Anova T test Chi square When to use what|Understanding details about the hypothesis testing

[@UnfoldDataScience]

Access Hindi, English courses here- www.unfolddatascience.com/s/store

[@bipulray2294]

Greatest teachers actually teach on humble white boards ❤️❤️❤️❤️thank you sir for this awesome explanation

[@YashpalNSharma]

Sample is an example set of a data population.
This video should have more views! I have read multiple blogs and sources but couldn’t understand things as easy as explained here.
Thank you again Aman! 🙏🏻

[@UnfoldDataScience]

Glad it was helpful Yashpal.

[@bhavikdudhrejiya852]

Very nice video.
Learning points of the video:
1. Test on : One continues features , Hypothesis on : mean , Comes under : One Sample Test , Name of Test : One Sample T-Test , Accept & Rejection hypothesis criteria on what scale comparison : p value
2. Test on : One categorical features - Two subclass , Hypothesis on : proportion between two class , Comes under : One Sample Test , Name of Test : One Sample Proportion Test , Accept & Rejection hypothesis criteria on what scale comparison : p value
3. Test on : Two continues features , Hypothesis on : correlation , Comes under : Two Sample Test , Name of Test : Correlation with T-Test , Accept & Rejection hypothesis criteria on what scale comparisons : correlation & p value
4. Test on : Two categorical features , Hypothesis on : proportion between two class based on other class , Comes under : Two Sample Test , Name of Test : Chi-Square Test , Accept & Rejection hypothesis criteria on what scale comparison : p value
5. Test on : One categorical feature - Two subclass & One continues feature , Hypothesis on : Difference of mean between two class(variance) , Comes under : Two Sample Test , Name of Test : Two Sample T-Test , Accept & Rejection hypothesis criteria on what scale comparison : p value
6. Test on : One categorical feature - More than two subclass & One continues feature , Hypothesis on : Difference of mean between more than two class(variance) , Comes under : Two Sample Test , Name of Test : ANOVA , Accept & Rejection hypothesis criteria on what scale comparison : p value

[@UnfoldDataScience]

Amazing. Thanks a lot for making me believe that it was understood. Keep learning.

[@iktejsinghjabbal4145]

I have'nt come across any video with a simpler explanation of these basic statistical analyses. Kudos to the tutor for making it so simple to understand!

[@UnfoldDataScience]

Glad it was helpful Iktej.

[@salonisingh6032]

I am speechless. i am doing Phd . and currently doing course work of phd. our faculty did not taught this.i was restless for months, saw numbes of videos on youtube but nothing solved my problem. one simple video of 9 min solved my every doubt and now i am confident that i can do this. thank you so much sir.

[@RachelLi-l6o]

Dude you are awesome. I will have my first data science technical interview tmr since I did my career transition from finance. I hope everything will go on well

[@kaciahanson5169]

You just saved my life with this assignment! Thank you!

[@UnfoldDataScience]

Thanks a lot.

[@SoumyaDasgupta]

The people who reacted dislikes came here for Gym videos for abs. Awesome explanation bhai.

[@UnfoldDataScience]

Thanks Soumya :)

[@arpanchakraborty2557]

Absolutely right 😂

[@adhikarieswar1372]

Nice explanation sir

[@ramu7762]

I have seen many videos but your explanation is simple and easy to understand. Thank you very much.

[@UnfoldDataScience]

Welcome Ramu.

[@comedyworld4730]

This is first time I got to know which test is applicable in which situation.
Thank you so much sir.
Please make more videos on statistics
Like PCA

[@UnfoldDataScience]

Keep watching

[@kamran_desu]

Very clear explanations.
Just to point out that correlation also has p-value for null hypothesis that there is no correlation.
I think its through the F-test (not 100% sure).
Correlation coefficient gives us the strength and direction while its p-value gives the confidence in the correlation claim.
E,g, the correlation between two data points will be 1, since its a perfect fit, however, p-value will be high since there's no confidence given low sample size.
Actually that raises another question linked to this video.
When do we use F-test? Anova?

[@UnfoldDataScience]

Yes absolutely right abt correlation. F-test is more of generic high level test whereas anova is specific type of procedure that produces f statistics.

[@divyamsaxena3198]

Beautiful... Only one word... Can't thank you enough brother... I thank god that I found you...

[@UnfoldDataScience]

Wow, thank you!

[@salonisingh6032]

I am speechless. i am doing Phd . and currently doing course work of phd. our faculty did not taught this.i was restless for months, saw numbes of videos on youtube but nothing solved my problem. one simple video of 9 min solved my every doubt and now i am confident that i can do this. thank you so much sir.

[@UnfoldDataScience]

Thanks Saloni. I put your comment on my LinkedIn. Your comments are precious.

[@salonisingh6032]

@@UnfoldDataScience thank you sir

[@harshitabisht1789]

Most simplest explanation of these topics I have ever studied. Thnx so much

[@shahzebshah7368]

Thank You Very Much, Sir.
It Takes A Lot Of Time And Brainstorming To Summarize These Concepts In Videos Like This. I Have Been Looking For This Video Since Very Long. This Video Removes All Of My Doubts.

[@manikantareddy1830]

Best one among all I watched. Cleared all my doubts. Such a great one, simplified to the core.
One small doubt:
My data is nominal Vs Nominal
2 sample
But more than 2 categories in outcome:
Example:
Type of placenta Vs Baby weight (took it as nominal)
Variable: Type of Placenta ( Normal / abnormal)
Outcome variable
Birth weight ( Low / Normal / high)
I want to see the association of Type of placenta with category of birth weight
Which test I can do for it
Thank you sir

[@UnfoldDataScience]

Chi square

[@Birdsneverfly]

Very very good video. Excellent explanation. As a Data Scientist, I can only admire this explanation.

[@UnfoldDataScience]

Thanks for your kind words 😊

[@rooppsychology6958]

Excellent lecture sir. Helpful for Ph.d scholars. Very helpful. Easy to understand

[@UnfoldDataScience]

Thank you

[@yaksh82]

very well explained even a layman can understand why these test is used for. Thanks a Lot brother.

[@destinyplummer3176]

All the years in my undergrad...it finally makes sense, thank you!

[@grievingflowers]

studying for media data science subject from korea university here :') thank you so much for your video!!

[@ravichaudhary4892]

Thank you so much bhai..... Specially for explaining so clearly that what is the difference between one sample and two sample..

[@UnfoldDataScience]

Welcome Ravi.

[@santhoshgattoji7517]

Perfect summary of the tests! Thanks again Aman. Now sampling : " this is the process of taking a sample of data from the actual population" and answer to your Q) "if we have numbers 1 to 100 can 1 to 10 a sample? A) generally NO because a sample should consist a min of 30 data points.

[@UnfoldDataScience]

Thanks Santhosh. my follow up question - If I tell you to take 30 sample from above data, can u take number 1 to 30? :)

[@santhoshgattoji7517]

@@UnfoldDataScience no aman, these 30 should be randomly selected from the population.

[@purnahangsubba9400]

Very precise and clear explanation, thank you sir, would love to watch more videos on subject....Beautiful presentation

[@UnfoldDataScience]

Thanks a lot.

[@vikrantmahajan142]

one of the best videos covering these topics.

[@Natarajan7565]

Sample/samples are a part of researching masses which is an ideal representation of the masses

[@soheilaahmadi4807]

Thank you so much for these amazing tutorials. I am working on the ANSUR dataset which contains anthropometric measurements. there are two sets of data one for males and one for females. For females, we have around 2000 samples and for males, 4000 samples. There are about 93 features that are the same for both genders. Features such as weight, height, waist circumference and etc. I want to concatenate these two datasets and do some clustering analysis on them means looking at them as just humans and ignoring the gender. I would like to know if I can do that or I need to do some analysis before that to find if there is a significant difference between each feature for different genders. Like comparing waist circumference for males dataset with waist circumference for females dataset. Which test should I apply? and what other things should I consider? Regards

[@UnfoldDataScience]

Both ways possible, either u combine data first then analyze or vice versa.
Coming to tests, many test can be performed depending on my variable type. For example hypothesis related to waist circumference can be done using anova

[@salehmuhammad6811]

Brilliant explaining techniques bro. God blessed you.

[@a.a7493]

Man you just explained it sooooooo well wow… best explanation on utube i spent so many time looking and wasting time not getting it but you just killed it ❤

[@UnfoldDataScience]

Thank you 😇

[@haillatesfaye3579]

Thanks so much. I need more from you ....... on ordinal, multinominal and poison logistic regression...

[@johnvarvatoss142]

BEST EXPLANATION EVER .. THANK YOU MAN

[@UnfoldDataScience]

My pleasure, please share with friends as well.

[@ramkiran3685]

You are explaining so nicely which many people are not doing. Keep it up

[@UnfoldDataScience]

Thanks Ram. Hope you are doing well

[@nikhilpawar7876]

Best statistics video on TH-cam 🔥

[@UnfoldDataScience]

Appreciate that comment Nikhil

[@kingp4033]

This was so helpful! Thank you so much!

[@kaiotoo7640]

very good and simple explanations. Thanks a lot

[@UnfoldDataScience]

Thank you

[@mr.trinadhnookathotiassist6071]

Very simple and effective Aman

[@TonyChipedza]

Wonderful and simplified explanation, i needed this..

[@carolMuRugi-65]

Wow! What a great explanation. I Understood everything. Thank you.

[@UnfoldDataScience]

Thanks Carol.

[@drrajkishorsharma]

A VERY NICE VIDEO WITH SUCH AN EASY EXPLANAION

[@UnfoldDataScience]

Thanks Raj.

[@shawgaa1457]

Best explanation I have found, thank you so much

[@y.suresh449]

Very simply and nicely explained.

[@sitharaayesha792]

Thank you very much for this clear and crisp explanation. It has been extremely helpful to understand the concept :)

[@UnfoldDataScience]

Glad it was helpful Sithara. Thanks for watching.

[@ashitnayak1912]

Awesome explanation. Got what I came for. ❤

[@ezequieldeleon93]

This is a world class video. Thank you so much.

[@UnfoldDataScience]

Glad you found it helpful 😊

[@Shrutiijaiswal]

Thank you so so so much sir!
Amazing to see your method of teaching. Tomorrow is my exam and this is indeed helpful

[@UnfoldDataScience]

All the best Shruti. Hope exam was good.

[@nup2943]

You simplified everything about all tests...Thank you so much🙂

[@UnfoldDataScience]

Welcome

[@Kumarsashi-qy8xh]

Thanks for giving all such good informations

[@UnfoldDataScience]

Welcome.

[@shubhammittal2367]

Amazing , now gets clear

[@asmitakhanna4371]

Very well explained sir, just 1 confusion difference between cat.l to cont. And cont to cont.
I.e. when to apply two sample t test and logistics regression

[@AkshayRakate]

crisp and clear explanation !!!!!!!!!

[@UnfoldDataScience]

Glad you liked it Akshay.

[@k.venugopalasstprofessor4880]

GOD BLESS YOU..I think I elder to you sir.... excellent.... explanation.... great..you resembles saint RAMANIJACHARYA... who told all secrets to the world inspite of restrictions from the almighty..

[@UnfoldDataScience]

So nice of you. Thanks a lot.

[@RohitRaj-ou7br]

Sir, your way of clearing concept is another level 🙏

[@UnfoldDataScience]

Thanks Rohit, plz share with others as well

[@pembawangchuk5429]

thank you for your videos.
I have a difficulty in which statistical test is best for new food product development project.

[@UnfoldDataScience]

Glad it was helpful!

[@36revanth]

superb man , very easily understood. appreciate it

[@lokesh4391]

Thank you so much Aman . You videos are very clear and able to understand very easily.

[@UnfoldDataScience]

So nice of you Lokesh.

[@sandipaghosh8850]

Awesome explanation...Thank you a lot for all these videos...

[@UnfoldDataScience]

Thanks Sandipa.

[@adityabenere6004]

Thanks sir amazing .. simple and to the point explanation 🔥🔥

[@UnfoldDataScience]

Thanks Aditya.

[@rashijain7085]

You are a good teacher

[@shurovi123]

Very well explained and to the point. Thank you so much.

[@MaserekaEric-cv8dt]

Very wonderful discussion. Thank you so much.

[@debipaikaray9084]

Great Video . Thanks

[@tnmyk_]

Amazing explanation! Well done!

[@UnfoldDataScience]

Glad you liked it Tanmay

[@trysonchisenga9406]

I have been enlightened, thank you

[@temiyeoluseun297]

Thank you so much. best video on subject

[@UnfoldDataScience]

Thanks Temiye.

[@unexpected2004]

This is great! So clear and precise !

[@UnfoldDataScience]

Thanks a lot :)

[@ritachaudhary5780]

Right

[@shashireddy7371]

Great explanation
Thanks Aman

[@annukaushik6803]

Thik is awesome outstanding

[@UnfoldDataScience]

Thanks Annu.

[@ritachaudhary5780]

Thank u greatly. You really cleared all my confusion.
Sir can we use one way anova for one categorical having two classes instead t test??

[@UnfoldDataScience]

Thanks Rita. YEs we can.

[@mousamibinckota]

Very well explained

[@UnfoldDataScience]

Thanks Mousami.

[@monikagadre6440]

Excellent explanation in simple words

[@UnfoldDataScience]

Thanks Monika.

[@peabeam6231]

Thank you. Easy to understand. Quick question: how would you categorize data that is an answer to a question "how many times a week?". The answer is always a number 1-7. Categorical?

[@vineetkaur1667]

Yes Categorical , I think

[@UnfoldDataScience]

Should be treated numerical I think, because its a count data, What do u guys think?

[@akshaypatil8155]

Sir for logistic regression you mentioned, continous as independent, categorical as 'target'? What do you mean by target? What do you mean by independent in this case?

[@UnfoldDataScience]

Hi Akshay,
independent variable is also known as "features or predictors"
dependent variable is also known as "target or response"

[@susmitsekhar5100]

Very nice explanation...I hope you will upload the next video very soon..

[@UnfoldDataScience]

Welcome Susmit. Sure. Happy Learning.

[@ankur8688]

To the point. Hats off.

[@UnfoldDataScience]

Thanks Ankur.

[@sureshbabuneerati6733]

excellent explanation sir

[@UnfoldDataScience]

Thanks a lot.

[@nasrullahturke4480]

Great overview brother ❤️ Really great 👍

[@UnfoldDataScience]

Thanks a ton

[@nishantbisen2080]

nicely explain ,thanks a lot sir

[@UnfoldDataScience]

Welcome Nishant.

[@Shanjida_tasnim02]

Best tutorial sirji

[@geetadandin4302]

Explained very well Sir

[@fiilixwonder7675]

You are a blessing 🙌

[@genogeno5220]

Thank you for this simple explanation. Clears all my questions now. I have subscribed and will follow up with your videos. You rock 💪👏

[@UnfoldDataScience]

Glad to be helpful. Thanks for your positive feedback 😊.

[@samirafursule8590]

This is super informative 👏

[@UnfoldDataScience]

Thanks Samira.

[@nehakumarisingh2920]

Thank you...can you please make video on difference in correlation and regression

[@UnfoldDataScience]

Thanks Neha, I have videos on correlation, covariance and regression, pls search it in my channel u will get ur doubts clarified.

[@janelynpheyloyola8988]

Thank you so much. Very well explained. This was very helpful 😊

[@akshitajain3174]

Nice explanation

[@UnfoldDataScience]

Thanks Akshita.

[@mdtayyab121]

Thank you so much, you really unfolded it

[@UnfoldDataScience]

Glad you found it helpful 😊

[@muhammedmk5650]

Good explanation brother...thanks a lot ...

[@UnfoldDataScience]

Welcome.

[@santoshkumargouda6270]

please make videos on A/B testing.

[@14febksa]

nice explanation sir what is difference between t test and student t test and how to justify their use

[@UnfoldDataScience]

Thanks Jawed.

[@spicytuna08]

awesome clarity!!!

[@UnfoldDataScience]

Glad it was helpful! pls share with friends.

[@thisumamarasinghe8171]

Sampling is taking a subset of individuals,objects or observations selected from a population to estimate characteristics and make inferences for the entire poplulation

[@mustahedinhoque4430]

If there is two continents variable then we do co-relation coefficient as you said ..can we do t test for two independent continuous variable.... Or is it necessary the continuation variable should be dependent.

[@vineetkaur1667]

Thanks for the simplified explanation, keep making more such content

[@UnfoldDataScience]

Thank you Vineet, I will

[@Islamicquranquotes786]

I m really impressed...I will be waiting for more of ur videos.... awesome explaination ❤️❤️

[@UnfoldDataScience]

Thank you so much 😀

[@Dr.Sumesh]

Nice explanation...

[@UnfoldDataScience]

Thanks Sumesh.

[@subhashachutha7413]

Wow nice video

[@UnfoldDataScience]

Thanks Subhash, happy learning. Tc

[@mecareless179]

Welll explained sir

[@archanabottu665]

Thank you! This is very helpful.

[@UnfoldDataScience]

Welcome Archana

[@jintoej2149]

Thank you for your explanation

[@swayansidhamishra3257]

Sampling is a technique of selecting subset of population to meke statistical inferences from them and to estimate characteristics of the total population