Sir you have no idea how good you are as a teacher, this playlist has really helped me to learn a lot about the Applied Statistical Analysis. I request you to please complete this playlist. Thank you very much. Keep up the good work.
You can easily understand this concept by considering an example... Let's assume we are assessing whether a patient has cancer or not. If our model predicts a positive result, but in reality, the patient does not have cancer, it is a false positive (Type 1 error), which is not harmful in the case of cancer. However, if the model predicts a negative result, and in reality, the patient has cancer, it is a false negative (Type 2 error), which is very detrimental to our model. Therefore, our focus should be on reducing this specific misclassification error.
yes, you are right. he made a little mistake. Type 1 : occurs when the null hypothesis is accepted when it is false Type 2 : occurs the null hypothesis is false when it is true
Please sir help me to solve this confusion or some one please please explain if I am wrong 3:31 yaha pr aapne kaha he ki , FP(i.e predicted true but in actual it is false) is type 1 error and FN(i.e predicted False but in actual it is true) is type 2 but here 12:28 , you say that we rejected the null hypothesis but in actual it is true that means it becomes FN sir , so It should be type 2 error but you say that it is type 1 error
Type 1 : occurs when the null hypothesis is rejected when it is true
Type 2 : occurs the null hypothesis is accepted when it is false
Sir you have no idea how good you are as a teacher, this playlist has really helped me to learn a lot about the Applied Statistical Analysis.
I request you to please complete this playlist.
Thank you very much.
Keep up the good work.
You can easily understand this concept by considering an example...
Let's assume we are assessing whether a patient has cancer or not.
If our model predicts a positive result, but in reality, the patient does not have cancer, it is a false positive (Type 1 error), which is not harmful in the case of cancer.
However, if the model predicts a negative result, and in reality, the patient has cancer, it is a false negative (Type 2 error), which is very detrimental to our model.
Therefore, our focus should be on reducing this specific misclassification error.
this is understandable but the way he created the relation with confusion matrix to conclude type1 and type2 error thats not clear
@12:15 it will be type 2 error or False Positive
@13:59 it will be type 1 error of False Negative
Oh bro thank you , I've been confused for the past 30 minutes yaar.
Mai v confuse ho gya tha
he is right in this part but opposite in initial 2
Krish sir, I think "Outcome 3 = FN(Type 2 Error)", & "Outcome 4=FP(Type 1 Error)". But in video you said vice versa. Please check it once again.
Yes also I think so
yes, you are right. he made a little mistake.
Type 1 : occurs when the null hypothesis is accepted when it is false
Type 2 : occurs the null hypothesis is false when it is true
Confusion matrix kafi confusing hey
please complete full statistics for DS/ML
Your FP and FN need to reverse in confusion matrix . They r causing real confusion .
true
SuPPerbbb explained Sir...
😮
Thanks sir...
Hello Krish after completion of this course will you help us in interview process also
in 12:05 you said in prediction it is false(0) and in reality it is true(1) then it should be FN but you take it as FP. please clarify
Yes it should be FN
Yes you are right it should be FN
Please sir help me to solve this confusion or some one please please explain if I am wrong
3:31 yaha pr aapne kaha he ki , FP(i.e predicted true but in actual it is false) is type 1 error and FN(i.e predicted False but in actual it is true) is type 2 but here 12:28 , you say that we rejected the null hypothesis but in actual it is true that means it becomes FN sir , so It should be type 2 error but you say that it is type 1 error
you are right bro, sir mistakenly switched the error types
Thank you sir
Brother 1 thing is wrong that you consider (0)of actual instead of predicted so basically outcome 3 should be FALSE NEGATIVE
Thanks 😊👍🏻
❤
To reduce this type 1 and type 2 errors is there any other way to reduce it other then hyperparameter tuning, threshold value adjustment
Good question
great knowledge
Type 1 and type 2 error in your confusion matrix diagram is interchanged. Please edit and do correction. This decreases our confidence in your videos
dimang ki upar se gya
mera comment refer karo shayad aapko help karega confusion matrix samajh ne me
Are ye faltu padata hai