Lecture 2 Flashcards
Research design must confer _________ and external validity
internal
Define internal validity
Define external validity
1) Internal validity: reflects the extent to which the clinical outcome of interest (dependent variable) in a study is caused by the treatment (independent variable)
Dependent variable = clinical outcome
Independent variable = treatment
2) External validity: the extent to which the results of a study can be generalized to other settings
Basic classifications of research design include what?
1) Purpose
2) Time orientation
3) Investigator orientation
4) RCT or Observational studies
What are the 2 types of purpose (basic classifications of research design)?
1) Descriptive studies
Generating a hypothesis
Answers “adverbs” related to observations
2) Analytical studies
Testing a hypothesis
More expensive
What are the 2 types of time orientation?
1) Prospective
All RCTs are prospective
More expensive
2) Retrospective
What are the 2 types of investigator orientation?
1) Intervention studies
Researcher controls treatment (i.e., treatment and provisions of treatment)
Randomized
Can determine cause and effect
2) Quasi-experimental
Researcher controls treatment (i.e., treatment and provisions of treatment)
Not randomized
Can show associations
Differentiate between RCT and observational studies
1) RCT: random
2) Observational studies include:
Cohort
Case-control
Cross-sectional
Case Series
Case reports
Randomized controlled trials (RCTs) occur in a ________ setting
controlled
What are the 2 essential elements of RCTs? (randomized control trials)
1) Randomization of participants into two groups
a) Interventional (experimental or treatment group)
b) Control
2) Prospective
RCTs: Because of randomization, all observed as well as unobserved baseline characteristics are distributed evenly among the experimental and control groups, which thereby alleviates the systematic differences among participants in influencing study results.
Thus, _____________ increases internal validity of RCTs.
randomization
1) The elements of RCTs that increase the internal validity of study results also contribute toward restricting their ___________________.
2) Why?
1) external validity (generalizability)
2) Since RCTs are conducted in tightly controlled clinical settings, the results may not be generalizable to routine (real-world) settings.
1) What setting do observational studies occur in?
2) What are the types of observational studies?
1) Natural setting
2) Cohort
Case-control
Cross-sectional
Case Series
Case reports
Define cohort
two groups, the exposed and the unexposed, are followed (prospectively or retrospectively) over a period of time until the development of outcome of interest
Cohort: intervention, looking for outcome
Give an example
Highest level of observational evidence
Prospective or retrospective
Example: Smokers vs. non-smokers; Who develops squamous cell carcinoma?
Define case-control and give an example
comparison of exposure status among individuals with the disease or outcome of interest (cases) and those without the disease or outcome (controls)
Example: Patients with squamous cell carcinoma; Who smoked?
Define cross-sectional observational studies and give an example
– prevalence studies; exposure and outcome of interest are measured at the same point in time
Example: How many people were infected with COVID-19 and died during 2020?
Define case series observational studies and give an example
collection of case reports
Credited with the discovery of AIDS and identification of the relationship between thalidomide and birth defects
Define case report. What is unique about this?
single patient with novel predicament
Lowest level of observational evidence
Methodology includes what?
1) Quantitative
2) Qualitative
3) Mixed methods
Define quantitative and positivism (they go together)
Numerical data
Positivism: all information derived from sensory experience should be empirical evidence
Define qualitative and constructivism (they go together)
Qualitative
Textual data
Constructivism: phenomenon of interest is socially constructed and therefore subject to multiple realities or interpretations
Define mixed methods
quantitative + qualitative data
Differentiate between primary and secondary quantitative methods. Give examples of each
1) Primary methods
Data specific for research question
Examples – surveys & observations
More expensive
2) Secondary methods
Data collected for different purpose but used for research question
Examples – medical charts & claims
Quantitative methodology:
1) Define reliability
2) Define Test-retest reliability
3) Define Inter-rater reliability
1) Consistency and reproducibility of results
2) Test-retest reliability: instrument’s consistency
3) Inter-rater reliability: researcher’s consistency
Quantitative: Give examples of validity
(This is an FYI slide)
-Validity
-Face validity
-Content validity: Measurement contains required domains or areas to accurately measure a concept
-Construct validity
-Criterion validity: Ability of an instrument to correlate well with a criterion or standard
-Convergent validity: Extent to which similar constructs correlate
-Discriminant validity: Extent to which an instrument purporting to measure a construct is able to differentiate it from a theoretically unrelated construct
Qualitative: Give the FYI slide for this
Grounded theory: Aims to build a theory about social processes from real-world observations
Ethnography: Aims to gain an in-depth understanding of the culture and process of a particular context by immersing themselves in the participants’ environment
Phenomenology: Aims to better understand/describe a particular event, activity, or phenomenon
Qualitative; define:
1) Purposive sampling
2) Quota sampling
3) Convenience sampling
1) Purposive sampling: Participant selection based on research question
2) Quota sampling: Participants are selected from mutually exclusive subgroups in such a way that the final assembled sample has the same proportions of individuals as the entire population with respect to one or more characteristics, traits, or phenomena of interest
3) Convenience sampling: Based on the researcher’s convenience in recruiting them
Qualitative methodology; define:
1) Snowball sampling
2) Theory-based sampling
1) Snowball sampling: Existing study participants nominate, refer, or recruit future participants in the study from among their acquaintances
-Good for hard-to-reach populations (e.g., sex workers, shoplifters, illicit drug users)
2) Theory-based sampling: Participants are sampled in order to develop an emerging theory or concept based on real life events
Give types of qualitative sampling
1) Purposive sampling
Participant selection based on research question
2) Quota sampling
Participants are selected from mutually exclusive subgroups in such a way that the final assembled sample has the same proportions of individuals as the entire population with respect to one or more characteristics, traits, or phenomena of interest
3) Convenience sampling
Based on the researcher’s convenience in recruiting them
4) Snowball sampling
Existing study participants nominate, refer, or recruit future participants in the study from among their acquaintances
Good for hard-to-reach populations (e.g., sex workers, shoplifters, illicit drug users)
5) Theory-based sampling
Participants are sampled in order to develop an emerging theory or concept based on real life events
Give 3 parts of mixed methods study design
Exploratory sequential
Study starts with a qualitative data collection and analysis phase, which informs the subsequent quantitative phase
Explanatory sequential
Initial quantitative phase of data collection and analysis, followed by the qualitative phase
Convergent design
Qualitative and quantitative data collection and analysis phases occur at similar time points
