How To Lie With Statistics Pt. 2

Posted by Klarissa Hudson in Statistics - Miles - C on

​Group Members Present: Klarissa & Symone
Pages Read: 47 - 91
Pages For Next Week: 92 - 142

Podcast Points:

  1. Choose one of the quotations inside the front cover and discuss how it relates to the Introduction. - Klarissa

    1. “Round numbers are always false.” - Samuel Johnson

  2. List as many sources of sample bias as you can that are mentioned in Chapter 1 and provide an example of each.

    1. Average Yaleman, Class of ‘24 makes $25,111 a year.

  3. Put the second paragraph on Page 18 (“A river cannot….”) into your own words.

    1. “A river cannot rise above its source.” To me means that you can’t get something more out of what you already have, which is not true. This paragraph elaborates on this by concluding that in different data sets, we’re able to get way more information than we’ve been told. Thus, the saying a river cannot rise above its source can not be true all of the time.

  4. What is the advantage of a stratified random sample and what difficulties does it pose, according to this chapter?

    1. Advantages:

      1. You can be sure that your samples are appropriately proportioned

    2. Difficulties:

      1. Each unit must only fit in one stratum

  5. Explain why advertisers often rely on a very small sample to substantiate their claims.

    1. If advertisers were to use large sample sizes then it would be harder to substantiate their claims and ideas.

  6. What does the author mean on Page 45 when he says, “Hardly anybody is exactly normal in any way…?”

    1. What I took from the quote “hardly anybody is exactly normal in anyway” is that there are plenty of outside factors that can screw up data and paint a different picture. So nothing or no person is always normal all of the time, just like data. A clear example of this can be looking at data that suggests people who go to sleep before 10 pm receive higher tests scores. Sure, sleep is important but other factors could influence this conclusion. Things like what they ate the night before the test, what they had for breakfast, what they did in the morning, etc.

Sources:
http://gizmodo.com/how-to-lie-with-data-visualization-1563576606
http://passyworldofmathematics.com/misleading-graphs/
How To Lie With Statistics pt.2

Comments (1)

Mark Miles (Teacher)
Mark Miles

Good second podcast. Great job answering the questions, but there was not a lot of new book material covered.

For next time, please respond to the following questions: <ol> <li>What is a semi-attached figure?</li> <li>What does post hoc mean?</li> <li>List several kinds of correlation that might lead to post hoc reasoning.</li> </ol>