AI Hints
Home›Statistics & Math for ML Tutorial›Effect Size and Pitfalls
Statistics & Math for ML · Lesson 66 of 138

Inference Quiz

Test yourself.

⏱ 2 min read▶ Video at 1:17:13🎓 Free
Watch this lesson in the Statistics & Math for ML courseWatch on YouTube ↗Full Statistics & Math for ML course

Let's test what you know about inference. Pause before each answer.

Inference Quiz
From the video: Inference Quiz
  • Five questions
  • Pause and think
  • Then listen

Question 1

How does the standard error change when you collect four times as much data? The answer is, it halves.

Quick check
4× the data?

Question 2

A p value is zero point zero three. With alpha at five percent, what do we do? The answer is, reject the null hypothesis.

Quick check
p = 0.03, α = 0.05?

Question 3

Which error is a false alarm, finding an effect that isn't there? The answer is a type one error.

Quick check
A false alarm?

Question 4

Which method builds a confidence interval by resampling your own data? The answer is the bootstrap.

Quick check
Resampling your data?

Question 5

A result is significant, but the effect size is tiny. Is it important? The answer is, probably not.

Quick check
Significant but tiny?

Summary

Excellent. Next, a new section, relationships between variables, starting with covariance.

Key takeaways
  • SE shrinks with √n
  • p < α: reject
  • Effect size matters
Next up: Covariance — moving together