General Methodological Concepts of Research Flashcards
Define Quantitative
Numbers used to represent data
Define Qualitative
Words used to represent data
What are the two branches of quantitative research?
Interventional, Observational
Define Interventional
Forced allocation to study groups
Define Observational
No forced allocation into study groups
Which study design is considered to be experimental?
Interventional
Which study design is considered to be natural?
Observational
This study design is useful for unethical study designs using forced interventions.
Observational
T/F: Most observational study designs are able to prove Causation
False; most observational studies are not able to prove Causation
What are the study designs of interventional studies?
Phases; 0-4
What are the study designs of observational studies?
- Cross-Sectional
- Case-Control
- Cohort
- Case Reports/Series; Ecological
List interventional phases in order of increasing evidence
Phase 0 –> Phase 4
List observational study designs in order of increasing evidence
- Case Reports/Series
- Ecological
- Cross-Sectional
- Case-Control
- Cohort
In the research evidence pyramid, name the top two studies
Systematic Reviews; Meta-Analyses
In the research evidence pyramid, name the second-tier studies
Interventional (exploratory) trials; Pragmatic (explanatory) trials
What increases moving up the research evidence pyramid?
Strength of evidence
What study is truly capable of showing causation?
Interventional (exploratory) trials
There are about 7 elements which study design is based on, list them
- Perspective of research question (hypothesis)
- Ability/desire of researcher to force group allocation (randomization)
- Ethics of methodology
- Efficiency and practicality
- Costs
- Validity of acquired information (internal validity)
- Applicability of acquired information to non-study patients (external validity, generalization)
What is the population in a human study?
All individuals making up a common group; from which a sample can be obtained if desired
What is the difference between “population” and “study population” in human studies?
A study population is a sample of the population, a sample to represent the whole population
What processes are used in drawing a sample from a population?
Random processes
Study population selection is based on…
- Research hypothesis/questions
- Population of interest
- Inclusion & exclusion selection criteria (iInterventional studies) and case & control group OR exposed & non-exposed group selection criteria (observational studies) impact external validity
Define Null Hypothesis
A research perspective which states there will be no (true) difference between the groups being compared
What is the null hypothesis asking of the data?
“To change our minds”
T/F: Null hypothesis is the most conservative and commonly utilized
True
What are the three statistical-perspectives a researcher can take?
- Superiority
- Noninferiority
- Equivalency
What does superiority compare to? What is its null?
- The placebo, asking if we are better
- Ho: I am not superior
What does non inferiority compare to? What is its null?
- The “gold standard,” asking if as effective but with another benefit (ie, less expensive, not taking Rx as often)
- Ho: I am worse
What is equivalency looking for? What is its null? What must the data do?
- Equality
- Ho: I am not equal
- Data must change our minds
What are the two types of error in inaccurately-accepting or rejecting null hypothesis?
Type I and Type II
What is a Type I error?
False positive
think: male, you’re pregnant
What is a Type II error?
False negative
think: pregnant female, you’re not pregnant
What are the kinds of sampling schemes?
- Probability samples
- Non-probability sampling schemes
What are the kinds of probability sampling schemes?
- Simple Random
- Systematic Random
- Stratified Simple Random
- Stratified Disproportionate Random
- Multi-Stage Random
- Cluster Multi-Stage Random
What is the probability sampling scheme?
Most common; every element in the population has a known (non-zero) probability of being included in sample
Define Simple Random Sampling
- Assign random numbers, then take randomly-selected numbers to get desired sample size
OR
- Assign random numbers, then sequentially-list numbers and take desired sample size from top (or bottom) of listed numbers
Define Systematic Random Sampling
Assign random numbers, randomly sort these random numbers, select highest (or lowest) number, systematically (by pre-determined sampling-interval) take every Nth number to get desired sample size
Define Stratified Simple Random Sampling
Stratify sampling frame by desired characteristics (ie gender), use Simple random sampling to select desired sample size
Define Stratified Disproportionate Random Sampling
- Disproportionately utilizes Stratified Simple Random Sampling when baseline population is not at the desired proportional percentages to the referent population
- Stratified sample ‘weighted’ to return sample population back to baseline population useful for over-sampling
Define Multi-Stage Random Sampling
Uses Simple random sampling at multiple-stages towards patient selection
“random on random on random on random”
Define Cluster Multi-Stage Random Sampling
Also “random on random” but ALL ‘elements’ clustered together (at any stage) are selected for inclusion
ie, ALL clinics or ALL households in a community
What is the non-probability sampling scheme?
Quasi-systematic or convenience samples
What is the Quasi-Systematic or Convenience sample?
Decide on what fraction of population is to be sampled and how they will be sampled
ex: all ppl last name beginning w/ M-Z, all ppl attending clinic e/ M/W/F for 6 mons, all ppl referred by selected-peers
What sort of bias is a concern in Quasi-Systematic or Convenience samples?
- Selection bias
- There is some known or unknown order to the sample generated by the selected scheme which may introduce bias
What are the two outcomes in human studies?
- Patient-oriented (vs. disease-oriented)
- Individual vs. combined
What is the most important and most useful outcome?
Patient-oriented