Essay

Choosing test-set size for a reliable estimate

Question: In a short analytical response, explain how the size of a test set should be chosen when the goal is a trustworthy estimate of end-to-end system performance.

Sample answer: The right test-set size is the one that gives enough statistical confidence in the estimate of overall system performance. In other words, the set is not large for its own sake; it is large enough to make the final performance estimate reliable.

Key points:

  • Test-set size is determined by the needed confidence level.
  • The estimate should concern overall system performance.
  • A larger set is useful only when it improves reliability.
  • Size is a means to confidence, not the objective by itself.

Rubric: A strong response should link test-set size to the desired confidence in the overall performance estimate and avoid treating size as an independent goal.

0

1

Updated 2026-08-12

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Machine Learning Strategy

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Yearning @ DeepLearning.AI