Sem 2 (3) Flashcards
Explain confounding
State what the confounder is
The mixing of effect between exposure,
the disease and
a third variable (which is the confounder)
Give some common cofounders
Age
Sex
Ethnicity
Smoking
Deprivation
Standardisation
the process of putting different variables on the same scale
What is the solution to cofounders?
Standardisation
What does standardisation allow?
to compare scores between different types of variables
Ecological study
What do they study?
Give an example
Data on group-level characteristics on groups of people
Colon cancer incidence per 100 women and per capita daily meat consumption
Issues with ecological studies
Measurement variation
Confounding
Chance - random error
Explain the issue of confounding with ecological studies
falsely inferring individual level association from group-level association
Cross sectional survey
What do they measure?
Who?
Give an example
Exposure and outcome measured simultaneously
Individuals
Effect of aircraft noise exposure on heart rate during sleep in the population living near airports
Which type of study/survey is most appropriate for prevalence?
Cross-sectional
Issues with cross sectional surveys
Sampling bias
Chance - random error
Confounding
Responder/participant bias
Case control study
What two bits of information are collected?
Then what?
Previous exposure status of everyone
Group of cases and non-cases
Compare the level of exposure to cases and controls
Which study type is retrospective?
Prospective?
Case-control study - looks back in time
Cohort study
What are the two types of case-control study?
Conventional
Nested
Conventional case control study
Retrospective collection of data (from recall)
Nested case control study
Collection of data from evolving outcome and exposure database of a concurrent or prospective cohort study
Advantages of a nested case-control study
Incidence rates can be calculated
Population for sampling is already defined
Can collect more detailed info
Issues with case-control study
Selection bias
Information bias
Confounding
Chance - random chance
Advantages of case control studies
Cheap
Quick
Good for rare diseases
Can study multiple exposures for single outcome
Selection bias issues (2)
The controls may not be comparable
The controls don’t represent the study population
Information bias issue
Misclassification
Types of misclassficiaiton (2)
What type of bias is it?
Non-differentiated - randomly inaccurate
Differentiated - systematic
Information bias
