CHAPTER 8 Reversion to the Mean Flashcards

1
Q

What is reversion to the mean?

A

A phenomenon where extreme observations are often followed by less extreme observations.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What outcomes tend to exhibit reversion to the mean?

A

Any outcome that is a function of both signal and noise.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Why is it important to understand reversion to the mean?

A

To avoid misinterpreting evidence and quantitative information.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Should we expect reversion to the mean for future projections like stock prices?

A

No, we shouldn’t expect reversion to the mean for beliefs about the future.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is the replication crisis?

A

The failure to replicate hyped scientific results in follow-up studies.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Who is Jonathan Schooler?

A

A psychologist who noticed systematic failures to replicate findings in his studies.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What happens to the effect sizes in replicated studies according to Schooler’s observations?

A

Effects tend to get systematically smaller.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is the Hawthorne effect?

A

When subjects change their behavior because they know they are being studied.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What are demand effects?

A

Situations where subjects behave differently to please the experimenters.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is cosmic habituation as proposed by Schooler?

A

The idea that the universe causes effects to shrink every time they are studied.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What did Francis Galton study in the 1860s?

A

The relationship between the size of parents and their children, particularly in height.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What does Galton’s regression line indicate about parents’ and children’s heights?

A

Taller parents tend to have taller children, but the slope is less than 1.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is the positive y-intercept in Galton’s regression line suggest?

A

Particularly short parents tend to have children who are taller than they are.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is regression to mediocrity?

A

A phenomenon where extreme measurements tend to revert toward the mean.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

How does Galton’s findings relate to cosmic habituation?

A

Both suggest some unseen force pushes outcomes toward the average.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What are the two main factors influencing seed size according to the model?

A
  • Genes inherited from the parent
  • Amount of sunlight received while growing
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What happens to exceptionally large or small seeds when they produce offspring?

A

Their offspring will tend to be larger than average but smaller than their parents.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What is the relationship between signal and noise in the context of reversion to the mean?

A

Reversion to the mean occurs in outcomes that are partly systematic (signal) and partly random (noise).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What is a common misconception about reversion to the mean?

A

That it reflects a gravitational pull toward the mean.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

In the example with John Junior and John III, what is the expected height of John III?

A

Shorter than John Junior.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

For John Junior’s father, what is the expected height compared to John Junior?

A

Shorter than John Junior.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

Why might people confuse the expected heights of John Junior and his father?

A

They might reason that reversion to the mean implies John Senior must be much taller.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What is the key takeaway regarding reversion to the mean?

A

It is crucial for interpreting evidence correctly across various contexts.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

What is reversion to the mean?

A

A statistical phenomenon where extreme observations tend to be followed by more moderate ones

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

If John Junior is very tall, what can we expect about his father’s height?

A

His father is probably shorter than him due to reversion to the mean

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

What is the relationship between the signal and noise in observations?

A

An outcome is made up of a signal (true value) and noise (random variation)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

True or False: Reversion to the mean is a gravitational force pulling things toward the average over time.

A

False

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

What do we generally observe about scores in athletic competitions over time?

A

Scores tend to revert to the mean, showing a pattern of improvement or decline

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

In the context of golf scores, what does a shallower regression line indicate?

A

Players who perform above average in one round tend to perform worse in the next round

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

Fill in the blank: Golf scores are a function of both skill (signal) and _______.

A

[noise]

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

What might explain why a player who had a good score in round 2 had a worse score in round 1?

A

Reversion to the mean, not necessarily pressure from performing well

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

What is the implication of seeking help when performance is unexpectedly poor?

A

It may lead to misattributing improvement to the help received rather than reversion to the mean

33
Q

Why might people believe that chiropractic adjustments or test prep strategies are effective?

A

Because people often seek help when at their worst, leading to natural improvement

34
Q

What is a common misconception about broken-windows policing?

A

That it is effective, while reversion to the mean may explain the observed decrease in crime

35
Q

What did a 2002 study on arthroscopic knee surgery reveal?

A

The surgery had no detectable effect on knee pain compared to sham surgery

36
Q

True or False: The placebo effect is when belief in treatment activates the body’s healing powers.

37
Q

What do medical researchers use to account for the placebo effect in trials?

A

Control groups receiving placebos, like sugar pills or fake surgeries

38
Q

What is one consequence of failing to consider reversion to the mean in scientific studies?

A

It can lead to misinterpretation of the effectiveness of interventions

39
Q

What is the placebo effect?

A

The phenomenon where believing you’re receiving a treatment can lead to health improvements, even without actual treatment.

Placebos can include sugar pills or fake surgeries.

40
Q

What is a treatment group in medical trials?

A

The group that receives the actual drug or treatment being tested.

41
Q

What is a control group in medical trials?

A

The group that receives a placebo treatment for comparison against the treatment group.

42
Q

Why is the improvement of the control group seen as evidence for the placebo effect?

A

Because both the treatment and control groups often show health improvements.

43
Q

What is reversion to the mean?

A

The statistical phenomenon where extreme observations tend to be followed by more average ones.

44
Q

What is a more effective way to test for a placebo effect?

A

Dividing the subjects into a group that receives a placebo and a group that receives no treatment at all.

45
Q

What did the 2011 study by Harvard Medical School find regarding asthma treatments?

A

Only the real treatment improved lung capacity, while placebo treatments did not.

46
Q

What is the implication of the findings regarding the placebo effect?

A

It suggests that the placebo effect may reflect mind over mind, not mind over matter.

47
Q

Who is Linus Pauling and what is his relation to vitamin C?

A

A chemist who advocated for vitamin C’s health benefits, despite little evidence supporting its effectiveness beyond preventing scurvy.

48
Q

What are the components of an estimate from data according to the favorite equation?

A

The true estimand, bias, and noise.

49
Q

What causes estimates to vary across different studies of the same phenomenon?

A

Noise from sampling variation.

50
Q

What is cosmic habituation?

A

The phenomenon where estimated effects tend to decrease in magnitude upon replication due to reversion to the mean.

51
Q

What role does publication bias play in scientific studies?

A

It affects which studies are published and replicated, often favoring surprising or statistically significant findings.

52
Q

What is the efficient-market hypothesis?

A

The theory that stock prices reflect all available information and that it is impossible to consistently predict price changes.

53
Q

In which scenarios should we not expect reversion to the mean?

A

When the signal is much greater than the noise.

54
Q

Why is there typically no reversion to the mean in stock prices?

A

Because stock prices reflect investors’ beliefs about the future, not just past performance.

55
Q

True or False: Beliefs can revert to the mean.

56
Q

What are some challenges created by the presence of noise in data?

A

Over-comparing, under-reporting, and reversion to the mean.

57
Q

What is bias in the context of estimating relationships?

A

A systematic error that can affect the accuracy of estimates, particularly in causal relationships.

58
Q

What is the Hawthorne effect?

A

The phenomenon whereby subjects change their behavior because they know they are being studied.

59
Q

What is a demand effect?

A

A specific instance of a Hawthorne effect in which research subjects change their behavior to try to please the researcher.

60
Q

Define signal in the context of outcomes.

A

The systematic component of an outcome that is persistent across observations.

61
Q

Define noise in the context of outcomes.

A

Random components of an outcome that change from observation to observation.

62
Q

What is reversion to the mean?

A

The phenomenon whereby, if one observation of an outcome made up of signal and noise is particularly large (respectively, small), other observations will typically be smaller (respectively, larger).

63
Q

True or False: Bias is a concern when learning about causal relationships.

64
Q

What does the phrase ‘correlation doesn’t imply causation’ mean?

A

The correlation between two features of the world may be a biased estimate of the causal relationship between them.

65
Q

What is the Dunning-Kruger effect?

A

The phenomenon where people with low ability in a domain overestimate their ability, while those with high ability are more accurate in assessing their own skills.

66
Q

What is the typical evidence for the Dunning-Kruger hypothesis?

A

Subjects tend to overestimate their IQ when they have low IQs and are more accurate when they have high IQs.

67
Q

Fill in the blank: The systematic component of an outcome is known as _______.

68
Q

Fill in the blank: Random components of an outcome that change from observation to observation are known as _______.

69
Q

What might you want to analyze to understand if players lose their nerve when aiming to break a record?

A

Collect data on performance under pressure and analyze trends in performance over time.

70
Q

What happens to a player’s performance after an exceptional start to a season, according to the concept of reversion to the mean?

A

They are likely to hit fewer home runs than in the initial exceptional games.

71
Q

What is the implication of mean reversion in stock prices?

A

It suggests that after a significant drop, a stock may not necessarily rebound as expected.

72
Q

In the context of self-assessment, what is the relationship between ability and accurate assessment according to psychologists?

A

A person’s ability in a domain affects their capacity to accurately assess their own ability.

73
Q

What is one potential flaw in the reasoning that if Paul’s son has a genius-level IQ, Paul must have a super-genius-level IQ?

A

Mean reversion; it does not necessarily follow that Paul’s IQ is higher due to John’s exceptional score.

74
Q

What should you consider when analyzing claims about phenomena that could be explained by mean reversion?

A

Evaluate the evidence presented and explore alternative explanations that account for the data.

75
Q

What is a common misconception related to the Hawthorne effect?

A

That changes in behavior are solely due to awareness of being studied, when they may be caused by other factors.

76
Q

What is the focus of Part 3 in the discussed content?

A

Examining the sources of bias in causal relationships and strategies for estimating them in an unbiased way.

77
Q

What is the significance of the figure showing the relationship between self-assessed IQ and test-assessed IQ?

A

It illustrates that people with low IQs tend to overestimate their abilities, while those with high IQs are more accurate.

78
Q

What did Levitt and List (2011) analyze regarding the Hawthorne effect?

A

They showed that the original data suggesting a Hawthorne effect was likely misinterpreted and attributed to other factors.