Kin 232 Module 5 Flashcards
Quasi experimental design
Involves manipulation of an independent variable but does not contain a control group and/or randomization
Used under conditions where true experimental designs are not possible or too expensive
Cannot be used to infer causation as conclusively as true experimental trials
Poorer internal validity
Quasi experimental most useful if
Control is exerted where possible
Masking procedures are used to solidify design
When preexisting groups exists
If there is no randomization in quasi experimental
Use pretest to ensure some level of group equivalent
When there is only a control group: there are two independent variables: time and supplementation
If there is no control group or randomization in quasi experimental
Don’t know what could have caused outcome (poor internal validity)
Used when its ethical
When time frame is really short (pilot study)
Independent variable will now be time (there are 2 levels)
The intervention may be initially be considered a indpendent variable but now its not because theres only one level of it, even though it is a “treatment”
Weakness to quasi experimental
Groups may not be equivalent , however there is a pretest
Repeated measures in quasi experimental
Missing randomization but there still can be many observation periods
Includes prepost , interim assessments, follow up assessments
What threats to internal validity does incorporation of a control group help rule out
History, testing, Instrumentation
Better internal validity
Time series Design
type of Observation design
Multiple measures to document patterns or trends in behavior over time
Purpose is to determine trend in outcome over time
To make it a quasi experimental design;
Manipulate variables, control group
Interrupted Time Series Design
Quasi experimental
Interrupted time series : time series is interrupted by an intervention within the series of measurements
Used for population level interventions (including policy changes)
Randomization not generally possible thus quasi experimental
May or may not have control group
Common in federation level (implication of programs in schools etc)
Repeated measures before and after intervention
A control group can be incorporated
Advantages to Interrupted Time Series Design
Time series: multiple measurements enhance confidence that there was a real change versus normal variation / repeated text effects
Disadvantages to Interrupted Time series Design
Lack of randomization and/or control still reduced internal validity relative to experimental design
May be a confounding event that occurred at same time as intervention
Exploratory stage in clinical trials phase
Preclinical research (cell culture, animals)
Non humans in laboratory conditions
Screens many potential compounds
If promising, request to to human trials
Pre approval stage in clinical trials phases
Phase 0 trial
Phase I trial
Phase II trial
Phase III trial
Post approval stage in clinical trials phases
Phase IV Trial
Alternate populations
Risk factors, benefits, optimal use
For treatments for cancer
Phase 0 trial
First trial in humans
Very small number of healthy people
Very small dose to ensure safety
