Confidence Intervals In Statistics- Part 1

In this video we will discuss about the Confidence Intervals About Mean when Population Standard
Deviation is given in a problem statement
Subscribe My Vlogging Channel:
• How To Stay Productive...
⭐ Kite is a free AI-powered coding assistant that will help you code faster and smarter. The Kite plugin integrates with all the top editors and IDEs to give you smart completions and documentation while you’re typing. I've been using Kite for a few months and I love it! www.kite.com/get-kite/?...
All Playlist In My channel
Interview Playlist: • Machine Learning Inter...
Complete DL Playlist: • Complete Road Map To P...
Julia Playlist: • Tutorial 1- Introducti...
Complete ML Playlist : • Complete Machine Learn...
Complete NLP Playlist: • Natural Language Proce...
Docker End To End Implementation: • Docker End to End Impl...
Live stream Playlist: • Pytorch
Machine Learning Pipelines: • Docker End to End Impl...
Pytorch Playlist: • Pytorch
Feature Engineering : • Feature Engineering
Live Projects : • Live Projects
Kaggle competition : • Kaggle Competitions
Mongodb with Python : • MongoDb with Python
MySQL With Python : • MYSQL Database With Py...
Deployment Architectures: • Deployment Architectur...
Amazon sagemaker : • Amazon SageMaker
Please donate if you want to support the channel through GPay UPID,
Gpay: krishnaik06@okicici
Telegram link: t.me/joinchat/N77M7xRvYUd403D...
Please join as a member in my channel to get additional benefits like materials in Data Science, live streaming for Members and many more
/ @krishnaik06
Please do subscribe my other channel too
/ @krishnaikhindi
Connect with me here:
Twitter: / krishnaik06
Facebook: / krishnaik06
instagram: / krishnaik06

[@krishnaik06]

Hello All, iNeuron is coming up with the Affordable Advanced Deep Learning, Open CV and NLP(DLCVNLP) course. This batch is starting from 17th April and the timing will be 12:30pm to 2:30pm IST on Saturdays and Sunday and it will be live sessions. Prerequisites: Python And Basic Machine Learning The course fees will be 3000 inr+18% GST. Download the syllabus and fill the form to reserve the seat ineuron1.viewpage.co/DLCVNLPAPRIL Incase of any queries you can contact the below number. 8788503778 6260726925 9538303385 8660034247 9880055539

[@klthelep]

bro iam an eee student i have an project on ML which has been given by my senior when i excute the app.py it is giving me some error . he said that u have to update the version like that sine it was made a year before . can you help me with it . (C:\Users\thelepankl\anaconda3\lib\site-packages\sklearn\utils\deprecation.py:143: FutureWarning: The sklearn.ensemble.forest module is deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.ensemble. Anything that cannot be imported from sklearn.ensemble is now part of the private API. warnings.warn(message, FutureWarning) C:\Users\thelepankl\anaconda3\lib\site-packages\sklearn\utils\deprecation.py:143: FutureWarning: The sklearn.tree.tree module is deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.tree. Anything that cannot be imported from sklearn.tree is now part of the private API. warnings.warn(message, FutureWarning) C:\Users\thelepankl\anaconda3\lib\site-packages\sklearn\base.py:329: UserWarning: Trying to unpickle estimator DecisionTreeRegressor from version pre-0.18 when using version 0.23.2. This might lead to breaking code or invalid results. Use at your own risk. warnings.warn( Traceback (most recent call last): File "server.py", line 27, in model = pickle.load(open("model.pkl","rb")) File "sklearn\tree\_tree.pyx", line 655, in sklearn.tree._tree.Tree._setstate_ KeyError: 'max_depth' . ) this is the error can you help me with it

[@tinashechinyati6823]

Hi Krish. Is this course still available, if so can I apply while in South Africa? Thanks

[@johnhhu2137]

Where is Confidence Intervals In Statistics- Part 2 ??????

[@aamibhutta8048]

can i access this course today from Pakistan

[@gg11229__aash]

nice. pls make sure you number the videos in your playlists by chronological order the way we are supposed to study so we can learn faster. keep doing this

[@dineshpramanik2571]

You're great Krish...Understood the concept by just watching one time this video...

[@bhargavikoti4208]

Thank you👍...much needed

[@TheMISBlog]

Great Video, Thanks Mr.Krish

[@kaviarasu.thuraiarasu89]

Hi Krish, can you make a video by taking a kaggle / real dataset and explain how/why hypothesis testing , z-test, annova test we using. That will really help to understand and corelate the realtime scenerio.

[@KiranSharma-ey6xp]

Thank you for video, I was confused above z alpha, and doubt clear here

[@khizerismail9684]

Hey Krish, This is Khizer your classmate(You remember?). I was going thru CLT and CI methods to apply in real world and found your videos. I found them very helpful, you have explained very beautifully. Man I felt so happy that my classmate is doing such great work. Keep up the good work!!

[@krishnaik06]

Thanks Khizer :)

[@yohannesayana9456]

Revise ur calculations...the interval is between 464.215 and 535.785

[@manandesai4767]

Use Z distribution, when Population S.D. known or sample size>30 (even if Pop S.D. is unknown) AND Use t-distribution when Pop S.D. is unknown or SS is less than 30.

[@arsalanamin5206]

Is it some kind of rule, or a hack ?

[@23swapnilagrawal]

it helped me..thanks..for the concept clearing and logical explaining.....👍👍✌✌😊😊😊😊

[@sanjayaweerasekera4606]

Great explanation! Keep up your good work

[@arpitdadhich2012]

Sir eagerly waiting for part 2!!!!

[@rajukalyaan8750]

Hi, Thanks a lot for your videos on Data Science. I may be asking for more, do you have any notes for all the videos.

[@cagdascanturk6373]

Thanks for the video Krish, it is obvious there is quite effort. But could you please check your results whethr they are correct please? (in my calculation I found different results)

[@kartikbhargav6316]

If I conclude then 95% confidence interval means that if we were to take 100 different samples and compute a 95% confidence interval for each sample, then approximately 95 of the 100 confidence intervals will contain the true mean value .

[@shilashm5691]

Correct.. He is wrong

[@PiyushSharma-jv4fy]

Exactly. You understand it right.

[@hostwind5207]

When calculating confidence intervals for quantitative sample data, what would we use to scale the critical values to reflect variability of our sample data ? a)mean b)quantiles c)standard error d)variance

[@mahikhan5716]

krish if it is not given std deviation value how can we calculate this ??

[@databhau4507]

Please make a video about AIC and BIC

[@MuskanMadaan]

Please upload video on the other ways to answer this question

[@taniyabanerjee2609]

Hello! I have a question. If we donot have population mean, how did we get the population SD.. Would be great if someone can please explain this :|

[@Rahul_Singh_Rajput_04]

Hi Krish , I got the Answer between 464.21 and 535.78.

[@MuskanMadaan]

Sir please continue making statistics videos..

[@rohitchan007]

Can you please make part 2 of this video?

[@dr.pallaviammuthomas3550]

Sir u told Confidence interval dealing with reduction or subtraction if it crosses 0 its not significant whereas dealing with division or ratios crossing 1 is not significant ..can u plz explain one more tym

[@Zenisnoob69]

I'm starting to like this subject fr

[@gowthammurali1224]

We can use probability method if std is not given...may i answer correctly pls reply in comment Mr krish .

[@jaspreetsingh5334]

can we use CLT when SD is not given

[@jainitafulwadwa8181]

Why do you need population deviation, we have sample means which will be normally distributed. Use z test on sample means to get mean , variance and confidence intervals.

[@subhadipghosh8194]

Sir, can you please update lectures on SVM kernels and how to use SVM in regression problems? I have been waiting for your explanation on SVM kernels for so long

[@krishnaik06]

Svm kernels already uploaded...check my complete ML playlist

[@subhadipghosh8194]

@@krishnaik06 Thank you sir, let me have a look.

[@ZibaFact]

Plz also tell how to calculate confidence interval using bootstrap

[@knowledgetrip3255]

Thank you

[@thepresistence5935]

we can tell degree of freedom right sir?

[@saurabhdaund27]

when alpha is significance value why did you do 1- alpha please explain

[@srikanthnimmala4457]

Awesome.....

[@abcd54051]

The Z table value should be for 1-0.05=0.95 Not 0.975. And if you look Z table Z value=1.96 suggest the Critical Region area as 0.95 (For 2 tailed test)

[@TarunKumar-bw9lr]

1-0.5 is 0.5 not 0.95

[@abcd54051]

Yes correct.. Correction 1-0.05=0.95. (5%=0.05). Can you plz answer my query then?

[@TarunKumar-bw9lr]

Both of you are correct. You are directly looking at the Z table for two tailed tests, he is looking at the values of standard Z table

[@abcd54051]

Thanks for the explanation.. :)

[@Harshal-dk2kr]

are bhai apko 95% significance level hai na to alpha 5% hoga.....Aur yeh 2 tailed test hai na so 2.5% hoga ...so alpha banega 0.025 ....so now we need to do 1-alpha to leave the that area containing alpha 2.5%..1-0-025=0.975 ok

[@neonatologist123]

How to calculate if SD not given??

[@ajaykushwaha4233]

Awesome

[@writesomecode413]

I got lower limit as 464.215459576 and Higher Limit as 535.784540424 , Is it something I did wrong calculation ?

[@ukquaratine1019]

you have to mutiply first like 1.96*100/sqrt 30 then 500 - Ans

[@Randomvideos-dh5wg]

You are correct sudheer, the lower and upper limits are 464.2 and 535.8 respectively.

[@sarthaksampann8395]

yes me too finding this answers

[@poojajena2253]

Yup I'm getting the same answers

[@soyalbhattacharya1757]

Same

[@EmreAkanak]

Hi Krish can you please recalculate it. Because it seems you made mistake and CI is between 464.21 and 535.78. Best wishes

[@KiranSharma-ey6xp]

Same here, got range of 464 and 535, and I also have check twice, but answer is as given in comment

[@geekyprogrammer4831]

you guys are correct!

[@tannurohela6192]

same. I also got the range as 464.215 and 535.784.

[@soyalbhattacharya1757]

Same.

[@agatambidibalakrishna3734]

Catch the logic of C.I what he said , he may have made a mistake but logic is the same and yes the lower limit is 464.21 and upper limit is 535.78

[@mayurgite4050]

Why you took Z value = 0.975? I am assuming we need to take z value = 0.25 for lower limit i.e. first 2.5% AND z value = 0.975 for higher limit i.e. last 2.5% Am I missing something?? Please correct me.

[@revasseurborn2000]

1-0.025 (1 is because the whole area and subtract 0.025 to get the middle area)

[@arsalanamin5206]

Does Part # 2 of this video exists ? If yes, then why that part is not visible in the respective playlist. Correction(s) required : The answers given at 11:59 (lower limit) and 12:20 (higher limit) are wrong. The correct answers are; Lower limit = 464.22 Higher limit = 535.78 Regards.

[@rajvardhansingh9203]

Thanks, someone pointed it out.

[@1234560pratik]

During the video I was thinking that wats app notification was mine..😂😂😂

[@keshavraghuwanshi1242]

sir,is confidence interval and confidence level same?

[@siblings794]

If population standard deviation is not given then we need to proceed with sample standard deviation. Instead of sigma we use s. Thanks.

[@balapranav5364]

Hypothesis one sample t test should be done for population std not given

[@bittughosh6749]

Can someone explain why the Confidence Interval becomes higher with increase in degree of Confidence and vice versa?

[@adityaprakash1172]

As the degree of confidence increases, the width of the confidence interval also increases. This is because a higher degree of confidence requires a greater level of certainty, which in turn requires a larger range of possible values. Conversely, if we decrease the degree of confidence, the interval becomes narrower because we are willing to accept a lower level of certainty, and thus a smaller range of possible values.

[@LuciaGWShaw]

I'm understanding got the 386 and 613

[@user-cm9ml2mn6j]

How do you get a 95%?

[@ParvezKhan-ir5km]

Why the z value is 1-0.025 it should be 1-0.05 ... isn't it?? Correct me anyone if i am wrong

[@KapilSharma-co8xq]

He has used 2 tailed test. 0.05/2 = 0.025

[@ompullarwar5526]

Can we say that, Confidence Interval will give us a range within which the mean of population will lie?

[@shalinisharma2782]

I recently came cross this question "For sample size n, the margin of error is 3. How many more samples do we need to make the margin of error to 0.3? 3. X draws from the normal distribution of mu with a standard deviation of 1. Decides whether mu is not zero. ". Can anyone answer this question

[@anuragmishra8031]

You can do this using same formula of error but your question statement doesn't look proper. Do you have any ss of this?

[@shalinisharma2782]

@@anuragmishra8031 Its a question asked in Google datascientist interview. I have done using the formula of Margin of error. I assumed sigma=1 , Moe=3 , z=1.96 and calculated n with both cases moe=3(Number of sample : N) and 0.3 (number of sample : n). Then I calculated %change n-N/N. Let me know if I did it correct, or something you want to add?

[@anuragmishra8031]

@@shalinisharma2782 yeah it's correct if it's interview question then we need to take few assumptions. Basically this problem deals with 'finding sample size n' when population S.D is known. Thank you for updating your approach here. All the best!

[@KiranSharma-ey6xp]

@Shalini Sharma You need sample size 10 times more than current have, i.e required sample size 10n

[@shouryasaraswat]

@@KiranSharma-ey6xp 100n because of the square root

[@sathiyaprasath3363]

hi krish , in the second round of my interview i was asked the qusetion " how do you calculate the average petrol consumption per day in india? " i replied , by using confidence interval formula we can find the range of average petrol price . he said " i'm not satisfied with it " and he asked how will u collect the data ? , i replied we can collect it from the distributors for 1 year or few months and find the average for 1 day . he said " i'm not satisfied with it " and he replied the answer is ' i will collect data from the source and find the average' and he added a feedback that this is a basic question and you not able to answer it. krish do you agree this scenario can be solved using confidence interval ?

[@gauravratan4448]

Hi Sathiya. This looks more like a guesstimate question asked in consulting interview. A lot of videos are made on this topic on youtube on how to proceed with such questions. In such questions, we basically divide our population into categories like the well-off, middle class, and poor and then segregate them on the basis of how many vehicles they might own and which of them uses petrol specifically. The idea of asking such a question is to see how analytically you can think and come up with a solution. I hope this is useful.

[@anuragmishra8031]

This is domain specific because petrols are very much maintained in system on daily basis so you can easily have access of whole population so no need to bother about sampling and other things

[@mayurgite4050]

If standard deviation is not given then we can first calculate std. Dev. using Central Limit Theorem and proceed with above steps. Please correct me if I am wrong.

[@gauravdebnath8387]

if you are going with central limit theorem, then why to follow the above steps again...in CLT, if we plot the mean values of the n samples, then ideally it will follow a normal distribution where the mean value = population mean, and from there we can calculate the SD1 & SD2, and we then know in Normal distribution 95% values are within 2SD and that would give the answer...hope this helps and i am able to explain

[@rbanyal]

Very good explanation. But there is a small error in the calculation of 500+1.96*100/sqrt(3) =535.78 and not 613

[@joeljoseph26]

the 95% is called Confidence Level!

[@debojitmunshi3038]

I guess Sigma is not population standard deviation, in fact it is sample standard deviation

[@ankesh23569]

Chebysev's inequality

[@ankita2170]

I liked the way you speak 🔆

[@aashishadhikari8144]

If u guys still dont get the intuition, search for Khan Academy's "Confidence intervals and margin of error." :)

[@shrishaildolle5642]

take 30 or more samples in each samples take 20K sharks take mean of each sample take mean of all samples

[@dheerajmitra7613]

what is use of this knowledge if we can't get a single job from this why you don't help us to crack the company at least startup rather than making these video we can give money for that

[@0SIGMA]

You should check his channel first rather than complaining. Still if you can't find go search another channel.

[@dheerajmitra7613]

@@0SIGMA Bro I didn't talk to you or mention any we word. How can you judge that you only watched most of the videos of him and no other people has done the same thing or may be more. There are many things which I can't explain on these comments not to you not Krish and there always a two faces of coin.

[@vineetaagarwal13]

@@dheerajmitra7613 dont worry dheeraj... Have patience... You just continue your learning.... You will get a gud job..... I know u didt asked me to interfere... I'm also looking for job after 4 year gap.... So be patience and see the magic of learning....

[@agatambidibalakrishna3734]

In order to get a job and do work after getting a job, you should know all these things of statistics, so be mature enough in life and he directly or indirectly helps freshers or even experienced to earn skills to get a job or do work in job, which is either in startup or MNCs companies

[@antijihadi4139]

Worst teacher

[@jaiswalmagic1]

my notes for this video : vishaljaiswal.notion.site/Confidence-Intervals-In-Statistics-Part-1-1fa02cd62520429aa54c5a159409c8c2 thoughts and comments are welcome. 😀

[@ahsansdiary6805]

Thank you