Study Designs

Question 1

Define covariate

Answer 1

• Covariates: characteristics (excluding the actual treatment) of the participants in an experiment
• Can be an independent variable (i.e. of direct interest) or it can be an unwanted, confounding variable

Question 2

Define confounding variable

What are 3 ways these can be dealt with?

Answer 2

• Confounding variable: a variable other than variables we are investigating that varies across treatments/groups
  
  • Ex., gender

1. Control for the variable/limit it
2. Measure it as part of the study (cofactor)
3. Ignore it (intentional or accidental)

Question 3

Define cofactor

Answer 3

• Cofactor: a variable measured as part of the study design that may or may not be important

Question 4

Compare replication and pseudo-replication

Answer 4

• Replication: more than one individual in a treatment group
  
  • Accounts for variation among individuals
• Pseudo-replication: measuring the same individual more than once
  
  • May account for measurement error

Question 5

Describe the 4 ways to control for a variable

Answer 5

1. Limit variation (controlling the environment)
2. Blocking (treat it as a cofactor)
3. Blinding (guard against bias)
4. Comparison (more than one treatment group)

Question 6

What is the randomized block design?

Answer 6

Randomised block: units from the sample are subdivided into blocks based on pre-existing characteristics, then randomly assigned from blocks to a treatment

Question 7

What is the matched pairs design?

Answer 7

• Matched pairs: pairs of units from the sample are matched based on similarity across pre-existing characteristics, then randomly assigned from pairs to treatments
  
  • An individual can be matched with themself (repeated measures)

Question 8

What is case control (observational)?

Answer 8

• Case control: subjects selected based on a defined outcome

Question 9

What is cohort (observational)?

Answer 9

• Cohort studies: subjects sharing a common characteristic are bserved at regular intervals over an extended period of time

Question 10

What is sample survey (observational)?

Answer 10

• Sample survey: a random sample drawn from the entire population of interest at one point in time, and the sample is usually surveyed

Question 11

Define ecological validity

Answer 11

• Ecological validity: will the results reflect the responses as would be observed in a “natural” environment?