How to conduct Hypothesis Testing step by step - simple and elegant (part 3)

Step by Step procedure in Conducting the Hypothesis Testing:

prerequisites: 

Part 1: What is Hypothesis Testing and When it is Used?

Part 2: How to decide Null and Alternate Hypothesis?   

              

https://www.isixsigma.com/

 

Before diving into the steps, first let’s understand the Important Terminology we need to understand:

Null Hypothesis: It is a well-established fact which is believed by all the people. It can also defined as an Assumption that treats everything equally and similarly.

Alternate Hypothesis: It is a new claim made against the Null Hypothesis. If we have enough evidence against the Null Hypothesis we will reject Null Hypothesis.

P-value: Probability of Null Hypothesis being true.

Significance level: probability of rejecting the Null Hypothesis when it is true. It is a critical point where we decide whether the Null Hypothesis is rejected or not.

Generally, the significant level will be 0.05 which means a 5 percent risk while concluding some difference exists when there is no actual difference.

Note: Lower the significance level, you need stronger the evidence to reject null hypothesis.

The significant level helps to conclude which hypothesis the data is supporting. It is done by comparing p-value with significant level.

 

Conducting the Hypothesis Testing step by step:

1.     State null and alternate Hypothesis:

Define the Null and Alternate Hypothesis from the given problem.

 

2.     Collect the data and conduct the experiment:

Gather the sample data and experiment to get the observed value.

 

3.     Set the significance level:

Define a critical point at which you want to reject Null Hypothesis.

 

4.     Determine p-value

We need to find the Probability of finding the observed value (we got in step 2) when the null hypothesis is True.

Need to do certain statistical tests based on the type of data to get the p-value.

Examples of statistical Tests:

1.     T – Test

2.     Z – Test

3.     Chi – Square Test

4.     Anova Test

 

5.     Decide whether to reject the Null Hypothesis or not:

Take the decision by Comparing the significant value and p-value.

      if  p-value < significant level:

                                                    Reject Null Hypothesis

                                     else:

                                                   Accept Null Hypothesis

 

Let’s have better understanding about the significant level and p-value which can helpful in interviews:

1.     Significant level is decided based on Domain Knowledge.

2.     If p-value < 0.01 it tells that there is very strong evidence against Null Hypothesis.

3.     In layman way, it tells that only in 1% of cases the null hypothesis is True and remaining 99% of cases the Alternate Hypothesis is True.

 

p-value (p) and significant value (alpha) comparison	Evidence against Null Hypothesis
p-value < 0.01	very strong evidence
0.01 < p-value < 0.05	strong evidence
0.05 < p-value < 0.1	mild evidence
p-value > 0.1	No evidence