Measures of Effect in 2x2 Tables Flashcards

1
Q

How do we calculate a risk ratio?

A

Risk of poor outcome in group a / Risk of poor outcome in group b

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

How do we interpret risk ratios?

A

= 1 means same risk
>1 means increased risk
<1 means reduced risk

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

What is the convention for risk ratios in clinical trials?

A

New, active or experimental treatment /conventional, placebo or control

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

What is the odds ratio?

A

The odds ratio (OR) is the ratio between the odds of the outcome in the active group and the odds of the outcome in the control group.

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

What additional step is required when calculating confidence intervals for risk ratios?

A

Calculate the standard error of the ln risk ratio (avoids answers with negative risk ratios which are meaningless)

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

Following using the ln risk ratio, how do we get back to the original risk ratio scale?

A

Anti-log of the final answer

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

How do we calculate a risk ratio with a confidence interval of 95%?

A

exp( ln(RR) +/- 1.96 * SE(lnRR) )

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

How can we calculate risk ratio confidence intervals using the error factor method?

A

See formula

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

How can we describe the sampling distribution of the ln risk ratio when n is sufficiently large (>10)?

A

We can say that it is approx normal therefore we can calculate a confidence interval with the formula we know from previous calculations

The same can be said about odd ratios

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

What happens to the risk ratio as the overall risk increases?

A

It becomes less extreme.

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

What is the number needed to treat?

A

The “number needed to treat” (NNT) is 1/risk difference.

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

How do we interpret NNT?

A

The lower the number the better

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

What is the number needed to harm?

A

For adverse events. Calculated the same way as NNT but larger numbers are better (i.e. more rare)

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

Why do some researchers prefer odds ratios?

A

The interpretation of the results does not depend on the occurence or non-occurence of an event is used as the outcome. Therefore

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

Statistically speaking, why might odds be more useful?

A

Confidence interval formula approximations are better for smaller sample sizes than risk ratios

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

Why is it important to identify confounders?

A

Skews data if not recognised - leading to false assumptions

Techniques can be used to adjust for confounders

Secondary analyses such as looking for characteristics associated with worse outcomes are susceptible to confounding

17
Q

What three variables must we consider in assessing a potential confounder?

A

Exposure of interest
Outcome of interest
Confounder

18
Q

What are the three criteria of confounders?

A
  1. An independent risk factor for the outcome of interest
  2. Associated with the exposure of interest
  3. Not a causal pathway between exposure and outcome
19
Q

Define the causal pathway

A

The causal pathway is the sequence of events that leads to an outcome being affected by an exposure

20
Q

How do stratified tables help to adjust for confounders?

A

Start with the unstratified table (crude table)

Divide groups into strata to explore the confounder

Calculate X2 and P-value of each strata to find significance

If the P-values are both more significant than the crude table then the confounder is confirmed

21
Q

What technique can we use to account for a confounding factor?

A

Mantel-Haenszel method

22
Q

How does the Mantel-Haenszel method work?

A

It is a weighting method of calculating the overall risk ratio adjusted for the effect of the confounder depending on whether it is a positive or negative confounder

23
Q

How does the Mantel-Haenszel method weight its calculation?

A

It gives more weight to the group with the larger sample size

24
Q

Where else can the Mantel-Haenszel method be employed in potential confounder identification?

A

Chi-squared testing

25
Q

Is there a statistical test for confounding?

A

No

26
Q

How are confounders adjusted for in RCTs?

A

Randomisation breaks the relationship between exposure and confounder

27
Q

Can the influence of confounders be total mitigated in RCTs?

A

No, weak relationships between treatment and potential confounders can still exist by chance - often called baseline imbalance. Therefore RCTs may present both adjusted and non-adjusted data to evidence baseline imbalance

28
Q

What are the potential effects of confounding?

A
  1. May be significant before adjusted and then non-significant after
  2. THe association may remain significant but with a less significant p-value
  3. The strata may show opposing results i.e. effect modifiers (common ones include gender). This phemonema is usually of interest in sub-group analyses. This can be tested for with an interaction test.
  4. The confounder may mask or partially hide an association that exists. As in RITA-3
29
Q

Does adjustment techniques like Mantel-Haenszel method always eliminate confounders?

A

No, it is possible for there to be residual confounding.

30
Q

What technique is optimal when dealing with multiple potential confounders?

A

Multiple regression to simultaneously adjust for multiple confounders both discrete and continuous.