Lecture 4 Categorical data Flashcards

1
Q
  • There is no association between categorical variable 1 and categorical variable 2
  • There is an association between categorical variable 1 and categorical variable 2

which is H0 and H1

A

top is H0 and bottom is H1

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

what is the Chi-squared test?

A
  • Looks at the difference between the observed and expected frequencies across the contingency table
  • The further away the observed values are from the expected values, the more likely it is the two variables are associated

– i.e. less likely the null hypothesis is true

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

what is relative risk?

A

The relative risk (RR) or risk ratio is the ratio of the probability of an outcome in an exposed group to the probability of an outcome in an unexposed group. Together with risk difference and odds ratio, relative risk measures the association between the exposure and the outcome.

Investigates how the risk of an event is associated with exposure to some risk factor

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

if the RR = 1, what does this mean?

A
  • Same likelihood of an event in exposed & unexposed groups
  • No association
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

if the RR <1, what does this mean?

A
  • Less likely to have an event if exposed
  • Negative association
  • Exposure protective
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

if the RR > 1, what does this mean?

A
  • More likely to have event if exposed
  • Positive association
  • Exposure harmful
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q
  • Because cohort studies & randomised controlled trials are prospective, it is possible to directly estimate risk of event based on exposure, ____ use RR
  • Case-control studies are retrospective with selection based on event status. Cannot evaluate risk of event based on exposure, ________ use RR
A

can

cannot

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

Summary: Relative risk

  • Directly estimates effect of _______ on event incidence
  • Used for cohort studies & ____
  • RR _ 1: positive association
  • RR _ 1: negative association
  • Can use ________ _______ to see if have significant association
A

exposure

RCTs

>

<

confidence intervals

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

another way of representing probabilities is _____

A

odds

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

what does Odds ratio = 1, mean?

A
  • Odds of being exposed is same for cases and controls
  • No association
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

what does Odds ratio <1 mean?

A
  • Less likely cases exposed than controls
  • Negative association
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

what does Odds ratio > 1, mean?

A
  • More likely cases exposed than controls
  • Positive association
How well did you know this?
1
Not at all
2
3
4
5
Perfectly