Probabilistic Reasoning

Question 1

probabilistic reasoning

Answer 1

ways to deal with uncertainty

Question 2

Sources of uncertainty:

Answer 2

perception
memory
testimony

Question 3

uncertainty about perception

Answer 3

foggy area, animal camouflaged in a tree that is hard to see, elvis impersonator

Question 4

uncertainty about memory

Answer 4

country flag, remembering who committed the crime when seeing a line up

Question 5

uncertain about testimony

Answer 5

thinking of whether or not to believe a weather forecaster’s words, a certain newspaper’s opinion

Question 6

probability

Answer 6

use of math as a way of modeling uncertainty and what the best thing to do would be

Question 7

sub

subjective probabilites are…

Answer 7

the probabilities that we assign in our reasoning

Question 8

Probability (X)

Answer 8

(X Possibilites)/(Total Possibilities)

Question 9

Baye’s Theorem

Answer 9

H = hypothesis
E = your evidence
Pr = the probability assigned to a possibility
Pr( H|E) = (P(E|H) X P(H)) / (P(E))

Question 10

Baye’s Theorem Example : COVID

Answer 10

H is that you have COVID, E is a positive test, P(E | H)=.7, and P(E | not H)=.1
Consequence 1: If the prior probability of H is sufficiently low, the posterior probability pr(H | E) will be low regardless of E. Basically: If you believe that H is almost impossible, new evidence won’t make much difference.
ANOTHER potential consequence (result of different num- bers/scenarios):
Consequence 2: If the likelihood of Pr(E | H) is about the same as Pr(E | not H), the posterior Pr(H | E) will be close to the prior p(H). Basically: if your evidence E is worthless, so you stick with what you already believed.

Question 11

Bayesian Optimality

Answer 11

Optimal approach to cue combination:
For discrepant cues, you should take their weighted average, where each is weighted by the reliability of that cue.
So, you put more weight on the source that is more reliable in order to get a more accurate average

Question 12

Fetsch et al. 2010

Answer 12

put Macaque monkeys on a moving platform . modified coherence of different things.
under graded visuals, the monkeys relied more on vestibular modality
better visual image: the monkeys relied more on vision than they normally would have
the monkeys are naturally using estimates of the reliability of their different sensory modalities.

Question 13

baesian suboptimality

Answer 13

Representativeness: When asked the probability that A belongs to a class B, people often rely on the degree to which A is resembles a paradigmatic example of B.
instead of doing probability theory in our minds, a lot of people just do this, relying on heuristics instead

Question 14

failures that result from representativeness

Answer 14

1. base rate neglect
2. insensitivity to sample size
3. misconceptions of chance
4. insensitivity to predictability
5. misconceptions of regression

Question 15

base rate neglect

Answer 15

“Steve is very shy and withdrawn, invariably helpful, but with little interest in people, or in the world of reality. A meek and tidy soul, he has a need for order and structure, and a passion for detail.”
Is it more likely that Steve is an engineer or lawyer?
people ignore the the relative base rate/frequency of the probability of the careers, and instead use resemblance of which character type is stereotypically more regarded with that career

another similar example: question post similar type of description: Is it more likely that Linda is a bank teller or a feminist bank teller
a feminist bank teller is STILL a bank teller, yet people still say feminist bank teller, even though that is less likely since it is a more narrow category

Question 16

insensitivity to sample size

Answer 16

Ex: Is a large or a small hospital more likely to have >60% boys? Ex: The ten counties with the lowest cancer rate voted for Trump by wide margins

Question 17

Misconceptions of chance

Answer 17

Fair coin flip: HTHTHTTHHHH Gambler’s fallacy: Next flip is more likely to be T than H

Question 18

Insensitivity to predictability

Answer 18

Evaluations of a student-teacher’s performance often = Predic- tions of a student-teacher’s future performance

Question 19

Misconceptions of Regression

Answer 19

fight pilot optical course
ones who did well were praised, ones who did bad were punishes
the ones who did worse before did better next time, and the ones who were prasied before did worse next time (incetive to then not give praise)
but it is just that: you are more likely to perform near the average. The praising or punishing is irrelevant

Question 20

Bayesian Sub-optimality: another heuristic

Answer 20

vailability: When asked the probability of A, people often rely on the ease with which instances of A can be brought to mind
Failures that result from Availability:
Influence of familiarity
Influence of ease of search: you think something that is harder to find is just less frequent, when that likely might not be the case Influence of salience
Influence of recency
Bias of imaginability
Illusory correlation

Question 21

Metacognition

Answer 21

• confidence often varies independently of accuracy
• iverconfidence tends to apply across domains
• more information can lead to overconfidence
• expertise can lead to overconfidence
• were bad at predicting which problems we can solve

Question 22

3 ways of testing metacognition:

Answer 22

image shows choice options
by committing to a choice, confidence goes up. (left side of image)
but you can also choose low high confidence options, (right side).

Question 23

```

~~~

kepecs 2012

Answer 23

the animal goes to the path with the better or less bad odor. wait time at one point on fast.
if they’re really sure they will wait as long as it takes to get the reward, but if they are unsure they will take the other path if theirs has a wait time
the more evenly balanced the odor on both sides, the more un- certain the animal is the mouse is using an estimate of how likely they made the right choice between the odors