W2: Study Designs Overview

Question 1

Cohort study

Answer 1

Start with source population, select group exposed and unexposed. Follow over time; measure outcomes in each group. Samples based on exposure status and follows prospectively. Investigator does not control exposure.

Question 2

Experimental (Randomized) trial

Answer 2

Source population –> invite people to participate, then randomly assign to treatment or control group. Follow over time, then measure outcomes. Investigator can control the intervention. Intervention precedes outcome measurement.

Question 3

Case-control study

Answer 3

People from source population are selected based on disease status (cases are diseased, controls are not). Ideally drawn from same source population. Investigator does not control exposure (measured in the past). Unique d/t sampling based on outcome.

Question 4

Cross-sectional study

Answer 4

Take sample from source population, measure who is exposed and unexposed. Snapshot – measures at only one point in time; compares outcomes in exposed and unexposed. No information about chronology of exposure and outcome. Can’t show causality.

Question 5

Ecological study

Answer 5

Samples only group-level data; compares different populations (eg colon CA and egg consumption in different countries). Ecological fallacy: incorrect assumption that association at population level exists at individual level (i.e. the men with cancer may not be the same men eating eggs).

Question 6

Quasi-experimental

Answer 6

Study in which groups with and without the intervention appear to differ only in intervention status, but were not randomly assigned

Question 7

Observational

Answer 7

Study in which investigator does not control the intervention

Question 8

Features of experimental studies

Answer 8

• Better quality comparison group
• Must consider ethical aspects of randomization
• Setting may be less realistic

Question 9

Features of observational studies

Answer 9

• More natural setting

- Fewer ethical concerns (no randomization)

Question 10

No individual level data?

Answer 10

Ecological study

Question 11

Goal OTHER THAN to understand how exposure/intervention affects disease?

Answer 11

Cross-sectional study

Question 12

Can you control the exposure/intervention?

Answer 12

YES: Experimental study
NO: Observational study

Question 13

For obs study- Are any of the following true?
Disease is rare
Exposure data difficult/expensive to obtain
Little is known about disease
Disease has long induction or latent period
Underlying population is dynamic
Study needs to be done quickly (eg outbreak setting)

Answer 13

YES: Case-control study
NO: Cohort study

Question 14

Parallel arm study

Answer 14

Type of experimental study in which investigators randomize one group to intervention, one group to control; measure predictors prior and outcomes post.

Question 15

Crossover study

Answer 15

Enrollment process same as parallel arm trial; mid-way through investigators measure outcomes, then have washout period and groups change assignments. Outcomes measured again at the end.

Question 16

Factorial study

Answer 16

Investigators randomize individuals to single or combined treatment (eg drug A &B, drug A & placebo, drug B & placebo, placebos A&B). Interested in single vs combined effects. Assumes intervention effects are independent (if not, larger sample sizes needed)

Question 17

Cluster/community study

Answer 17

Entire groups are randomized rather than individuals. Cluster can be any group w/shared characteristic that connects them (eg people w/certain healthcare provider, villages, schools). Use when intervention delivered at the group level. Special sample size calculations and analyses needed to account for clustering.

Question 18

Exchangeable

Answer 18

Control and treatment groups being balanced on measured and unmeasured characteristics

Question 19

Key requirements for randomization

Answer 19

Truly random (all participants have fixed probability of assignment to each group). Not determined by investigator, clinician, or participants. Not based on predictable pattern (because then investigator could predict who gets intervention vs control).

Question 20

Truly random randomization techniques

Answer 20

Coin flip, random number table, computer generated random number (most commonly used)

Question 21

Non-random randomization techniques

Answer 21

MRN, name, DOB, order of enrollment

Question 22

How do you check that randomization was successful?

Answer 22

Check the balance table (compares characteristics of each group at baseline)

Question 23

What’s the most common reason randomization fails?

Answer 23

Sample sizes are too small

Question 24

Stratified randomization

Answer 24

Randomizing groups separately based on certain given characteristic (eg randomize men separately from women, to ensure even balance of treatment assignment by gender)

Question 25

Block randomization

Answer 25

Randomizing groups separately from each other, eg by geographic location. Can help ensure arms are balanced throughout study. Particularly helpful when sample size is small or trial is interrupted.

Question 26

How might study participants being aware of their treatment assignment affect study outcome?

Answer 26

They may change their health behavior or have a changed perception of their health, which could influence the outcome.

Question 27

How might investigators being aware of treatment assignments affect study outcome?

Answer 27

Their attitudes about the intervention may also influence participants.

Question 28

How might outcome assessors being aware of treatment assignments affect study outcome?

Answer 28

It could influence their measurement of the outcome.

Question 29

How might data analysts being aware of treatment assignments affect study outcome?

Answer 29

It could affect how they make choices in the analysis of the data, which could skew results.

Question 30

Benefits of blinding study participants

Answer 30

Less loss to follow up
Increased compliance with the intervention
Less bias in behaviors or physical responses to intervention

Question 31

Benefits of blinding investigators

Answer 31

Less transfer of attitudes about intervention
Less chance of differential treatment administration
Less chance of differential withdrawal of participants

Question 32

Benefits of blinding outcome assessors

Answer 32

Reduced bias in outcome assessment

Question 33

Benefits of blinding data analysts

Answer 33

Less biased decision making during data analysts

Question 34

Open trial

Answer 34

No blinding used

Question 35

Single blinded trial

Answer 35

Either participants or investigators are blinded

Question 36

Double blinded trial

Answer 36

Two groups do not know treatment assignment (usually study participants and either investigators, outcome assessors, or data analysts)

Question 37

Triple/quadruple blind trials

Answer 37

Three or four groups are blinded (study participants, investigators, outcome assessors, data analysts)

Question 38

Allocation concealment

Answer 38

The person allocating study participants to treatment or control does not know what the next treatment allocation will be. Prevents bias resulting from who is chosen to participate (selection bias)

Question 39

Subjective vs objective outcomes

Answer 39

Subjective outcomes: dependent on judgment of outcomes assessor or study participant
Objective outcomes: not dependent on judgment of outcomes assessor or study participant

Question 40

How will results be biased when non-compliance occurs?

Answer 40

Biased toward the null

Question 41

Intention to Treat analysis

Answer 41

Analyze the data using original treatment assignments, regardless of adherence to treatment assignments. Answers the question “How well does the treatment work among people who were offered it?”

Question 42

Per protocol analysis

Answer 42

Analyze the data using what people actually did (i.e. people who did not adhere to treatment assignments are moved to the other group for analysis). Answers the question “How well does the treatment work among people who received it?”