Epidemiology Flashcards
SELECTING EVIDENCE FOR COMPARATIVE
EFFECTIVENESS REVIEWS - evidence pyramid
Filtered resources
- systematic reviews
- critically-appraised topics
- critically-appraised individual articles
Unfiltered resources
- randomized controlled trials
- cohort studies
- case-controlled studies, case -series, and case reports
Background information, expert opinion
Levels of evidence pyramid
systematic reviews are at the top of the pyramid, meaning they are both the highest level of evidence and the least common. As you go down the pyramid, the amount of evidence will increase as the quality of the evidence decreases
ATTRIBUTES OF QUALITATIVE RESEARCH
Open, not closed, questions
Exploratory not explanatory
Focus on meaning
Grounded theory
Qualitative vs. Quantitative
Quantitative - methods: Experiment, survey - question: How many Xs? - reasoning: Deductive - sampling method: statistical - strength: Reliability
Qualitative - methods: Observation, interview - question: What is X? - reasoning: Inductive - sampling method: Theoretical - strength: Validity
RESEARCH PARADIGMS
Quantitative
Qualitative
Natural sciences
Social sciences
“objectivity” “subjectivity”
Impersonal
Human actions
Approach from the outside
Personal involvement of researcher
Medium/large scale Small scale
Explaining Understanding
Generalizing from specific
Interpreting the specific
Society
Individual
FALSIFICATION PRINCIPLE
Any scientific hypothesis and resultant experimental design must be inherently falsifiable.
It is easy to obtain confirmations, or verifications, for nearly
every theory — if we look for confirmations. (e.g. “all swans are white”, “melatonin is a safe drug”)
A theory which is not refutable by any conceivable event is
non‐scientific.
Irrefutability is not
a virtue of a theory but a vice.
Karl Popper Conjectures and Refutations (1963).
THE RESEARCH QUESTION
The research hypothesis is often presented in the negative, e.g. “The addition of metformin to maximal dose
sulphonylurea therapy will not improve the control of Type 2 diabetes”.
This is known as
a null hypothesis.
Scientists do this to say ‘let’s assume there’s no difference; now let’s try to disprove that theory’
This approach (setting up falsifiable hypotheses which you
then proceed to test) is the essence of the scientific method.
BRADFORD-HILL’S CHECKLIST (1965)
FOR JUDGING CAUSALITY
- Temporality
- Strength
- Specificity
- Consistency
- Biological Plausibility
RELATIVE RISK (OF DYING ON THE TITANIC, 1912)
The relative risk (sometimes called the risk ratio) compares the
probability of death in each group.
For females, the probability of death is 33% (154/462=0.33).
For males, the probability of death is 83% (709/851=0.83).
The relative risk of death is 2.5 (0.83/0.33). There is a 2.5 greater probability of death for males than for females.
ODDS RATIO
The odds ratio compares the relative odds of death in each
group.
For females, the odds were 2 to 1 against dying
(154/308=0.5).
For males, the odds were almost 5 to 1 in favor of death
(709/142=5).
The odds ratio for dead or alive is 10 (higher than RR)
Odds Ratio adv/ disadv
Null value is 1.0
Difficult to interpret
Available in all research designs
Covariate adjustment is easy
Invariant to labeling of events and nonevents
Relative risk adv/ disadv
Null value is 1.0
Easy to interpret
Not available in case-control designs
Covariate adjustment is hard
Labeling of events and nonevents creates ambiguity.
define covariate
In statistics, a covariate is a variable that is possibly predictive of the outcome under study. A covariate may be of direct interest or it may be a confounding or interacting variable.
