Measurement Scales Flashcards
What are the two types of error found in statistical studies?
Random Error (chance) Systematic Error (bias)
What causes random error and what is it reduced by?
- Caused by sampling variation
- Reduces as sample size increases
How is systematic error quantified?
By the difference between the true value and the expected value
What are the 3 types of systematic error? Give a description of each
External Validity - study sample is not representative
Internal Validity - groups within the study aren’t comparable
Healthy Worker Effect - individuals exhibit lower overall mortality
What are the 4 sources of bias?
- Recall error
- Observer error
- Measurement error
- Misclassification
What is prevalence and how is it measured?
Proportion of people who have a disease at a given point in time
Number of People with the Disease / Total Population
What is incidence and how is it measured?
- The number of new cases of a disease within a given timeframe
- Measured in events per person, per year
What compares the incidence rate between two groups?
Incidence rate ratio
What is relative risk?
Describes the comparison of event probability between two groups
What is an odds ratio?
A relative comparison of the odds of two groups
What is the equation for odds ratio?
Odds of group A / Odds of group B
ad / bc
How is relative risk calculated?
Absolute risk for group A / Absolute risk for group B
What is risk difference and what is the equation used for this?
- The difference in risk between 2 groups
Absolute Risk in Group A - Absolute Risk in Group B - No difference between groups = 0
What is confounding?
When the association or effect between an exposure or outcome is distorted by another variable
How can confounding be minimalised?
By adjusting data using standardisation (weighted averages)
