Download presentation
Presentation is loading. Please wait.
Published byDoris Erin Caldwell Modified over 8 years ago
1
Probability and Statistics “Critical Thinking”
2
Flawed statistics Statistics are often misused and flawed either because of: (1) Evil intent on the part of dishonest people, or… (2) Unintentional errors on the part of people who don’t know any better
3
Types of errors Misleading graphs Biased questions Biased (non-random) sample, such as voluntary response Sample size too small Mistaking correlation for causality Allowing survey participants to “self- report”
4
Types of errors – Biased questions Effect of the wording of a question: “Should the President have the line item veto to eliminate waste?” 97% yes “Should the President have the line item veto, or not?” 57% yes
5
Types of errors – Biased questions Effect of the order of questions: “Would you say that traffic contributes more or less to air pollution than industry?” 45% blamed traffic; 27% blamed industry “Would you say that industry contributes more or less to air pollution than traffic?” 24% blamed traffic; 57% blamed industry
6
Types of errors – Small sample size You must be sure to survey a large enough number of people to represent the population. The more people you survey, the more accurate your results will be. For example, if you survey 20 people in the U.S. and ask who they will be voting for there will be a + or - 20% “margin of error.” If you ask 1000 people, there will be a + or – 3% margin of error.
7
Types of errors – Correlation/Causality Just because two variables seem to have an effect on each other doesn’t mean that they do. Example – People who sleep 6 hours a night live longer than people who sleep 8 hours or more Will simply sleeping for less time cause me to live longer or could there be another explanation?
8
Types of errors – Self-reporting Suppose in a survey you ask 100 people if they wash their hands after using the bathroom and 80% say yes. Do you think that statistic is reliable? Why or why not? Suppose you ask 100 women at random how much they weigh and their mean weight is 117 pounds. Do you think that statistic is reliable? Why or why not?
9
Classwork / Homework Pages 23-26 (all evens or odds)
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.