Week 1

Question 1

What are the three questions to find out confounders?

Answer 1

Q1: is the variable a risk factor/protective factor for the outcome?
Q2: is the variable associated with the exposure?
Q3: is the variable not an intermediate in the causal pathway?

Question 2

What is selection bias in a cohort study?

Answer 2

When there is a difference in the loss to follow up or enrollment procedures

Question 3

What is the target population in a cohort?

Answer 3

The population you want the study to be generalizable to

Question 4

What is the source population in a cohort?

Answer 4

People who can join in the study

Question 5

What is the study population in a cohort?

Answer 5

People who start the study with you (reply to the invitation)

Question 6

What is the population for analysis in a cohort study?

Answer 6

People with all data available

Question 7

Which populations differ from each other when external validity is not good?

Answer 7

The source population differs from the target population.

Question 8

Which type of selection bias is likely with cross-sectional and case-control studies?

Answer 8

Selective enrollment issues

Question 9

Which type of selection bias is likely with prospective cohorts and RCTs?

Answer 9

Selective loss to follow up?

Question 10

Which populations differ from each other when selection bias occurs?

Answer 10

study population from the source population or population for analysis

Question 11

What are the disadvantages of a cross-sectional study?

Answer 11

reverse causality, assessment of prevalence, selection bias (enrollment)

Question 12

What are the disadvantages of a cohort study?

Answer 12

Expensive, time-consuming, confounding, external validity (effect modification), long enough follow up time?, selection bias (loss to follow up), information error

Question 13

What are the advantages of a cohort study?

Answer 13

Cause and effect is clear, rare exposures can be studied, possible to investigate exposure over time, possible to study many different outcomes

Question 14

What is the study outcome of a cross-sectional study?

Answer 14

Prevalence ratio

Question 15

What is the outcome of prospective studies?

Answer 15

IRR/IPR = RR

Question 16

What is the outcome of case-control studies?

Answer 16

OR (estimate of IRR)

Question 17

With what study designs do you match cases with controls?

Answer 17

(nested) case control

Question 18

What are the weaknesses of a case-control?

Answer 18

Selection bias (enrollment), information error (recall bias), confounding (reduced by restriction/matching/stratification), effect modification, reverse causation, hard to define exposure afterwards

Question 19

What are the advantages and disadvantages of looking at prevalence vs incidence in a case-control?

Answer 19

Prevalence: more cases but they could have changed their exposure
Incidence: no changed exposure but you need to interview people very soon after their diagnosis

Question 20

What are the advantages and disadvantages of looking at hospital-based vs population-based controls in a case-control?

Answer 20

Hospital based controls: potential information errors are the same as in the cases, but selection could be related to the exposure
Population based controls: they are more representative for the source population, but it is hard to reach the population

Question 21

What are the advantages of a case-control?

Answer 21

You can study rare diseases and many risk factors at once

Question 22

What are the weaknesses of a RCT?

Answer 22

Ethical, short term, fixed exposure, intermediary endpoints, high risk populations, effect modification, selection bias

Question 23

Is the case cohort a prospective or retrospective design? And what type of bias is therefore limited?

Answer 23

Prospective, recall and selection bias

Question 24

What people are the comparison in a case cohort?

Answer 24

A random sample of the whole cohort: sub-cohort. They are all free of disease at baseline

Question 25

What are the advantages of a case-cohort?

Answer 25

Efficiency, reduces selection bias and recall bias, can be used for multiple diseases and sub-cohort can be used to calculate person-time risk

Question 26

What are the disadvantages of a case-cohort

Answer 26

Need large cohort, reduces power, loss to follow up, no matching, potential sample degradation

Question 27

Is the nested case control a prospective or retrospective design? And what type of bias is therefore limited?

Answer 27

Prospective, recall and selection bias

Question 28

Describe the selection of cases and controls in a nested case control study

Answer 28

Cases are all new cases of the disease and each control is sampled from the cohort with incidence density sampling

Question 29

What are advantages of the nested case-control?

Answer 29

Efficiency, reduction of selection and recall bias

Question 30

What are disadvantages of the nested case-control?

Answer 30

Reduced power, case-control pairs can only be used for 1 outcome, person time is not estimate

Question 31

When does selection bias occur?

Answer 31

When those selected to be in the study differ from those not selected

Question 32

Is selection bias a threat for internal or external validity?

Answer 32

Internal

Question 33

What are two types of selection bias?

Answer 33

Enrollment and follow up

Question 34

What are two types of information error?

Answer 34

``` Measurement errors (continuous variables) Classification errors (discrete variables) ```

Question 35

What will happen with a distribution when there are random errors?

Answer 35

The distribution will become wider -> more people in the tips.

Question 36

What is sensitivity and specificity regarding information error?

Answer 36

Sensitivity: percentage of the exposed that are correctly classified specificity: percentage of the unexposed that are correctly classified

Question 37

How can you check for confounding when looking at graphs?

Answer 37

Draw an imaginary line through the data

Question 38

If the crude OR is 3, and the stratified ORs are 1,5 and 1,5 is it confounding or effect modification?

Answer 38

Confounding

Question 39

If the crude OR is 3, and the stratified ORs are 4 and 1,5 is it confounding or effect modification?

Answer 39

Effect modification

Question 40

How can you control confounding?

Answer 40

Through the design (restriction and matching) | Through data analysis (stratification, multivariable modelling)

Question 41

Will the power increase or decrease when the effect size will get larger?

Answer 41

Increase

Question 42

Will the power increase or decrease when the variance will get smaller?

Answer 42

increase

Question 43

Will the power increase or decrease when the sample size will get smaller?

Answer 43

Decrease

Question 44

Will the power increase or decrease when the alpha will get bigger?

Answer 44

Increase

Question 45

What is counterfactual thinking?

Answer 45

What if the situation would be exactly the same but with 1 thing different

Question 46

How can you imitate counterfactual thinking?

Answer 46

With well controlled RCTs

Question 47

What is additivity, synergism and antagonism in the causal model of rothman?

Answer 47

No interaction, and interaction

Question 48

If the background risk is low, are you more or less likely to pick up a high RR?

Answer 48

More likely

Question 49

What do you do when the heterogeneity is high with a meta-analysis?

Answer 49

Try to stratify or subgroup analysis

Question 50

What is a sensitivity analysis?

Answer 50

Exclude studies with a high risk for bias

Question 51

How can you check for publication bias?

Answer 51

With funnel plots, if it is symmetric, there is no publication bias.

Question 52

What is the difference between fixed and random effect models?

Answer 52

Fixed: you assume that there is 1 true association Random: assume populations differ from each other