Return to Video

Statistical Rigor Exercise - Intro to Data Science

  • 0:00 - 0:05
    Alright. So, why are statistical significance tests useful? So,
  • 0:05 - 0:07
    they do provide a formalized framework for comparing and
  • 0:07 - 0:11
    evaluating data. And they do enable us to evaluate
  • 0:11 - 0:13
    whether perceived effects in our data set reflect differences across
  • 0:13 - 0:16
    the whole population. They do not make a bad
  • 0:16 - 0:19
    result look good. Significant sets are useful because they provide
  • 0:19 - 0:23
    a formalized framework for comparing and evaluating data. Different
  • 0:23 - 0:26
    tests have different assumptions and rules that they incorporate, and
  • 0:26 - 0:29
    using a particular test ensures that everyone is on the
  • 0:29 - 0:31
    same page in so far as what we're assuming about
  • 0:31 - 0:35
    our data. Significance tests also enable us to evaluate whether
  • 0:35 - 0:38
    perceived effects in our data set reflect differences across the whole
  • 0:38 - 0:41
    population. As was the case with our company, where ten
  • 0:41 - 0:45
    out of ten people polled preferred the color blue. Sometimes an
  • 0:45 - 0:48
    affect that we seen in a small sample does not
  • 0:48 - 0:52
    reflect what might be true across the entire population. A statistical
  • 0:52 - 0:54
    significance test let's us formally determine whether or not this might
  • 0:54 - 0:58
    be the case. Unfortunately, a bad result is not going to
  • 0:58 - 1:00
    look any better or worse as a result of using a
  • 1:00 - 1:03
    statistical significance test. If our data's
  • 1:03 - 1:05
    bad, or there's really no difference
  • 1:05 - 1:08
    between our two samples. We're not going to be able to
  • 1:08 - 1:11
    undo that with a test. It is possible though that different tests
  • 1:11 - 1:15
    might give us different results. The really important thing and we'll
  • 1:15 - 1:17
    go into this a bit more is that you need to use
  • 1:17 - 1:19
    the right test in the right situations. Why don't we talk a
  • 1:19 - 1:22
    little bit about how we might actually run a statistical significance test.
Title:
Statistical Rigor Exercise - Intro to Data Science
Description:

more » « less
Video Language:
English
Team:
Udacity
Project:
ud359: Intro to Data Science
Duration:
01:24

English subtitles

Revisions Compare revisions