stats Flashcards

1
Q

level 1

A

3 RCTs
meta-analysis of all relevenat RCTs

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

level 2

A

1 large RCT

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

level 3

A

controlled trials without randomisation

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

level 4

A

case control or cohort

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

level 5

A

systematic qualititive

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

level 6

A

single qualititive

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

relative risk >1

A

increased risk in exposed groups

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

relative risk of 0.8

A

risk in exposed group is 20% lower than the unexposed group

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

how prevalence affects PPV

A

low prevalence may have a low PPv despite high spec and sensitivity

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

OR <1

A

exposure is associated with a lower odds of outcome

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

exposure is associated with a higher odds of outcome

A

OR>1

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

type 1 error

A

rejecting the NH when it is true

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

type 2 error

A

accepting the NH when it is false

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

value towards 1 indicates low false positives

A

specificity- rules iN disease

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

value towards 1 indicated low false negative

A

sensitivity - rules OUT disease

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

how does prevalance affect PPV

A

low prevalance will have low PPV

17
Q

calaculating prevalence

A

incidence x disease duration

18
Q

how to calculate incidence

A

nos of new cases / number at risk in that time

19
Q

how to calculate prevalence

A

nos of total cases/ total population