Love for Linear Models

Transcript

1. 1.

   LINEAR MODELS ARE GREAT ALEX GOLD SOLUTIONS ENGINEER RSTUDIO @alexkgold

   Slides at: https://github.com/akgold/dsdc_linear_models
2. 2.

   IT ME.

3. 3.

   WHAT DOES IT MEAN TO BE LINEAR? + some prediction

   error +βhp = β0 + βcyl Just a number
4. 4.

   WHAT DOES IT MEAN TO BE LINEAR? Y = βX

   + ϵ
5. 5.

   ALEX <3 LINEAR MODELS

6. 6.

   None
7. 7.

   Y = βX + ϵ

8. 8.

   Y = ∑ k βk fk (xi ) + ϵ

9. 9.

   None
10. 10.

    None
11. 11.

    None
12. 12.

    gender = β0 + β1 weight + β2 height

13. 13.

    gender = β0 + β1 weight + β2 height VS

14. 14.

    gender = β0 + β1 weight + β2 height VS

15. 15.

    None
16. 16.

    It’s all about the Data-Generating Process

17. 17.

    mpg = β0 + β1 cyl + disp mpg =

    β0 + β1 cyl + β2 cyl2 + β3 log(disp) OR ?
18. 18.

    None
19. 19.

    1. INTERPRETATION MATTERS. 2. LINEARITY ISN’T RESTRICTIVE. 3. MO’ SQUIGGLY

    = MO’ OVERFITTING. 4. SMALL DATA’S OK. 5. IT’S ALL ABOUT THE DGP. @alexkgold https://github.com/akgold/dsdc_linear_models