Cara Uji Beda Dua Kelompok dengan Jamovi | Independent Sample t-test dan Paired Sample t-test

Summary

In this video, the presenter explains how to conduct a two-group comparison using Jamovi software. The focus is on comparing independent groups (e.g., male vs female) and paired groups (e.g., before vs after a training). The process includes checking assumptions like normality and homogeneity of variance, then selecting the appropriate statistical test: Independent Sample T-test for normally distributed data or the Mann-Whitney U test for non-parametric data. Paired data is analyzed using the Paired Sample T-test. Clear steps are provided for analyzing different types of data and interpreting results, making it easy for viewers to follow along.

Takeaways

• 😀 The video explains how to perform a two-group difference test using the software Jamovi.
• 😀 It covers two types of groups: independent (different individuals) and paired (same individuals measured twice).
• 😀 An example of independent groups is comparing the performance of men and women, where the groups are entirely different people.
• 😀 For independent groups, if assumptions like homogeneity and normality are met, an independent sample t-test can be used; otherwise, the non-parametric Mann-Whitney U test is used.
• 😀 For paired groups, an example is comparing religiosity before and after training, where the same individuals are measured twice.
• 😀 Paired group testing focuses on normality assumptions, as homogeneity is not relevant because only one group is being tested.
• 😀 If normality is met for paired groups, a paired sample t-test is used; if not, the non-parametric Wilcoxon signed-rank test is applied.
• 😀 In Jamovi, you can visually check for normality by seeing if data points align with a diagonal line in plots.
• 😀 In independent sample t-tests, the significance is checked through the p-value, and if less than 0.05, the result is considered significant.
• 😀 The video also demonstrates the analysis steps in Jamovi, including checking assumptions and performing the t-tests or Mann-Whitney U and Wilcoxon tests.
• 😀 Results from the analysis include descriptive statistics, effect size, and significance values, which are all shown in Jamovi output.

Q & A

What is the purpose of the video?

The video explains how to perform a two-group difference test using the Jamovi software, focusing on both independent and paired groups.

What are the two types of groups discussed in the video?

The video discusses two types of groups: independent groups (where individuals are different) and paired groups (where the same individuals are measured at two different times).

Can you provide an example of an independent group comparison?

An example of an independent group comparison is comparing the academic performance (measured by a test score) between male and female students.

What assumptions are checked before performing the independent sample t-test?

Before performing the independent sample t-test, the assumptions of normality and homogeneity of variance are checked.

What should be done if the assumptions for the independent sample t-test are not met?

If the assumptions are not met, a non-parametric test, like the Mann-Whitney U test, should be used instead of the independent sample t-test.

What is the significance of the homogeneity of variance test?

The homogeneity of variance test checks whether the variances of the two groups are equal. This assumption needs to be met for the independent sample t-test to be valid.

What is the role of the normality test in the analysis?

The normality test checks whether the data follows a normal distribution. If the data is normally distributed, a parametric test like the independent sample t-test can be used.

How is the independent sample t-test result interpreted in the video?

In the video, the result of the independent sample t-test shows a significant difference between male and female students' academic performance, with the p-value less than 0.05, indicating that the difference is statistically significant.

What is a paired group comparison, and how is it tested?

A paired group comparison involves comparing the same group of individuals at two different points in time, such as before and after a training session. The paired sample t-test is used to analyze this type of data.

What happens if the assumptions for the paired sample t-test are not met?

If the assumptions for the paired sample t-test are not met, a non-parametric test like the Wilcoxon signed-rank test can be used.

What does the video suggest regarding the effect size and hypothesis testing?

The video suggests that the effect size should be reported along with the test results to understand the magnitude of the difference. The choice of hypothesis depends on whether there is a prior assumption about the direction of the difference.