# Lecture 6 - Chance, bias, confounding and true causal relationshiop Flashcards

1
Q

What are measures of association?

A
• Identify causes of disease
• Estimate how much disease is due to an exposure
• Compare incidence of disease in two populations
• Common measures (relative risk, odds ratio, hazard ratio)
2
Q

Relative Risk

A

ratio of the risk (incidence) of disease (the outcome) in those ‘exposed’ compared to the risk (incidence) of disease (the outcome) in those ‘not exposed’

RR = (incidence in exposed group)/(incidence in unexposed group)

3
Q

What is the strongest study type in terms of evidence?

A

Meta-analysis of RCTs

4
Q

What are two types of errors?

A
• Random Error

- Systematic Error (aka bias)

5
Q

What is random error?

A

An error that decreases precision

6
Q

What is systematic error?

A

An error that decreases validity

7
Q

What are the three types of bias?

A
• Selection Bias
• Information Bias
• Confounding Factors
8
Q

What is selection of bias?

A

Bias shown in selecting subjects

Usually results from comparative groups not coming from the same study base and not being representative of the populations they come from

9
Q

What is information bias?

A

Bias shown in collecting information or measurements

10
Q

What is the difference between chance and bias?

A
• Chance is caused by random error bias is caused by systematic error
• Errors from chance will dance each other out in the long run (w/ large sample size) bias won’t
• Chance leads to imprecise results while bias leads to inaccurate results
11
Q

How do you asses the role of chance in a study?

A
• Hypothesis Testing

- Estimation

12
Q

What is hypothesis testing?

A
• Use statistical test to examine the null hypothesis

- if p value is less than 0.05 then result is statistically significant

13
Q

What is estimation?

A
• Uses statistical methods to estimate the range of values that is likely to include the true value
• It is associated with “confidence intervals” – if value corresponding to no effect falls outside interval then result is statistically significant
14
Q

What are the benefits of Random Allocation (randomization)?

A
• Reduces bias in those selected for treatment (guarantees treatment assignment will not be based on patient’s prognosis)
• Prevents confounding (known and unknown potential confounders are evenly distributed)
15
Q

What are the two conditions that must be met for confounding factors?

A
• Be associated with exposure (without being the consequence of exposure)
• Be associated with outcome (independently of exposure..not an intermediary)
16
Q

How to minimize confounding factors?

A

Properly design a Randomized Control Trial to distribute confounding factors equally between the groups

17
Q

What are the two main types of information bias?

A
• Reporting Bias (recall bias)

- Observer Bias (interviewer bias and biased follow-up)

18
Q

What are Bradford Hill’s “Criteria” for Judging Causality?

A
• Temporality
• Consistency
• Strength of association
• Dose-response relationship
• Biological plausibility
• Specificity
• Experimental evidence
• Analogy
• Biological coherence
19
Q

How is consistency good?

A

When all different evidences and studies etc show similar results

20
Q

What does strong association mean?

A

It increases likelihood that relationship is one of cause and effect

21
Q

What does a weaker association mean?

A

It means that it is difficult to exclude the alternative explanations (you need to take them seriously)

*But a weak association does not mean it is not causal

22
Q

What is Dose-Response Relationship?

A

It illustrates that with increased dosage or decreased dosage a specific outcome is achieved

23
Q

What is biological plausibility?

A

Biological mechanism by which exposure alters risk of disease