Ch. 11: Reasoning About the Design and Execution of Research Flashcards
what are the eight steps in the scientific method
- generate a testable question
- gather data and resources
- form a hypothesis
- collect new data
- analyze the data
- interpret the data and existing hypothesis
- publish
- verify results
what is a hypothesis
proposed explanation or answer to a testable question, often in the form of a if-then statement
what is accomplished during experimentation
variables of interest are manipulated and controlled OR subjects are observed in order to collect new data
what is the purpose of an if-then statement
it ensures that a hypothesis is testable
what does the FINER method apply to
evaluating a research question (not hypothesis)
what are the questions the FINER method asks
- is the necessary research FEASIBLE
- do others find this INTERESTING
- is the question NOVEL (new)
- would the study be ETHICAL
- is the question RELEVANT
what kind of research is basic science research
research conducted in a lab and not on people, allowing for the most control
what is a control/standard
condition that can be applied to multiple trials as near identical as possible –> method of verifying results
what are positive controls
controls that ensure a change in the dependent variable
what are negative controls
controls that ensure no change in the dependent variable
often used to test for placebo effect
what is the independent variable
the variable that is being manipulated in an experiment
goes on the x-axis
what is the dependent variable
the variable that is being measured in an experiment
goes on the y-axis
when is a relationship CAUSAL
when a known variable links an independent and dependent variable
- -> change in independent variable ALWAYS precedes a change in the dependent variable
- -> changes in dependent variables do not occur without experimental intervention
what is accuracy/validity
the ability of an instrument to measure a true value
“on target”
lack of = systematic error
what is precision/reliability
the ability of an instrument to read consistently and within a narrow range
“together”
lack of = random error
what is bias
systematic error
what will an unreliable tool introduce
random error
what is human subjects research
research conducted on human subjects with significantly less control and weaker established relationships
what is randomization
method used to control for difference (like age and gender) between groups in biomedical research
randomly (using a coin toss or die roll) establishes a control group from the entire research group
what is blinding
method to control for bias of perception against a group or variable
subjects or investigators do not have information about which group the subject is in
what is a single blind study
either the subject or the assessor does not know what group the subject is in
what is a double blind study
the subject, the assessor AND the investigator do not know what group the subject is in
what are confounding variable
third-party variables outside of the independent and dependent variables being evaluated which can confuse correlation with causation
what are binary variables
yes vs no, better vs worse
what are continuous variables
amount of weight lost, percent improvement
what are categorical variables
state of residence, socioeconomic status
what are observational studies
research that does not carry out an experiment, but analyzes available data
what are cohort studies
subjects are sorted into groups based on differences of interests and assessed at different intervals to determine rate of outcomes of interest
what are cross-sectional studies
patients are categorized into groups at a single point in time
what are case-control studies
identify number of patients with outcome and work backwards to determine if their was an incident of exposure
what does Hill’s criteria evaluate
how likely relationships between observed criteria are to be causal
what are the aspects of hill’s criteria
temporality - independent before dependent strength dose - response consistence plausibility consideration of alternatives experiment specificity coherence
when does selection bias occur
when subjects selected for an experiment are not representative of the target population
when does detection bias occur
when educated professionals use their knowledge inconstiently
when does observation bias occur
when the behavior of subjects is altered simply because they are aware they are being observed
in what phase does all bias occur
in the experimentation phase
in what phase does confounding occur
in the data analysis phase
what is the only necessary criterion for Hill’s criteria
TEMPORALITY exposure (independent variable) must occur before the outcome (dependent variable)
what are the core ethical tenants
- beneficence
- nonmalficence
- autonomy
- justice
