Qm
Statistics

Linear model versus decision tree, on test error

bias-variancemsemodel-selection

You compare two models on the same problem, where expected test error is squared bias+variance+irreducible noise\text{squared bias} + \text{variance} + \text{irreducible noise} and the noise is 5:

  • Linear model: squared bias 10, variance 2
  • Decision tree: squared bias 1, variance 9

Which model has the lower expected test error, and what is it?

Your answer

Solving needs a free account

Answers, streaks and solutions unlock when you are signed in. Reading the question and the hint stays free.

Create a free accountSign in

Discussion

Sign in to join the discussion · reading is open to everyone

💡 Discussion rules

  1. No full solutions here. Hints and approaches only.
  2. Complexity, edge cases and intuition are the point.
  3. Interview experiences are welcome. Respect your NDAs.

Loading discussion…

Learn the concepts

The theory behind this question.

The Bias-Variance DecompositionUnderfitting and Model MisspecificationACF and PACF Model IdentificationBandwidth Selection for SmoothersBeating the Linear Baseline: When ML Actually Helps

Related questions

Which model has the lowest expected test error?Underfit, balanced, or overfit: pick the bestFind the missing variance from total test errorThe error floor no model can beatBlend an unbiased noisy forecast with a biased sharp one
All questions →