[PART 2] KONSEP DASAR STATISTIKA INFERENSIA

Summary

This lecture introduces core concepts of quantitative research methodology, focusing on population, sample, and hypothesis formulation. It explains the difference between population and sample, emphasizing the importance of representative sampling. The speaker covers both parametric and non-parametric statistics, highlighting tests like t-tests, ANOVA, and chi-square. Students are guided on how to select the right statistical test based on data scale and characteristics. The importance of using statistical software like SPSS is also discussed to perform hypothesis testing efficiently. Overall, the lecture equips students with the foundational knowledge for conducting quantitative research and data analysis.

Takeaways

• 😀 Understanding the difference between **population** and **sample** is crucial in quantitative research. Population refers to the entire group being studied, while a sample is a subset selected for the research.
• 😀 In quantitative research, the **sample size** is determined using specific **sampling techniques**. This helps to avoid researching the entire population, which can be inefficient.
• 😀 A **null hypothesis (H0)** suggests no relationship or effect in the data, while an **alternative hypothesis (H1)** indicates the presence of an effect or relationship.
• 😀 Before conducting statistical tests, researchers must perform **prerequisite tests** such as **normality tests** (to check if data is normally distributed) and **homogeneity tests** (to check if variance is consistent).
• 😀 **Parametric statistics** require data that is normally distributed and has homogeneous variance. Common tests include **t-tests** and **ANOVA**.
• 😀 **Non-parametric statistics** can be used when data does not follow a normal distribution or has unequal variance. Tests include **Chi-square**, **Wilcoxon**, and **Rank Sum tests**.
• 😀 Choosing the right statistical test depends on the **type of data** (nominal, ordinal, interval, ratio) and the assumptions about the data’s distribution and variance.
• 😀 **Nominal** and **ordinal data** typically require **non-parametric tests**, while **interval** and **ratio data** are usually analyzed using **parametric tests**.
• 😀 A good researcher must be familiar with the basics of using **statistical software** (e.g., SPSS or Excel) to perform analysis, including normality and homogeneity tests.
• 😀 Researchers should aim for a **clear understanding** of how to formulate hypotheses, select appropriate tests, and interpret data accurately to draw valid conclusions in quantitative studies.

Q & A

What is the difference between a population and a sample in quantitative research?

A population refers to the entire group that is being studied, while a sample is a subset of the population selected for analysis. A sample is used when studying the entire population is impractical due to time, cost, or logistical constraints.

How can you identify the population in a research study?

The population in a research study is usually identifiable from the title of the study. For instance, in a study on the performance of 'students in class 10 SMK in Pontianak', the population is clearly the students in that specific class at that specific school.

What is the importance of using a sample in research?

Using a sample allows researchers to collect data from a manageable number of participants that accurately represent the population, making the study more efficient while still ensuring reliable results.

What are null and alternative hypotheses in research?

A null hypothesis (H0) asserts that there is no effect or no relationship between variables. An alternative hypothesis (H1) suggests that there is an effect or a relationship. These hypotheses are tested to determine the outcome of the research.

What is the role of statistical tests in research?

Statistical tests are used to analyze data and test hypotheses. They help determine whether the observed results are statistically significant and whether they support the null or alternative hypothesis.

What is the difference between parametric and non-parametric statistics?

Parametric statistics assume that the data follows a specific distribution (like normal distribution) and have homogeneous variances. Non-parametric statistics do not require these assumptions and are used when the data does not meet the conditions for parametric tests.

When should parametric statistics be used in a research study?

Parametric statistics should be used when the data follows a normal distribution and has homogeneous variances. Before using parametric tests, researchers need to perform tests for normality and homogeneity.

What statistical tests fall under parametric methods?

Common parametric tests include the T-test (for comparing two groups), ANOVA (for comparing three or more groups), regression analysis (for examining relationships between variables), and correlation analysis.

What is the significance of data scales in selecting statistical tests?

The scale of data (nominal, ordinal, interval, or ratio) determines which statistical test is appropriate. For example, parametric tests are typically used with interval or ratio data, while non-parametric tests are used for nominal or ordinal data.

How can researchers ensure they are using the correct statistical test for their data?

Researchers must first identify the scale of their data (nominal, ordinal, interval, or ratio) and then select the appropriate test based on whether the data meets the assumptions for parametric testing, such as normality and homogeneity. If these assumptions are not met, non-parametric tests should be used.