Module 11 Flashcards
Evaluating epi associations (key questions 1-3)
- Could association have been observed by chance?
- Determined through statistical tests - Could association be due to bias?
- Bias refers to systematic errors (ex: sample selection, data analysis) - Could other confounding variables have accounted for the observed relationship?
Evaluating epi associations (key questions 4-5)
- To whom does this association apply?
- Representativeness of sample
- Participation rates - Does the association represent a cause-and- effect relationship?
- Considers criteria of causality.
Statistical power
The ability of a study to demonstrate an association if one exists. Determined by:
– Frequency of the condition under study
– Magnitude of the effect
– Study design
– Sample size
How to know study is valid
Eliminate alternative explanations
o Bias (systematic error)
o Confounding
o Random error
Internal validity
The appropriate measurement of exposure, outcome, and association between exposure and disease
– Proper selection of study groups
– Lack of error in measurement
External validity
The ability to generalize beyond a set of observations to some universal statement
Random errors
Reflect fluctuations around a true value of a parameter because of sampling variability. Contributing factors:
- Poor precision
- Sampling error
- Variability in measurement
Poor precision
- Occurs when the factor being measured is not measured sharply
- Precision can be increased by increasing sample size or the number of measurements
Sampling error
- Occurs when the sample selected is not
representative of the target population - Increasing the sample size can reduce the
likelihood of sampling error
Variability in measurement
The lack of agreement in results from time to time reflects random error inherent in the type of measurement procedure employed
Factors that contribute to systematic errors
- Selection bias
- Information bias
- Confounding
Bias
Systematic error that leads to incorrect/invalid estimate of association (easier to avoid than to remove or fix)
Types: selection, information
How to evaluate for bias
o Identify source
o Estimate magnitude
o Assess direction
Selection bias
Error due to systemic differences in characteristics between those selected for study and those not
o Case control—if different criteria related to exposure
o Retrospective cohort—if selection of exposed or unexposed group related to outcome
Preventing selection bias
o Define study population independent of disease not after cases appear (prior to follow-up)
o Get same information from cases and controls
o Don’t let disease influence the availability of information
o Don’t let disease influence loss of subjects to follow-up
Information bias
The means of obtaining information about subjects is inadequate/ incorrect. Sources: 1. Misclassification bias 2. Bias in abstracting records 3. Bias in interviewing 4. Bias from surrogate interviews 5. Surveillance bias 6. Recall bias 7. Reporting bias
Confounding
Mixing of effects between exposure, outcome,
and third variable (confounder)
Factors other than exposure that ↑↓ risk of disease
Criteria for confounders
To be a confounder, an extraneous factor must satisfy the following criteria:
- Be a risk factor for the disease
- Be associated with the exposure
- Not be an intermediate step in the causal path between exposure and disease
Confounding magnitude and direction
Magnitude of confounding = (RR crude – RR adjusted)/RR adjusted
o Size bias depends on degree of association
o Effect of multiple confounders may be large
Direction of confounding
o Exaggerate (positive confounding)
o Hide (negative confounding)
Methods to control confounding
Prevention strategies—attempt to control confounding through the study design itself
In designing the study: Individual and Group matching
In analysis of data: Stratification and Adjustment
Matching
Matches subjects in the study groups according to the value of the suspected/known confounding variable to ensure equal distributions.
- Frequency matching: the # cases with particular match characteristics is tabulated (Group matching)
- Individual matching: the pairing of one or more controls to each case based on similarity in sex, race, or other variables (matched pairs)
Analysis strategies to control confounding
- Stratification: analyses performed to evaluate the effect of an exposure within strata (levels) of the confounder
- Multivariate techniques: use computers to construct mathematical models that describe simultaneously the influence of exposure and other factors that may be confounding the effect
Risk factors
Exposure that is associated with a disease.
Due to the uncertainty of “causal” factors the term risk factor is used.
Criteria for risk factors
- The frequency of the disease varies by category or value of the factor (ex: light vs. heavy smokers)
- The risk factor precedes onset of the disease
- The observation must not be due to error
Koch’s Postulates for disease causation
Criteria to prove an organism caused disease:
– The organism is always found with the disease
– The organism is not found with any other disease
– The organism isolated from the diseased host can produce disease when introduced to another susceptible host
*Not as useful for non-infectious diseases
Modern concepts of causality
- 1964 Surgeon General’s Report - Five criteria for causality: strength of association, time sequence, consistency upon repetition, specificity, coherence of explanation
- Sir Austin Bradford Hill expanded list to include: biologic gradient, plausibility, experiment, and analogy
