Statistika Parametrik atau Nonparametrik? || Memilih jenis uji dan syarat uji parametrik

Summary

This lecture covers the fundamental principles of parametric and non-parametric statistics, focusing on the importance of selecting the correct statistical test based on data type and assumptions. It explains when to use parametric tests like t-tests and ANOVA, and when to resort to non-parametric tests such as Mann-Whitney U or Kruskal-Wallis, especially when data doesn't meet parametric assumptions like normality. The session emphasizes understanding data size and testing assumptions, ensuring students can apply the theory to real-world situations, especially using SPSS software for practical analysis.

Takeaways

• 😀 Understand the importance of choosing the right statistical test based on data type (parametric vs non-parametric).
• 😀 Parametric tests are used for interval and ratio data, while non-parametric tests are used for nominal and ordinal data.
• 😀 If parametric assumptions like normality or homogeneity of variance are not met, non-parametric tests should be used instead.
• 😀 Common parametric tests include the t-test and ANOVA, while non-parametric alternatives include the Mann-Whitney U test and Kruskal-Wallis test.
• 😀 Always check assumptions (normality, linearity, homogeneity) before selecting a statistical test.
• 😀 If normality is violated for two independent groups, the Mann-Whitney U test can be used as a non-parametric alternative to the t-test.
• 😀 In cases with three or more groups, the Kruskal-Wallis test is often used instead of ANOVA when assumptions are violated.
• 😀 Data transformation (like converting to ordinal) can help in using non-parametric tests when the assumptions for parametric tests are not met.
• 😀 SPSS software will be used in practice sessions to directly apply statistical tests, making theory actionable in real-life situations.
• 😀 It is critical to understand both theoretical and practical aspects of statistical tests to make informed choices in data analysis.

Q & A

What is the significance of choosing the correct statistical test in research?

Choosing the correct statistical test is crucial because it directly impacts the validity and accuracy of the research findings. Using the wrong test can lead to misleading results and incorrect conclusions.

What is the difference between parametric and nonparametric tests?

Parametric tests are based on assumptions about the data, such as normality and homogeneity, and typically require interval or ratio data. Nonparametric tests, on the other hand, do not rely on these assumptions and can be used with nominal or ordinal data, making them more flexible in certain situations.

When should you choose a parametric test over a nonparametric one?

A parametric test should be chosen when the data meets the assumptions of normality and homogeneity, and when the data is interval or ratio in nature. For example, if data is continuous and normally distributed, a parametric test like a t-test would be appropriate.

What are examples of nonparametric tests, and when should they be used?

Examples of nonparametric tests include the Mann-Whitney U test and the median test. These tests are used when the assumptions for parametric tests are not met, such as when the data is not normally distributed or when the sample sizes are small.

What is the role of sample size in selecting a statistical test?

The sample size is important because it influences the power of the statistical test. With small sample sizes, nonparametric tests are often preferred as they are less sensitive to deviations from normality.

How do you decide whether to use a t-test or a Mann-Whitney U test?

If the data is normally distributed and the variance is homogeneous between groups, a t-test is appropriate. However, if the normality assumption is violated, the Mann-Whitney U test should be used as it is a nonparametric alternative for comparing two independent groups.

What is the purpose of performing a one-way ANOVA?

A one-way ANOVA is used to compare the means of three or more independent groups to determine if there are any statistically significant differences between them.

What happens if the assumptions for a one-way ANOVA are violated?

If the assumptions of normality or homogeneity of variance are violated, alternative nonparametric tests, such as the Kruskal-Wallis test, can be used to analyze the data without relying on the strict assumptions of parametric tests.

What is the Mann-Whitney U test used for?

The Mann-Whitney U test is used to compare two independent groups when the data does not meet the assumptions required for a t-test, such as when the data is not normally distributed.

Why is it important to understand the theory behind statistical tests before applying them in practice?

Understanding the theory behind statistical tests ensures that researchers can correctly choose the appropriate test for their data and research questions. It helps avoid errors and ensures that the test results are valid and meaningful when applied in practice.