DATA COLLECTION CHOOSING THE BEST PLACE TO SOURCE 9/2/17

Question 1

What are signs of measurement error? (3)

Answer 1

1. inherent variation/instability in the variable
2. imperfect meausrement equipment/technique
3. the same variables arising from the same questions may be biased in different ways depending on the context

Question 2

What is response bias?

Answer 2

what interview wants they get

Question 3

What is prestige bias?

Answer 3

what appears favourable

Question 4

What is recall bias

Answer 4

prospective/retrospective

Question 5

Missing variables

Answer 5

1. are they in key variables
   e. g. exposure or outcome
   - find alternative variable

or in a potential confounder

• assess what the potential consequences are of not including this variable
• think of the proxies

Question 6

What does missingness/missing data in key variables reduce?

Answer 6

it reduces the number of participants on whom you have complete data

Question 7

What happens if there is missing data in some key variables? e.g. outcome, exposure or confounder

Answer 7

1. compare participants with complete and missing data
2. create a missing category for missing measurements
3. interpolate/ statically estimate what the missing measurements might/are likely to have been