from each other. ANOVA is a powerful tool, especially for complex experimental designs.