Study designs Flashcards
What are the 3 types of study designs?
- RCT
- Cohort study
- Case-control study
What is a RCT?
= randomised control trial
Participants randomly allocated to intervention or control group (e.g. standard treatment or placebo)
Practical or ethical problems may limit use
What is a cohort study?
- Observational
- prospective.
Two (or more) cohorts selected according to their exposure to a particular agent (e.g. medicine, toxin) and followed up to see how many develop a disease or other outcome.
The usual outcome measure is the relative risk.
Examples include Framingham Heart Study
What is a case-control study?
- Observational
- retrospective
Patients with a particular condition (cases) are identified and matched with controls.
Data is then collected on past exposure to a possible causal agent for the condition.
The usual outcome measure is the odds ratio.
Inexpensive, produce quick results
Useful for studying rare conditions
Prone to confounding
What is confounding in statistics?
a variable which correlates with other variables within a study leading to spurious results
case-control studies are vulnerable to confounders
How can CONFOUNDING be controlled in the design stage of an experiment?
Randomisation
aims to produce an even amount of potential risk factors in both populations (cases and controls)
How can CONFOUNDING be controlled in the analysis stage of an experiment?
Stratification
Adjustment or normalisation for that confounding variable to remove its effect in the study outcome
What are the 3 types of association?
DIRECT
a true association not linked by a third (confounding) variable
SPURIOUS
an association that has arisen by chance and is not real
INDIRECT
the association is due to the presence of another factor (a confounding variable)
What criteria are used to establish whether an association is causal?
Bradford-Hill criteria
What are the main aspects of the BRADFORD-HILL criteria used to establish causation in a study?
STRENGTH
The stronger the association the more likely it is to be truly causal.
TEMPORALITY
Does the exposure precede the outcome?
SPECIFICTY
Is the suspected cause associated with a specific outcome/ disease?
COHERENCE
Does the association fit with other biological knowledge?
CONSISTENCY
Is the same association found in many studies?
What is bias?
the situation in a trial where one outcome is systematically favoured
What is SELECTION BIAS?
Error in assigning individuals to groups leading to differences which may influence the outcome
What are the sub-types of selection bias?
SAMPLING BIAS
subjects are not representative of the population
VOLUNTEER BIAS
One risk factor or study aspect may make certain individuals more or less likely to volunteer for a study. This can lead to further sampling bias
NON-RESPONDER BIAS
similar to volunteer bias, but in the opposite effect. Those who do not respond to a survey (for e.g.) may disproportionately fall into one of the categories being measure over the other
What is prevalence/incidence bias?
= Neyman bias
occurs when a study is investigating a condition that is characterised by early fatalities or silent cases.
It results from missed cases being omitted from calculations
What is admission bias?
= Berkson’s bias
cases and controls in a hospital case control study are systematically different from one another
This is because the combination of exposure to risk and occurrence of disease increases the likelihood of being admitted to the hospital
What is recall bias?
Difference in the accuracy of the recollections retrieved by study participants
possibly due to whether they have disorder or not
particularly an issue in case-control studies
What is the Hawthorne effect?
Describes a group changing it’s behaviour due to the knowledge that it is being studied
What is procedure bias?
Occurs when subjects in different groups receive different treatment
What is lead-time bias?
Occurs when two tests for a disease are compared, the new test diagnoses the disease earlier, but there is no effect on the outcome of the disease
What is a placebo?
inert substance that has no inherent pharmacological activity.
It looks, smells and tastes like the active drug with which it is compared.
A placebo need not always be pharmacological. It could be procedural, for example, sham electroconvulsive therapy (ECT), where the patient is anaesthetised but not given ECT
What is an active placebo?
drug which has its own inherent effects but none for the condition that it is being given.
This does not mean that it will lack any ACTIVE effects
e.g. using atropine for a study into antidepressants
What is a nocebo?
a placebo that produces prominent side effects
In which types of studies, are placebo effects seen to be more powerful?
Treatments that are perceived as being more powerful tend to have a stronger placebo effect than those that are perceived to be less so
e.g. injected placebos have a greater effect than oral placebos
What does ‘placebo sag’ mean?
a situation where the placebo effect is diminished (attenuated) with repeated use
In what kind of illness is the placebo effect greater?
in mild illness
What is the duration of the placebo response?
usually quite short lived
What does ‘regression to the mean’ refer to?
The observation that symptoms which are extreme on first measurement are likely to have improved on subsequent measurements
i.e. a variable is extreme on its first measurement, it will tend to be closer to the average on its second measurement.
What does SENSITIVITY mean in stats?
Proportion of patients with the condition who have a POSITIVE test result
What does SPECIFICITY mean in stats?
Proportion of patients without the condition who have a NEGATIVE test result
What is the positive predictive value?
The chance that the patient has the condition if the diagnostic test is positive
What is the negative predictive value?
The chance that the patient does not have the condition if the diagnostic test is negative
What is the consideration for predictive values?
They are prevalence dependent
What is PRECISION?
Quantifies a tests ability to produce the same measurements with repeated tests
What is a type 1 error?
the null hypothesis is rejected when it is true
What is a type 2 error?
the null hypothesis is accepted when it is false
What is defined as the POWER of a study?
probability of (correctly) rejecting the null hypothesis when it is false
- power = 1 - the probability of a type II error
- power can be increased by increasing the sample size
What is the null hypothesis?
states that two treatments are equally effective
A significance test uses the sample data to assess how likely the null hypothesis is to be correct
Which are the stable characteristics for a disease or study?
- Precision
- sensitivity
- accuracy
- specificity
Why is the positive predictive value dependent on disease prevalence?
The positive predictive value is low in conditions whereby the prevalence is low
This is due to the fact that as the prevalence falls, the number of true positives falls also.
