Calculating R-squared | Regression | Probability and Statistics | Khan Academy

Поделиться
HTML-код
  • Опубликовано: 19 дек 2024

Комментарии •

  • @BurkeyAcademy
    @BurkeyAcademy 14 лет назад +5

    @norwayte The 12% is unexplained. Real world examples are important here. Suppose x is height of a person and y is weight. Then 88% of the variation in weight can be explained by knowing someone's height. The other 12% is explained by either something else(diet, genetics, etc.), or just randomness (no real cause at all).

  • @debendragurung3033
    @debendragurung3033 8 лет назад +3

    i thought I was going insane learning the conditional probability, but this saved my day. More concrete and logical.

  • @jester69r
    @jester69r 11 лет назад +9

    I LOVE YOU KHAN

  • @lokeshagarwal6701
    @lokeshagarwal6701 6 лет назад +1

    At 7:06 why does the SE line does not explain the error SE of difference from the mean of y

  • @GHOSTrex1324
    @GHOSTrex1324 4 года назад

    Sal be hittin those excel shortcuts 😉

  • @shengyuanyi
    @shengyuanyi 12 лет назад

    This helps a lot. Thank you very much. I hope I can do the same job if I have enough ability. I will be good if I can get a PhD degree in Engineering.

  • @ldpy33
    @ldpy33 4 года назад

    Here's the question: IS THE ANSWER E?)
    Which of the following tells us how strong the relationship is between two variables?
    a) the slope of a line
    b) the intercept of a line
    c) the coefficient of determination
    d) the coefficient of correlation
    e) both C and D are correct

  • @Godsrul3z
    @Godsrul3z 9 лет назад

    Amazing job, thanks a lot

  • @Jaytaxman
    @Jaytaxman 14 лет назад +8

    Take a drink every time he repeats himself!!!

  • @MrFrenchfriesman
    @MrFrenchfriesman 11 лет назад

    for a one predictor model should i use R^2 or adjusted R^2

  • @daelynnmerritt5861
    @daelynnmerritt5861 12 лет назад

    First year in statistics....do I use parentheses when doing the coefficient of determination? For example, I am confused now because I read that you can't have a negative correlation of determination. For instance, say you had Rxy = -.7....now, would that be like this (-.7)squared, or just -.7 squared...each gives different results....a negative and a positive...but I don't know which one to use? Thanks!

  • @AlExIsAwEsOmE70
    @AlExIsAwEsOmE70 12 лет назад

    what about when the difference between the "best fit" line is much much larger than the mean and the squared error with the line of "best fit" is actually much larger than the squared error with the mean? then you get a negative r squared?

    • @rahulkhinchee7104
      @rahulkhinchee7104 5 лет назад

      it means that the variations in y is explained by x. Thus, not a best fit

  • @TreachMarkets
    @TreachMarkets 14 лет назад

    Someone told me about the area equation. They mentioned Pi R Squared. This is incorrect. Pi R Round. Cake R Squared. Get it right, people!

  • @jaskaransingh0304
    @jaskaransingh0304 Год назад

    why is line and variation in x interchangeable?

  • @lokeshagarwal6701
    @lokeshagarwal6701 6 лет назад

    Why is the SE error by the line does not describe the error in mean of Y

  • @MinhTran-fu1qd
    @MinhTran-fu1qd 10 лет назад

    YOU.ARE.GOD!

  • @johnchen0213
    @johnchen0213 13 лет назад

    why is it 41/42?? someone explainnnnnn

    • @jasper1376
      @jasper1376 7 лет назад

      looks like noone explained, did you pass school anyway?

  • @WiscoBadger52
    @WiscoBadger52 11 лет назад +1

    i am drujnkha

  • @norwayte
    @norwayte 14 лет назад

    And the 12% is explained by what? Where come the 12% from?