Skip to main content

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. ...

What is Hypothesis Testing and Why it is used - simplified (Part 1)

Hypothesis Testing is an interesting topic for the interviewers to decide whether the interviewee is good at statistics. Unfortunately, This is the topic on where Most of us fumble upon.

In this blog, I will try to explain what and why exactly the Hypothesis Testing is needed in layman way. Let’s get into it.

 

Whenever I listen the word Hypothesis Testing, The following quote comes into my mind.                      

“INNOCENT UNTIL PROVEN GUILTY”

 

Let’s understand a practical scenario, what will happen in a court room if a person is guilty of a crime?

1. Firstly, The Judge always presumes that the person is Innocent.

2. Secondly, The Lawyer tries to prove that the person is guilty based on the Evidence. 

 

Here, the lawyer is indirectly trying to reject the Judge’s presumption based on the collected evidence. This is what exactly happens in Hypothesis Testing.

There will be a fact and A claim is made against the fact. We need to try to prove that the fact is no more valid so that the claim will become true. 

 

Simple right.

Now if you got some understanding of the above scenario, you almost understood the Hypothesis Testing.

 

Hypothesis – A claim that we want to investigate or test.

Hypothesis Testing is a technique which helps us to get rid of certain element of randomness in a given claim based on the data. 

The Hypothesis Testing is used to know about the population parameters based on sample data taken from it.

Hypothesis Testing is taken from the Inferential Statistics to determine with how much probability the given Hypothesis is True. It evaluates two mutually exclusive statements about the population to find which statement is best suited based on sample data.

 

Real Time Example:

Scenario: Drug A heals the pain in few hours, A Scientist came and claimed that the new Drug B heals the pain much faster than the Drug A.

Claim: Drug B takes less time to heal the pain than Drug A.

 

In this scenario, we can’t give the Drug B to millions of people directly without any testing. A clinical trial is to be done.

 

Case A:

Let’s say there are 100 volunteers, 50 people took Drug A and 50 people took Drug B.

Result: Drug A took 3hrs to heal and Drug B took 1hr to heal.

Now can we decide the claim that Drug B is better than Drug A is true?   Obviously, No. Because we tested on only 100 people out of Billion people. So the result may be a random luck.

 

Case B:

Let’s say there are 1000 volunteers, 500 people took Drug A and 500 people took Drug B.

Result: Drug A took 3hrs to heal and Drug B took 1hr to heal.

Now can we decide the claim that Drug B is better than Drug A is true?   Obviously, Again No. Because there might not be any diversity in the two groups. All people that took Drug B may be younger with good immune power than the people who took Drug A. so again the result may be a random luck.

  

So, Here It is hard to come to the conclusion about the claim. There comes Hypothesis testing which helps us to figure out the observed result is not due to random chance but there is a reason behind it.


Note: Since collecting the data from whole population is impossible, sample data is taken and try to decide whether the claim is true or not.


In the next blog I will explain what are Null Hypothesis and Alternate Hypothesis and how to identify them. please find the below link for part 2. 

Part 2: How to decide Null and Alternate Hypothesis? - simplified

Part 3: How to Conduct Hypothesis Testing step by step? - Easy and Elegant

If there are any queries, please specify in the comments below...

For More Content please follow...

 


Comments

Popular posts from this blog

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. ...

Simple Understanding of INCEPTION_V3 and it's Architecture (part 3)

INCEPTION_V3 Prerequisites:  VGGNet OR VGG16:  VGG16 Architecture   By looking it's name, everybody think's that it is a complicated story just like the movie INCEPTION. But trust me, I will prove you that it is wrong by explaining in the most detailed way. Till now, If we take a layer in any neural network we only applied single operation like convolution or maxpooling and also with fixed kernel size for the whole layer.  But Now, The idea is, why can't we use all the operations in a single layer at a time. There comes INCEPTION_V3. Lets zoom a single layer in the inception_v3, source: It's a screenshot from AndrewNg class If you observe the above figure, convolution operation with kernel sizes 1x1,3x3,5x5 and the max-pool operation, all have applied at a time. Here comes a problem, COMPUTATION. only from single layer we are getting billions of computations. For example, lets do a simple mathematical calculation here, Note: To understand this you need to know how c...

Simple Understanding of VGG16 and it's Architecture (part 2)

Vgg16 Architecture:   Prerequisites:  ALEXNet  :  ALEXNet Architecture   * vgg refers to visual geometry group who has developed vgg16 architecture. * 16 refers to number of layers. VGG16 or VGGNet is a convolution neural network and it is a simplified and better version of Alexnet. Remembering Alexnet architecture is very difficult, Later on 2014, vgg16 came as an architecture and it is very simple to remember. VGG16 is very simple where:  ·   It is built on Convolution operations with fixed kernel_size=(3x3), padding=’same’, and stride=1 for all Convolution layers. ·     And also Maxpooling operation with pool_size=(2x2) and stride=2 for all Maxpool layers.       Let's see the architecture of vgg16 source:https://qph.fs.quoracdn.net/main-qimg-e657c195fc2696c7d5fc0b1e3682fde6 If you observe the figure, As said all convolution layers have 3x3 kernels and all maxpool layers have size of 2x2. Note 1: For...