Please enable JavaScript.

Coggle requires JavaScript to display documents.

Statistical learning (Variables (Error term (Types (Irreducible (Larger…

- - - - Features
      - Independent variables
      - Variables
      - Predictors
  - - - Response
      - Dependent variables
  - - - Reducible
      - Irreducible
        
        Larger than zero
- - - - Training data
  - - - Amount by which fˆ would change if we estimated it using a diﬀerent training data set
    - - The error that is introduced by approximating a real-life problem, which may be extremely complicated, by a much simpler model
      - Generally, more ﬂexible methods result in less bias
- - - - 1 Assumption of a functional form
        
        Linear model
      - 2 Fit or train the model
        
        Least squares
    - - No assumption of the form of f
      - Examples
        
        Thin-plate spline