MDM 1

Question 1

What is critical to understanding evidence?

Answer 1

Counterfactual

Question 2

Experimentation = Best way to test causality - three features?

Answer 2

Indep. variable, Dep variable, random assignment

Question 3

Correlation..

Answer 3

DNE causation

Question 4

Internal validity

Answer 4

Did random assignment happen?

Question 5

Threats to internal validity

Answer 5

1) Random assign. didn’t happen, 2) Small # randomly assigned units, 3) Attrition

Question 6

External validity

Answer 6

Can you generalize?

Question 7

Random Assignment VS Random Sampling

Answer 7

RA = Random assg. to different conditions (ensure internal validity)
RS = Random sample of units to include in the study

Question 8

Reasons not to experiment

Answer 8

Too expensive
Benefit = low
Physically, legal, ethically impossible

Question 9

Chance

Answer 9

streakier and lumpier than we would expect

Question 10

Gambler’s Fallacy

Answer 10

Chance will correct itself

Question 11

Low sample?

Answer 11

Greater variance, less reliable, more chance

Question 12

Calculating odds of a patter AFTER you notice

Answer 12

WRONG

Question 13

P-Hacking

Answer 13

1) Stop data collection when p

Question 14

Regression to mean

Answer 14

Perform = f(skill,luck)

Low luck is followed by avg luck

Question 15

Availability Bias

Answer 15

What is in front of us is it

Question 16

Hindsight bias

Answer 16

Clinton

Question 17

Anchoring

Answer 17

seems informative, if you have no idea and seems plausible, acts as default

Question 18

Curse of knowledge

Answer 18

Tapping tone, running turn

Question 19

Attitude projection

Answer 19

think about class survey

Question 20

Bias of perspective

Answer 20

McNamara

Question 21

Motivated Reasonings

Answer 21

f(desire, ambiguity)

Question 22

Can I vs Must I

Answer 22

Can I ( I like this)
Must I (I don't like this)

Question 23

MR is different from

Answer 23

conscious corruption (punishments don’t work)

Question 24

Causes of overconfidence

Answer 24

Availability, anchoring, failure to appreciate chance, biases of know. and perspective, MR, reward for overconfidence

Question 25

Overconfidence = good and bad

Answer 25

Good = motivation Bad = everything else (especially decision making)

Question 26

Intuition Good when...

Answer 26

Near-perfect, immediate, unbiases feedback, doesn't change in an importnat way

Question 27

Is X greater than Y? How much?

Answer 27

Amazon stocks, Ravens football, elephant weight

Question 28

Bootstrapping

Answer 28

Judge makes decisions. Calculate weights. Apply weights and make changes.

Question 29

Reliability vs validity

Answer 29

Rel = how much do 2 predictions correlate with each other? Validity = How much does prediction correlate with outcome. Difficult to have val w/out rel & rel will be higher than val.

Question 30

Why is human judgement unreliable?

Answer 30

1) Fatigue/distraction 2) Incidental factors (mood, framing, order, etc.) 3) Random error that leads to inconsistent weighting

Question 31

Steps - random statistical model

Answer 31

1) Determine sign of each regression coefficient 2) Standardize all variables 3) Choose a coeffecient at random over range 0 to 1 4) Use these coefficients to make predictions

Question 32

Human judges often use?

Answer 32

Useless info

Question 33

Caveat to models

Answer 33

1) Data used must reflect range of actual possibilities 2) Must have quantifiable criterion 3) Stat models don't account for "soft" var's which can matter 4) Diversity is difficult

Question 34

How to overcome algorithm aversion?

Answer 34

Give people some control - people are less tolerant of algorithm mistakes

Question 35

Methods of combining opinions

Answer 35

1) Group deliberations 2) Averages opinions 3) Prediction markets

Question 36

Problems with discussion

Answer 36

- Bias - Opinions are not voices - Anchoring on one idea - Opinions are not independent

Question 37

Ingredients for eliciting information. Make sure groups are?

Answer 37

- Knowledgeable - Diverse/unbiased - Independent - Motivated to contribute - remove the risk!

Question 38

Adding options can

Answer 38

Drastically change decisions!

Question 39

Prospect Theory

Answer 39

1) Losses weigh heavier than gains 2) Risk-averse in gains; risk-seeking in losses 3) people are sensitive to arbitrary ref. points

Question 40

Rules for Gains/Losses

Answer 40

Integrate losses Segregate gains Integrate small losses with large gains

Question 41

Endowment effect

Answer 41

Selling prices tend to be 2x greater than buyign prices

Question 42

Probability weighting

Answer 42

people overweight very small probabilities (.01), but underweight mid-high probabilities (.8-.9)

Question 43

Steps for designing interventions

Answer 43

ID specific behavior Ask why is this happenign What env. factors influence this Change env.

Question 44

Why defaults work/matter?

Answer 44

1) Mech. reasons (decision costs, forgetting, etc.) 2) Belief-based: Social norm, recommednation 3) Psych. reasons: Risk-averse, regret, lack of reasons for making active choice

Question 45

Why don't people act to help at times?

Answer 45

Diversion of responsibility