Research Designs Flashcards
What types of Research Design exist?
Descriptive (PO)
Analytical (PICO)
What are the different sub-categories of Descriptive Research Design ?
Survey/case reports
Qualitative
What are the different sub-categories of Analytical Research Design ?
Observational analytic
Experimental
Describe the Descriptive Research Design
- non analytical, not to quantify relationship, no hypothesis
- without an “intervention” (retrospective)
- N can be small but # of variables can be large
- descriptive information to support or invalidate theories
- reveal important findings = new hypothesis
- examples : case reports, case series, single case design, qualitative studies and surveys, cross sectional studies
Describe the Analytical Research Design, observational analytic branch
- quantify relationship between two factors : Effect of intervention/exposure on outcome
- test hypothesis
- measuring intervention, exposure (case control, cohort, cross sectional studies)
Describe the Analytical Research Design, experimental branch
- Researchers manipulate intervention/exposure
- Quasi experimental: test causality with sub-optimal variable control (before/after design)
- True experimental: test causality with optimal variable control (randomized control trial)
Description of Case-Study/ Case Series
- Descriptive information, exposure, outcome
- No control group
- Explore new treatment/topic on which limited knowledge exists
- Elaborate new hypothesis
- Often qualitative research
Definition of Case-Study/Case series
A participant with a condition of interest will provide information about clinical outcome.
Description of Case Control Design
- Retrospective
- Cases (with a specific characteristic or situation vs. controls allowing a comparison between differences
- No active control
Definition of Case Control Design
A retrospective measurement consisting into a comparison between participants with and without outcomes of interest assessed regarding previous exposure to intervention or causal factor.
What are the advantages of Case Control Design?
- Quick and cheap
- Feasible on very rare disorders or those with long lag between exposure and outcome
- Fewer subjects needed than cross sectional studies
What are the Disadvantages of Case Control Design?
- Reliance on recall or records to determine exposure status
- Confounders
- Selection of control groups is difficult
- Potential bias: recall, selection
Description of Cohort Design
-prospective (can also be retrospective)
-one group is not exposed to the situation of interest
VS.
-one group is exposed to the situation of interest
- the allocation of groups is not under control
-there are no causal relationships between the characteristics of groups
Definition of Cohort Design
Prospective analysis of the outcome of a study taking place between participants exposed and not exposed to the intervention.
What are the advantages of Cohort Design?
- Ethically safe
- Subjects can be matched
- Can establish timing and directionality of events
- Eligibility criteria and outcome assessments can be standardized
- Administratively easier and cheaper than RCT
What are the disadvantage of Cohort Design?
- Controls may be difficult to identify
- Exposure may be linked to a hidden confounder
- Blinding is difficult
- Randomisation not present
- For rare disease, large sample sizes or long follow up is necessary
What are the characteristics of Cross Sectional Design?
- At 1 point in time
- Which factors influence particular outcome
- Exploratory
- Relatively inexpensive, easy
- No causality
Definition of Cross Sectional Design
Measurements on outcomes and factors made at one point in time on a group of participants.
What are the Advantages of Cross Sectional Design?
- Cheap and simple
- Ethically safe
What are the disadvantages of Cross Sectional Design ?
- Establishes association at most, not causality
- Recall bias susceptibility
- Confounders may be unequally distributed
- Group sizes may be unequal
What are the characteristics of Before/After Design ?
- Prospective
- Assess and compare outcomes before and after intervention
- No control group, subjects serve as their own control
Definition of Before/After Design
Participants -> Assessment -> Intervention -> Outcome studied in a prospective time
What are the characteristics of Single Case design ?
-Prospective
-Cfr. Before/after design
-no control group : individual subject serves as his own control
-participants studied during multiple phases :
Minimum 2 designated by letters by convention
Baseline (A) and treatment intervention (B)
Definition of Single Case Design
Individual client -> Baseline evaluation (A) -> Intervention (B) -> Evaluation (A) -> Intervention (B) studied prospectively
What are the characteristics of Randomized controlled trial (RCT) ?
- Experimental study : “does things to people in order to observe the effects”
- Random allocation -> internal validity
- 1 experimental group vs 1 control group (controlled manipulation of at least one independent variable)
- test effectiveness of intervention (causality)
- highly controlled
Definition of RCT
Participants -> Stratification -> Randomization -> Experimental group/Control group -> Outcome
What are the advantages of RCT ?
- Unbiased distribution of Confounders
- blinding more likely
- randomization facilitates statistical analysis
What are the disadvantages of RCT ?
- Expensive time and money
- Volunteer bias
- Ethically problematic at times
Compare RCT and SCD
-Major differences :
Means by which the experimental control is achieved
Number of participants in the study
Both are scientifically credible when properly applied.
Characteristics of Experimental Design
-Random Assignment
-Researcher controlled manipulation of independent variable
-Researcher control of experimental situation and setting, including control / comparison group
-control of variance :
Clearly spelled out sampling criteria
Precisely defined independent variable
Carefully measured dependent variable
What are the types of variables ?
- independent variable
- dependent variable
- extraneous variable
What are the validity criteria of experimental trial ?
- comparability of the groups at the beginning
- large numbers
- blinding of assessors, raters and statisticians
- no confounding factors
- reliability of the measurements
What are the potential causes of bias in quantitative research ?
- Researchers
- Components of the environment the settings
- Individual participant or sample
- How groups were formed
- Measurement tools
- Data collection process
- Data and duration of the study
- Statistical tests and analysis interpretation
Why is rigor important ?
- because the validity of the study depends on it
- striving for excellence in research and adherence to detail
- precise measurement tools, representative sample and tightly controlled study design
- logical reasoning is essential
- precision, accuracy, detail and order required
Definition of Internal Validity
Extend to which the independent variable caused the outcome of the study. Are you actually measuring what you were supposed to measure ? Avoiding confounding factors.
What is external validity ?
The possibility to generalize results.
Define reliability
- the accuracy and repeatability of the measured outcome, divided between inter rater and intra rater
Reliability vs validity
Reliability is about the consistency of a measure and validity is about the consistency of the measure
