Summary on Industry Demonstration of Hypothesis Testing

So what did you learn in this session?

1. T-distribution:
   • A T-distribution is used whenever the standard deviation of the population is unknown
   • The degrees of freedom of a T-distribution is equal to sample size n - 1
   • For sample size ≥ 30, the T-distribution becomes the same as the normal distribution
   • The output values and results of both t-test and z-test are same for sample size ≥ 30
      
2. Two-sample mean test - paired:
   • It is used when your sample observations are from the same individual or object
   • During this test, you are testing the same subject twice
      
3. Two-sample mean test - unpaired:
   • During this test, you are not testing the same subject twice
   • It is used when your sample observations are independent

4. Two-sample proportion test:

   • It is used when your sample observations are categorical, with two categories

   • It could be True/False, 1/0, Yes/No, Male/Female, Success/Failure, etc. 
      

5. A/B Testing:

   • A/B testing is a direct industry application of the two-sample proportion test

   • It is a widely used process in digital companies in the ecommerce, manufacturing and advertising domains

   • It provides a way to test two different versions of the same element and see which one performs better

You can download the lecture notes for the module from below. The lecture notes include a summary of the entire module.

(Note: On page 14, the image for positive Z-value mistakenly shows one for a negative Z-value.)