Chapters 16 and 17 Flashcards

1
Q

What does Statical Hypothesis Testing do?

A

It automates decision-making and favors objectivity by setting a threshold a priori.

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

a (alpha):

A

used to designate the significance threshold

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

What do you conclude and therefore do if a P value is less than the alpha?

A

Conclude that the difference is statistically significant and reject the null hypothesis

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

Type I Error

A

Incorrectly reject null

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

Type II Error

A

Incorrectly fail to reject null

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

Is there an option to accept null?

A

No, just to reject or not

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

Which type of error is preferred?

A

Usually, a type II error is preferred over type I error. e.g. prefer to release a criminal over imprisoning innocents

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

Choose alpha how?

A

a priori

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

Which alpha is common?

A

0.05 is common

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

Increasing alpha makes what more likely?

A

Increasing alpha makes type I more likely and type II less likely.

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

Decreasing alpha makes what more likely?

A

Decreasing alpha makes type II more likely and type I less likely

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

What kind of alpha will a very conservative scientist choose?

A

A low alpha, however, scientists often just report the exact P value and put less emphasis on choosing alpha.

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

You will never know…

A

from a single analysis if you have made a type I or type II error.

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

Even worse error than type I or type II.

A

Rejecting the null hypothesis correctly but wrong about effect direction.

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

The only way to reduce the chances of all three errors is…

A

to increase sample size.

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

Just because a result if statistically significant does not ensure…

A

that it is scientifically important.

17
Q

The ______ may not be worthy of attention.

A

size of the effect.

18
Q

Common mistakes

A
  1. Believing that statistical hypothesis testing is an essential part of all statistical analyses
    - Could just look at P value and CI without alpha
19
Q

Common mistakes 2

A
  1. Believing that if a result is statistically significant, the effect must be large.
    - Focus on the size of the effect and its CI
20
Q

If the sample size is large enough, even tiny, inconsequential differences will be…

A

statistically significant.

21
Q

Common Mistakes 3

A

If the results are non-significant with the analysis that you chose, you can’t just do a slightly different analysis (e.g. nonparametric) with the same data and report only the most unusual results

  • You shouldn’t just add more data if you got close but not quite significant results (must redo all of it)
  • Probably a common violation
22
Q

Don’t do multiple tests and just…

A

report the significant ones (No data diving)

  • Possibly the cause of many conflicting studies and reporting significant but incompatible results
  • If many separate labs study the same problem then this can happen inadvertently
23
Q

If the 95% CI includes the value that defines the null hypothesis, you can conclude the P value is…

A

> 0.05

24
Q

If the 95% CI excludes the null hypothesis value, then the P value is…

A
25
Q

The size of the CI and the range of the nonsignificant values are the same size if confidence level=

A

1-alpha