REKAMAN PERKULIAHAN STATISTIK : UJI NORMALITAS

Introduction

In this tutorial, we will explore the concept of normality testing in statistics, which is essential for understanding whether your data follows a normal distribution. This is crucial for various statistical analyses, including hypothesis testing. The tutorial is based on the video "REKAMAN PERKULIAHAN STATISTIK: UJI NORMALITAS" by Indah Alsita.

Step 1: Understanding Normality Testing

Normality testing assesses if a dataset is well-modeled by a normal distribution. Here are the key points:

• Importance of Normal Distribution: Many statistical tests assume that the data follows a normal distribution. If this assumption is violated, the results may not be valid.
• Common Tests for Normality:
  • Shapiro-Wilk Test
  • Anderson-Darling Test
  • Kolmogorov-Smirnov Test

Step 2: Collecting Your Data

Before performing normality tests, you need to gather your dataset. Follow these steps:

1. Identify the data source: Choose data from surveys, experiments, or other relevant studies.
2. Ensure sufficient sample size: A sample size of at least 30 is often recommended for robust testing.
3. Organize your data: Use software like Excel or statistical packages (R, SPSS, Python) to arrange your data systematically.

Step 3: Performing Normality Tests

Once your data is ready, you can conduct normality tests using statistical software. Here’s how to do it in R:

1. Install necessary packages:

   install.packages("nortest")
   

2. Load your data:

   data <- read.csv("yourdata.csv")
   

3. Conduct the Shapiro-Wilk Test:

   shapiro.test(data$your_variable)
   

   • Interpret the output: Look for the p-value. If it is less than 0.05, the data is not normally distributed.

Step 4: Visualizing Data Distribution

Visual representation helps understand the data distribution. Use these methods:

• Histogram: Plot the frequency of data points.
• Q-Q Plot: Compare the quantiles of your data against the quantiles of a normal distribution. A straight line indicates normality.

In R, you can create a Q-Q plot with:

qqnorm(data$your_variable)
qqline(data$your_variable)

Step 5: Making Decisions Based on Normality

After testing for normality, decide on the next steps:

• If your data is normally distributed, proceed with parametric tests (like t-tests or ANOVA).
• If not, consider non-parametric tests (such as Mann-Whitney U test or Kruskal-Wallis test) which do not assume normality.

Conclusion

In this tutorial, we covered the essential steps of normality testing, including understanding what it is, collecting your data, performing tests, visualizing distributions, and making informed decisions based on your findings. By following these steps, you will be able to assess the normality of your data effectively, making your statistical analyses more robust and reliable. Next, consider exploring the various statistical tests available depending on your data's characteristics.