Introduction to the module Flashcards
(28 cards)
What is Epidemiology?
The study of how often diseases occur in different populations and why
Data-driven and relies on a systematic and unbiased approach to the collection, analysis and interpretation of data
What do basic epidemiological methods tend to rely on?
Careful observation and use of valid comparison groups to assess whether what was observed, e.g. the number of cases of disease in a particular area during a particular time period or the frequency of an exposure among persons with disease, differs from what might be expected.
What is epidemiology often described as?
Basic science of public health
Quantitative discipline that relies on a working knowledge of probability, statistics and sound research methods
Method of causal reasoning based on developing and testing hypotheses to explain health-related behaviours, states and events.
What does epidemiology provide?
The foundation for directing practical and appropriate public health action based on this science and causal reasoning
Epidemiological information used to plan and evaluate strategies to prevent and manage disease
What is intuition?
Ability to understand something instinctively, without the need for conscious reasoning
Thinking you know something without really knowing how or why you know it
What are the components of intuition?
Fast
Unconscious
Low effort
Everyday decisions
Error prone
What are the components of rational thinking?
Slow
Conscious
High effort
Complex decisions
Reliable
What can intuition lead to?
Bias
What is confirmation bias?
The tendency to search for data that can confirm our beliefs, as opposed to looking for data that might challenge those beliefs
Selective thinking
Ignore or dont look for the relevance of what contradicts your beliefs
e.g. if you believe that disease outbreaks are more likely to occur in a certain region, you might take more notice of disease reports from that area but pay less attention to disease reports from other regions
When can researchers sometimes be guilty of confirmation bias?
By setting up experiments or framing their data in ways that will tend to confirm their hypotheses!
What is probability?
The likelihood of a random event happening
probability = number of events / number of possible outcomes
Knowing how to calculate the probability of a disease event or events happening can be invaluable when making decisions
How you calculate probability depends on the type of event you are interested in. What can these events be?
Independent
Conditional
Mutually exclusive
What is correlation?
In statistics, correlation or dependence is any statistical relationship between two random variables or bivariate data, whether or not they are causal
Correlation is a statistical measure that indicates the extent to which two or more variables fluctuate in relation to each other.
If you saw correlation between two variables, how would you decide if it is scientifically meaningful?
Does there actually appear to be a correlation?
How likely is it due to chance?
What is the possible causal mechanism(s)?
Does it make sense?
Are confounding variables a possibility?
Anything else?
What are the steps to seeing if correlation is meaningful?
Apparent causation –> Probable cause-effect
What is validity?
The degree to which the inference drawn from a study is warranted when account is taken of the study methods, the representatives of the study sample, and the nature of the population from which it is drawn
What is internal validity?
The extent to which systematic error is minimised during all stages of data collection
What is external validity?
The extent to which results of studies provide a correct basis for generalisation to other circumstances
What are the three threats to validity?
Bias
Confounding
Chance
What is bias?
Selection bias
Information bias
What is selection bias?
Error due to systematic differences in characteristics between participants and non-participants
What is information bias?
Systematic error from inaccurate measurement (classification) of subjects on study variables
What is confounding?
Distortion in the estimated effect of an exposure caused by a variable that is associated with both the outcome and the exposure of interest, but is not on the causal pathway
What is chance?
Because we can not study entire populations, some chance factor may affect our estimate of an effect
Can adjust using stats e.g. 95% probability that results is not due to chance - p=0.05
