# Hypothesis Testing

Discussion Forum 3

What is hypothesis testing? Explain the general process and the steps included in conducting a hypothesis test? What is the difference between parametric and nonparametric hypothesis testing?

Hypothesis Testing

Hypothesis testing, in my opinion, is one of the most important concepts that is utilized in statistics. In statistical analysis, a hypothesis can be described as a postulation about a population parameter. Where the assumption being made, may or may not be true. The goal of hypothesis testing is to either reject or accept the null hypothesis. Defining hypothesis testing is described as the process of choosing hypothesis for a specific probability distribution that is based on observed data (Tutor Vista, n.d.).

There are 5 important steps in the process of hypothesis testing. The steps included in conducting a hypothesis test are:

3. Set the Significance Level. In step 3, one would calculate the test criterion based on the values that were obtained from the sample.

• Specify the Null Hypothesis and specify the Alternative Hypothesis. This step is where a null and alternative hypothesis is identified to be tested.
• Identify the test criterion to be used.

4. Calculate the Test Statistic and Corresponding P-Value. During this step, one would find the critical values within the required levels of significance.

5. Drawing a Conclusion. Lastly, in step 5, one would conclude whether to either accept or reject the null hypothesis.

(Tutor Vista, n.d.)

Parametric testing is the hypothesis test that provides generalizations for making statements about the mean of the population. Nonparametric testing is the hypothesis teat that is not based on underlying assumptions. For example, it does not require population distribution that are signified by specific parameters. One difference between parametric and nonparametric hypothesis testing are that in a parametric test, the statistic is based on distribution whereas in a nonparametric test, the statistic is arbitrary. Additionally, the measure of central tendency for a parametric test is mean and the measure for nonparametric is median (Surbhi, 2016).

References