Statistics Flashcards
How does RANZCOG classify their levels of evidence?
From level 1-5
List the levels of evidence and what they mean in RANZCOG?
I - systematic review of RCTs
II - High quality RCT
III - Observational case control or cohort studies
IV - case report or case series (non analytical)
V - expert opinion
Give 3 examples of descriptive study types?
Correlational
Cross sectional
Case reports and case series
Give two examples of analytical observational studies
case controlled studies
cohort studies
give two examples of analytical interventional study types
Randomised controlled trials
clinical controlled trials
Give an example of a secondary study
Systematic review
Describe case control studies
Cases are selected on basis of outcome
carefully matched to control group who do not experience the outcome
examine exposure retrospectively
Describe cohort studies
Experimental group selected on basis of exposure
carefully matched to control group who are not exposed
Examine outcome status prospectively
In what scenario are case control studies good? list another benefit
Good for rare outcomes and common exposures
Relatively fast and cheap
In what scenario are cohort studies good? list another benefit
good for rare exposures and common outcomes
most rigorous of epidemiological studies
Describe a case report
a case is a detailed report on the profile of a single patient
rare events are usually reported in case reports
Describe what a case series is
Case series is a report on a series of patients with an outcome of interest
Give 3 disadvantages of descriptive studies
highly susceptible to bias
suggests association not causation
does not establish temporal relationship between cause and effect
may confuse characteristics of a group with characteristics of an individual
List 3 types of bias that affect case control studies
recall bias
selection bias
measurement error
describe detection bias and list a way it can be mitigated
where measurements are taken differently between treatment groups
mitigated by blinding
describe selection bias and a method to mitigate this form of bias
where subject allocation results in treatment groups that are systematically different, apart from in the intervention being studied.
Can be mitigated by randomisation
Describe observer bias and how to mitigate this
where the data collector is able to be subjective about the outcome
blinding, hard outcomes (measurable)
describe publication bias and how this can be mitigated
when negative studies are less likely to be published than positive ones
clinical trial registries
describe recall bias and how this can be mitigated
altered reporting of symptoms by patients depending on which group they have been allocated to
blinding
describe response bias and how to mitigate
when patients who enrolled for a trial are not representative of a population making the results not generalisable
Random sampling
Describe the Hawthorne effect
When the process of doing the study improves the outcome
use of control group + masking the study intent from patients/participants and observers
