Heuristics and biases Tina Nane 2 Heuristics and biases Lotto - - PowerPoint PPT Presentation

1

Heuristics and biases

Tina Nane

2

Heuristics and biases

“Lotto Icon” by Dapete is licensed under CC BY 2.5

2

Heuristics and biases

• Heuristics
• Tricks, rules of thumb, habits to reason under

uncertainty

“Lotto Icon” by Dapete is licensed under CC BY 2.5

2

Heuristics and biases

• Heuristics
• Tricks, rules of thumb, habits to reason under

uncertainty

• Errors
• Violation of the axioms of probability
• Estimates not in accordance with one’s belief

“Lotto Icon” by Dapete is licensed under CC BY 2.5

2

Heuristics and biases

• Heuristics
• Tricks, rules of thumb, habits to reason under

uncertainty

• Errors
• Violation of the axioms of probability
• Estimates not in accordance with one’s belief

“Lotto Icon” by Dapete is licensed under CC BY 2.5

2

Heuristics and biases

• Heuristics
• Tricks, rules of thumb, habits to reason under

uncertainty

• Errors
• Violation of the axioms of probability
• Estimates not in accordance with one’s belief
• Bias
• “misperceptions” of probabilities

“Lotto Icon” by Dapete is licensed under CC BY 2.5

3

Biases

• Anchoring
• Availability
• Confirmation bias
• Representativeness
• Conservatism bias
• Ostrich effect
• Overconfidence
• Control

3

Biases

• Anchoring
• Availability
• Confirmation bias
• Representativeness
• Conservatism bias
• Ostrich effect
• Overconfidence
• Control

"Bury your head in the sand" by Sander van der Wel is licensed under CC BY-NC-ND 2.0

4

Biases

• Anchoring
• Availability
• Confirmation bias
• Representativeness
• Conservatism bias
• Ostrich effect
• Overconfidence
• Control

5

Availability

• “If you can think of it, it must be important”

(Tversky & Kahneman)

• The frequency with which a given event occurs is

usually estimated by the ease with which instances can be recalled

6

Availability

"Plane takes off" by Oregon Department of Transportation is licensed under CC BY-NC-ND 2.0

7

Availability

"chiang rai to chiang mai" by arcibald is licensed under CC BY-NC 2.0 “Plane crash into Hudson River” by Greg L am Pak Ng is licensed under CC BY 2.0

8

Availability

“Earthquake, Tsunami, Nuclear Disaster” by DonkeyHotey is licensed under CC BY-SA 2.0

9

Availability

“Earthquake, Tsunami, Nuclear Disaster” by DonkeyHotey is licensed under CC BY-SA 2.0 "Johns Hopkins Inlet under partially sunny skies (!)" by roy.luck is licensed under CC BY 2.0

10

• Want to get $6,500
• Advertise it for $7,500

‘IJ-hallen-003 by Davy Landman is licensed under CC BY-SA 2.0

11

Anchoring

• Judgment under uncertainty: Heuristics and biases

(Kahneman & Tversky,1974)

• When we estimate a probability, we
• First produce a number
• Then consider arguments for shifting that number up or

down

• The estimate might depend too much on the initial number

“Anchor” by EugeneZelenko is licensed under CC.0

12

Anchoring

• Subjects are asked to estimate the 5% and 95%

quantiles of a continuous probability distribution

• Often experts “anchor” too close to the central value
• Distributions are often “too concentrated”

“Anchor” by EugeneZelenko is licensed under CC.0

13

Overconfidence

• Tendency to think that one knows more than one

in fact knows

• “the most significant of the cognitive

biases” (Kahneman, 2011)

"un-overconfidence" by genebrooks is licensed under CC BY 2.0 "1334276584137_154" by 璇梓 is licensed under CC BY-SA 2.0 "High Power Channel-type Reactor" by Kamil Porembiński is licensed under CC BY-SA 2.0 "Atlantis 8 Julio 2011 Launch" by mikeb2012 is licensed under CC BY 2.0

14

Overconfidence

• 93% of American drivers claim to be better than

the median (Svenson, 1981)

"un-overconfidence" by genebrooks is licensed under CC BY 2.0 "0012_10" by Frisno is licensed under CC BY-NC-ND 2.0

15

Control

• Belief that if some aspect of an event is

controllable, then its probability is influenced

“Control” by Nick Youngson is licensend under CC BY-SA 3.0 “ L

• t

t

• I

c

• n

” b y D a p e t e i s l i c e n s e d u n d e r C C B Y 2 . 5

16

Why do we care?

• People, including experts, frequently use heuristics

to handle subjective probabilities, leading to potentially biased assessments.

• Important to be aware of these biases, and to “fix”

them or develop expert elicitation methods that minimise biases.

“Bias” by Nick Youngson I s licensed under CC BY-SA 3.0

17

Want to read more?

1. Kahneman, D., Slovic, S. P ., Slovic, P ., & Tversky, A. (Eds.). (1982). Judgment under uncertainty: Heuristics and biases. Cambridge university press. 2. Cooke, R. (1991). Experts in uncertainty: opinion and subjective probability in science. Oxford University Press on Demand. 3. Kahneman, D. (2011). Thinking, fast and slow. Macmillan.

“Bias” by Nick Youngson I s licensed under CC BY-SA 3.0

18

Thank you for your attention!