English subtitles

← Fail to Reject the Null - Intro to Inferential Statistics

Get Embed Code
3 Languages

Showing Revision 6 created 05/24/2016 by Udacity Robot.

  1. We can't prove that the null hypothesis is true. We can only obtain evidence to
  2. reject the null hypothesis. Let's take a simple example. Let's say, our null
  3. hypothesis is that most dogs have four legs. And we define most as more than
  4. 50% of dogs. This 50% is analogous to our alpha level where we set our
  5. criterion for making a decision. Our alternative hypothesis is that most dogs
  6. have less than four legs. Note that this is like a one tailed test. Where we're
  7. not guessing that most dogs have a different amount than four legs. We're
  8. guessing most dogs have less, so there's a direction. Now let's say we sample
  9. 10 dogs and find that all of them have four legs. Did we prove that the null
  10. hypothesis is true, that most dogs have four legs?