Please enable JavaScript.

Coggle requires JavaScript to display documents.

Regression - Coggle Diagram

- - - - Lowest possible value 0 if all the outcomes in the partition have the exact same value
      - lower SSD = more "agreement" in the outcome
      - Split data so it minimizes SSD
      - No upper limit
  - - - aka putting the outcomes into different segments
      - not as good as more detailed predictive outcomes
- - - - predicted value > actual value
    - - predicted value < actual value
  - - - on avg, underpredicting
    - - on avg. overpredicting
  - - - negative numbers are transformed into positive
      - positive numbers stay positive
      - sum them & take the avg.
  - - - absolute value of error
      - divide by actual value
      - sum them
      - take the avg
      - multiply by 100
  - - - square the prediction errors
      - sum them
      - take the avg.
      - square root the whole thing
- - - - Y
      - represents outcome
      - numerical/continuous
    - - Predictors
      - covariates
      - X
      - Attributes of an observation used to predict Y
- - - - if yes, normalize first, compute distance second
      - outcome variable NOT normalized
      - usually use standardization
    - - Predictor = avg. of Ys of neighbors
  - - - lots of attributes = need lots of observation to have a good prediction
    - - not good for "real time" predictions
      - especially bad with large dataset
- - - - k-NN
      - Regression Tree
  - - - k-NN
      - Decision Tree