Week 9 - Experimental Designs/Quasi-Experimental Designs Flashcards
assigned to independent group
between-subjects design
subjects act as their own controls
within-subjects design
a way of describing an experimental design that is based on the number of factors
factorial design
name 3 types of experimental designs.
- btwn-subjects design
- within-subjects design
- factorial design
does not include either random assignment or a control group
quasi-experimental design
did the experimental treatment make the difference in this specific instance rather than extraneous variables
internal validity
name 7 threats to internal validity
- history
- maturation
- testing
- instrumentation
- selection bias
- experimental mortality
- interaction among factors
events occurring during the experiment that are not part of the treatment
history
biological or psychological processes within participants that may change due to the passing of time ex: aging, fatigue, hunger
maturation
the effects of one test upon subsequent administrations of the same test
testing
changes in testing instruments, raters, or interviewers including lack of agreement within and btwn observers
instrumentation
identification of comparison groups in other than a random manner
selection bias
loss of participants from comparison groups due to nonrandom reasons
experimental mortality
factors can operate together to influence experimental results
interaction among factors
- generalizability of results - to what populations, settings, or treatment variables can the results be generalized
- concerned with real-world applications
external validity
how is external validity controlled?
by selecting subjects, treatments, experimental situations, and tests to be representative of some larger population
what is the key to controlling most threats to external validity?
random selection
name 2 types of external validity.
- population validity
- ecological validity
refers to the extent to which the results can be generalized from the experimental sample to a defined population.
population validity
refers to the extent to which the results of an experiment can be generalized from the set of environmental conditions in the experiment to other environmental conditions
ecological validity
name 4 threats to external validity.
- interaction effects of testing
- selection bias
- reactive effects of experimental setting
- multiple-treatment interference
the fact that the pretest may make the participants more aware of or sensitive to the upcoming treatment
interaction effects of testing
when participants are selected in a manner so they are not representative of any particular population.
selection bias
the fact that treatments in constrained laboratory settings may not be effective in less constrained, real-world settings
reactive effects of experimental setting
when participants receive more than one treatment, the effects of previous treatments may influence subsequent ones
multiple-treatment interference
name 4 tools to control validity jeopardizing factors.
- pre-test
- control group
- randomization
- additional groups
what is the scientific standard for investigating cause and effect relationships?
pretest-posttest control group design
describe pretest-posttest control group design.
- 2 or more independent groups
- 1 independent variable
- 1 or more dependent variables
- random assignment
- also known as a parallel groups study
Describe posttest-only control group design studies.
- similar to pretest-posttest control group design
- except NO PRETEST is administered to either group
- used when pretest is impractical, contraindicated, or potentially reactive
Describe factorial designs for independent groups.
- incorporates two or more independent variables
- subjects randomly assigned to various combinations of the levels of the variables
- larger samples are needed
how are factorial designs described?
- according to the number of independent variables ex: two-way or two factor design
- also described by the number of levels within each factor
ex: a 3x3 design has 2 independent variables each with 3 levels
used when concerned that an extraneous factor might influence the between groups difference
randomized block design
used during random assignment to ensure that participants are similar across groups on this attribute
blocking variable
designed to control or “remove” the effect of nuisance factors
randomized block design
- subjects used as their own control
- also called within-subjects design
repeated measures designs
name 3 effects of repeated measures.
- practice effects
- carryover effects
- order effects
what is used as a possible solution of order, practice, and carryover effects?
Latin Square
- participants are randomized to a treatment sequence - either intervention followed by control or control followed by intervention
- used to control for order effects
- should only be used when condition is stable
- considerations for washout period
crossover designs
-used in studies with more than one independent variable
two-way design with two repeated measures
- two independent variables
- one repeated across all subjects
- the other randomized to independent groups
mixed design
- allows for continuous analysis of data
- compares success of intervention for successive pairs of subjects
- stopped as soon as the evidence is strong enough to detect a difference - may result in a reduction of subjects needed
- an alternative approach to the RCT
- specially constructed charts for visual analysis of outcomes
sequential clinical trials
what do quasi-experimental designs lack?
- random assignment
- comparison group
- or both
quasi-experimental designs are more likely than experimental designs to have threats to what?
internal validity
-time is the independent variable
time series designs
name 3 types of time series designs.
- one-group pretest-posttest design
- repeated measures design
- interrupted time series design
- all subjects receive the same treatment
- no comparison group, which limits internal and external validity
- independent variable is time
one-group pretest-posttest design
- multiple measures of the dependent variable are taken
- all subjects receive the same treatment
- no comparison group, which limits internal and external validity
- IV is time
repeated measures design
- multiple measures of the dependent variable are taken
- interrupted by one or more treatment occasions
- all subjects receive the same treatment
- no comparison group, limits internal and external validity
- IV is time
interrupted time series design (ITS)
-use of existing groups or where groups are self-selected
nonequivalent group designs
name 3 types of nonequivalent group designs.
- nonequivalent pretest-posttest control group design
- historical controls
- nonequivalent posttest-only control group design
- pretest-posttest design
- no random assignment
- intact groups
- subject preferences
- threats to validity include interaction of selection with history and maturation
nonequivalent pretest-posttest control group design
- compares treatments by using a historical control group who had received a different treatment during an earlier time period.
- threats due to confounding bc of imbalances in characteristics of the groups
historical controls
- uses existing groups instead of random assignment
- use for exploratory purposes NOT explanatory
- threats due to confounding, selection biases, and attrition
nonequivalent posttest-only control group design
nonequivalent posttest-only control group design is used for which types of purposes?
exploratory purposes NOT explanatory
more people drop out of which type of group?
control groups
must have ___ validity to have ___ validity.
internal, external
controlling threats to validity involves developing what?
an experimental design
a study is designed to compare elbow extensor strength of a single group of subjects with the shoulder positioned in a number of different positions. what type of design does this represent?
repeated measures design
a study is designed to determine the effect of aspirin and stretching on low back pain. Comparisons are made between groups taking/not taking the medication, and three types of stretching. In this study, medication and stretching are two independent variables. Subjects are randomly assigned to one of six groups. This is an example of what?
factorial design
Persons with hip osteoarthritis are randomly assigned in a multi-group randomized trial to either an aquatic exercise group, a cycling exercise group, a strength training group or to a control group to assess the effect of the training condition on pain. Based on this description, this study has how many independent variables?
3
