Reproducibility Crisis Flashcards

1
Q

Brian Wansink

A
  • experiments on eating behaviours
  • abused statistical procedures to look like research was successful
  • p-hacking and HARKing
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is ‘Crisis of Reproducibility’?

A

published research can’t be replicated/reproduced

  • misuse of statistics
  • not just about statistics
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Why researchers use statistics?

A
  • to find relationships between variables if they think they are linked
  • ignore noise and try find relationships that hold true ‘in general’
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What hypothesis do researchers test for?

A

null hypothesis / statistical tests that estimate how well the data supports the null hypothesis
- rarely test if a relationship exists but test to see if no relationship exists

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

what is the null hypothesis?

A

hypothesis that no relationship (statistical significance) exists

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

What is the p-value?

A
  • probability that null hypothesis is true (probability that results are due to chance)
  • lower p-value –> less likely null hypothesis is true; more reasonable to reject null hypothesis
  • higher p-value –> more likely null hypothesis is true (no relationship exists); accept null hypothesis
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What would be the null hypothesis for study testing to see if there’s an extra $1000 annual income per year of schooling?

A
  • there is no relationship between years of schooling and income
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What does a p-value of 0.55 mean?

A
  • 55% chance that null hypothesis is true / 55% chance that there’s no relationship between years of school and income
  • expect a statistical test this extreme 55% of the time
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What does a p-value of 0.01 mean?

A
  • 1% chance that null hypothesis is true
  • very unlikely that there’s no relationship between 2 values
  • very unlikely to get p-value this extreme
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Most common cut off for statistical significance

A

p < 0.05

- researchers only incorrectly reject null hypothesis 5% of the time (1 in 20)

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

What is the issue with p-value cut off being <0.05?

A
  • p<0.05 so 1 in 20 (5%) chance that null hypothesis is true
  • so for every 20 tests run, you will incorrectly reject null hypothesis 1 time (null hypothesis is true in in 20 times)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is p-hacking?

A
  • Repeating a statistical test to get false positives / false statistically significant results
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is HARKing?

A

Hypothesis after results are known

- can’t collect data then frame hypothesis around data

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

What is the risk of a false positive with the accepted p value for a statistically significant result

A
  • 1 in 20 chance of false positive (rejecting null hypothesis when it is true and there’s actually no relationship)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Examples of why research can be wrong

A
  • small sample size
  • publishing studies with small effects
  • relying on a small number of studies
  • generating new hypothesis to fit data
  • flexibility in research design
  • intellectual bias
  • conflict of interest
  • competition to produce positive results
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Is flexibility in research design good?

A

NO - shouldn’t change research design to fit data

17
Q

Why does so much research fail to replicate?

A
  • bad method
  • researchers not constrained
  • culture in research to get new and exciting results
18
Q

Example of how researchers edit their data

A
  • exclude outliers from analysis
  • p-hacking
  • HARKing
  • stopping collecting data when they achieved their desired results
  • looking for effect in subgroups instead of whole populations
19
Q

How do researchers get away with this sloppy science

A
  • they have freedom in research
  • ## they justify altering methods midway as flexibility
20
Q

Can researchers justify altering research design before it’s complete

A

not good but sometimes there’s good reasons, e.g. :

  • study causes harm
  • trial working (can’t deny control group)
21
Q

Why is it bad that researchers don’t share their data/methods

A

can’t be checked and critiqued

- privacy restrictions / archive fails

22
Q

What effect does researchers wanting positive results have on fellow research?

A

publication bais towards pos results:

  • studies aren’t replicated
  • neg results turned into pos results
  • neg results aren’t publishes
23
Q

What can be done to improve statistical use in research?

A
  • better training
  • p < 0.01 (null hypothesis incorrectly rejected 1 in 100 times)
  • confidence intervals instead of significance testing
  • make raw data available