Hypothesis testing Practical Implementation Part 2|Hypothesis testing with data example in python

Hypothesis testing Practical Implementation Part 2|Hypothesis testing with data example in python
#HypothesisTestingPython #UnfoldDataScience

Hi Everyone,
My name is Aman and I am a data scientist.

About this video:
In this video I discuss about hypothesis testing techniques in python.
I discuss hypothesis testing with some real life example to make viewers understand how hypothesis testing can be implemented in python using various techniques. I discuss in detail the usability of t-test,anova,non parametric test and stationary test
Below questions are answered in this video:

1. How to do hypothesis testing in python
2. Parametric vs Non parametric hypothesis testing
3. Stationary test in hypothesis testing
4. T-Test hypothesis testing
5. Anova hypothesis testing
6. T-test and Anova practical examples in python

About Unfold Data science: This channel is to help people understand basics of data science through simple examples in easy way. Anybody without having prior knowledge of computer programming or statistics or machine learning and artificial intelligence can get an understanding of data science at high level through this channel. The videos uploaded will not be very technical in nature and hence it can be easily grasped by viewers from different background as well.

Join Facebook group :

Follow on twitter : @unfoldds

Follow on Instagram : unfolddatascience

Watch python for data science playlist here:

Watch statistics and mathematics playlist here :

Watch End to End Implementation of a simple machine learning model in Python here:

Learn Ensemble Model, Bagging and Boosting here:

Access all my codes here:

[manoharkulat]

Clear explanation, now my confusion gone away. Thanks Aman👍

[souravbiswas]

Quality of a good teacher is how to make the students understood in the simplest way, and you have that. Keep up doing this 👍👌

[rajeshn]

Very nicely explained with simple examples, thanks a lot Aman for sharing the knowledge

[r]

My doubt is when to perform parametric and when to perform non parametric test..for which

[ravneetkaur]

In parametric anova, variables are categorical (2 classes) vs continuos but scores are continous variables only. please explain...
Also, generally if p>0.05 we reject alt hypothesis that means it should print "same distrubtion of scores" right? If not then plz tell what have u considered as null and alt hypo?
why in every test you have taken null hypo as "change/ different ditrubution" because according to innocent until proven guilty, null should be both distributuons are same and there is no change
in stationarity, why are we considering 3 consecutive values, why not 2 or 4 etc why only 3 ?

[sabaamanollahi]

Thanks for the great video, in 9:16 --> tstat instead of stat ( in the print function)

[mukeshkumar-khfh]

Hi Aman if ques is about the average time required to complete the request of each complaint type, where we have more than 2 category of complaint, then we use z, t test or annova??, and should we consider two tail or one tail??

[sudipnarayanchoudhury]

@Aman..
Can you please tell me what is the difference between these three statements.
--> Observations/data are normally distributed.
--> Observations/data are identically distributed.
--> Observations/data are uniformly distributed.

[hasneemzamananni]

If I am using two variable purchase of organic food and price... And my hypothesis is PURCHASE rate is related with the organic food price then which test I should use??

[dhineshmathiyalagan]

Hi Aman ..Thanks for explaining the concept, it is really useful. Can you please help me understand below on stationarity test.

At 11:15 frame .. you mentioned that we use different timeframes(3 day window) from the same sample for 'adfuller test'. I would like to understand if the window size is fixed or is that something user can modify.

[ajaykushwaha-jemw]

Hi, They way you teach reminds me of my group studies, which were more effective than class studies. Your explanation are very nice, example you to give to understand concept are very nice. Thank you for making such nice video. I have request. Suppose we are working in Health sector at that time we wont take p-value as.05 it has to me much less. So how can we reduce p-value, to understand this can you make a video on Health care domain.

[prafulturanur]

Hi
If we convert the categorical variable to numeric then instead of applying different test we can only apply the correlation and come to know the relationship beween the columns
Is this method a good approach or not. Could you please suggest

[shalinigupta]

it would be great if you can create a video on z-test and t-test and which test to consider while solving a case study

[quamar]

Can you make a video on used case project where these hypothesis testing used and show how different value effects the model

[gajariaanand]

Thank you for making this video sir, however, it would have helped more if you had stuck to the wine dataset throughout the video and explained these concepts because I can just google the python code to implement the test, but how to implement this on a realtime dataset is hard to find an example. I was expecting that kind of explanation from this video, but eventually, I was disappointed, However, I appreciate your work.

Thank you.

[k-ws]

Aman rather than doing t test on one feature with two sub groups can we do it with two different numerical features. ?

[bijaynayak]

Hi Aman, very good contents are captured.
question is when we say sample vs population, can we say the collected or historical data sets are sample and unseen or live data is population?

[thepresistence]

Bro you have told t test is used for 2 classes in categorical and one sample In numerical? but we have used the same feature right?

[diwakermishra]

Great tutorial
I think the second part of hypothesis testing is placed before first part in this playlist.

[souravkumar]

sir, can u please provide the jupyter notebook for both part?