Observational Studies Flashcards
Descriptive studies ……. hypotheses
Analytic studies ……… hypotheses
generate
test
Define bias
Systematic deviation of results from the truth, or the processes leading to such deviation
Give examples of the following:
- selection bas
- information (observation) bias
Selection bias - sampling bias - responder bias - follow-up bias Information (observation) bias - recall bias/social acceptability bias - recording bias/interviewer bias
Define confounding
effects of additional variable that might be responsibly for an observed association
Confounder can:
- cause spurious association
- exaggerate association
- or mask association between exposure and disease
Define incidence
- the total number of new cases commending during a specified period in a defined population
Define prevelance
- the total number of individuals who have the diseases at a particular time
Prevalence = incidence x duration of disease
Explain what incidence rate is and how to calculate it
number of new cases of a specific disease arising within a population over a specified time period divided by the person-time accumulated
Explain what incidence risk is and how to calculate it
number of new cases of a specific diseases arising within a population over a specified time period divided by the number of persons at res at the beginning of the time period
Explain was point prevalence is and how to calculate it
number of persons with disease at some time point
divided by
total population at risk of disease at the same time point
Explain what period prevalence is and how to calculate it
number of persons with disease at any time during a specified period
divided by
total population sen over the period of time
What are the 8 criteria for assessing causality?
- biological plausibility
- time
- strength of association
- biological gradient or dose-response relationship
- consistency
- specificity
- coherence
- experiments
Criteria for Assessing Causality
1. biological plausibilty
does it make biological sense
Criteria for Assessing Causality
2. time
logically a cause must precede its potential effect
Criteria for Assessing Causality
3. strength of association
the stronger the association of an exposure with disease occurence then the harder to conceive of likely confounders which might explain the association
Criteria for Assessing Causality
4. biological gradient or dose-response relationship
causality as a plausible interpretation is strengthened if there is a strong dose-response
Criteria for Assessing Causality
5. Consistency
- consistent with other studies in different populations, places and times add weight to a cause-effect interpretation
Criteria for Assessing Causality
6. Specificity
if the supposed cause is associated with one disease only ,or the dissed is associated with one cause only, can add weight to causal interpretation
Criteria for Assessing Causality
7. coherence
should not contradict what is already known about the natural history and biology of the disease
Criteria for Assessing Causality
8. experiments
occasionally natural experiments offer themselves, such as tap-water fluoride levels and specific disease outcomes
How would you go about determining if the association is causal?
First consider confounding, bias and chance
Secondary use 8 criteria for causality as aid to inferring causation
- -
- to alert the medical community to what types of persons were most/least affect by disease
- to assist in the evidence-based planning of health and medical care facilities
- to provide suggestions concerning dissed aetiology for further investigation using analytic studies
What are case reports/series
- careful detailed report of individual patients or a series of patients
- suggest hypotheses
- no control groups
- can be useful even though no control e.g. thalidomide and congenital malformations
When would a cross-sectional study be undertaken?
Give 3 examples
- if in a particular geographical area we were to determine the point prevalence of a particular disease
Examples - determining need for specific health or social services
- development of hypotheses concerning risk factors for a disease
- determining trends in prevalence
Give three examples of random sampling methods
- simple random sampling
- cluster sampling
- stratified sampling
Give three examples of non-random sampling methods
- systematic sampling e.g. every 2nd patient
- snowball sampling
- street survey
Can a casual relationship be establish with a cross-sectional study
unclear of direction of relationship as only have a snapshot in time
What are the advantages of cross sectional studies
quick
inexpensive
What are the disadvantages of cross sectional studies?
- time sequence and causation
- cohort effects when interpreting relationships with age
- problems with interpretation of prevalence which is a mixture of incidence and survival relating to a disease
What are the four ways of analysing cross sectional studies?
- compare means (T test)
- compare proportions (Chi squared)
- correlation (Pearson)
- strength of association: prevalence ratio, odds ratio
Describe ecological studies
measure rates of death or disease in populations and the population rate of a risk factor
Groups of individuals as units of study
What are scatter plots and Pearson’s correlation coefficient?
Scatter plots = visually inspect the relationship between exposure and disease
Correlation =r
- numerically decreases the association between exposure and disease
- values from +1 to -1
What are the advantages of ecological studies?
quick
inexpensive
hypothesis generation
What are the disadvantages of ecological studies?
- subject to confounding
- prone to sampling bias
- prone to information bias
- the group of people described by disease data are often not the same people as those described by the exposure data
- the time relationship between the measurements for exposure and disease is often unclear
So we cannot assume from a relationship found amongst groups of individuals that the same relationship also holds at the individual level