Study Design

Question 1

double blind

Answer 1

both experimenter and subjects are blinded

Question 2

crossover study

Answer 2

Each study participant receives all treatments that are being investigated but at different times

Order of treatments is randomized

Washout often included between treatments

Question 3

partial crossover or incomplete block

Answer 3

In some crossover designs, particularly ones with more than 2 treatments, patients may not receive all treatments under investigation, but would receive more than 1

Question 4

Pros of Crossover Study Design

Answer 4

Each patient serves as their own control.

Reduces between-subject variability.

Allows for detection of smaller effect sizes with reduced sample sizes.

Question 5

Effect Size

Answer 5

Quantitative measure of the magnitude of a phenomenon (eg. the correlation between 2 variables)

Small effect size is one in which there is a real effect, i.e. something is really happening in the world - but which you can only see through careful study.

Question 6

Parallel Study

Answer 6

Two groups of treatments: A & B

One group receives only A, other group receives only B

Question 7

Longitudinal Study

Answer 7

Repeated observations of the same variables over short or long periods of time.

Often observational but can be structured as longitudinal randomized experiments.

Question 8

Large Effect Size

Answer 8

Can be seen by the naked eye, easily observed.

Question 9

Small Effect Size

Answer 9

There is a real effect, i.e. something is really happening in the world - but which you can only see through careful study.

Question 10

Confounders

Answer 10

Variable that influences both dependent and independent variables.

Question 11

Why is the influence of confounders reduced in crossover studies?

Answer 11

Each patient is their own control.

Question 12

Optimal crossover designs require ________ subjects.

Answer 12

fewer

Question 13

Which patient population best aligns with crossover study design?

Answer 13

Crossover studies are often done to improve symptoms of patients with chronic conditions.

May be infeasible or unethical for curative treatments or rapidly changing conditions.

Question 14

What are two main issues with crossover studies?

Answer 14

1. “Order” Effects. Order of treatment may effect outcome, eg. drug with many adverse effects given first, making patients taking a 2nd, less harmful medication, more sensitive to any adverse effects.
2. “Carry-over”. Carry-over between treatments which confounds estimates of treatment effects. In practice “carry-over” effects can be avoided with a sufficiently long “wash-out” period between treatments. However, planning for sufficently long wash-out periods requires expert knowledge of the dynamics of the treatment, which is often unknown.