Study Unit 5: Research design Flashcards
what is internal validity:
extent to which the study confirms the existence of a cause-effect relationship
what are confounding variables
Confounding variables (variables that confound or confuse the interpretations) are also called nuisance variables or extraneous variables.
name some threats to internal validity
History refers to uncontrolled events that influence the outcome of the research. If an event that is not related to the study occurs during the study and influences the dependent variable, this event will confuse the causal relationship that the researcher assumes exists
There may be changes within the subjects themselves over time. The subjects being studied may undergo physical or psychological changes (this is known as maturation)
Instrumentation is a threat to the validity of the study if the measuring instrument deteriorates or improves over time.
Selection of subjects to be assigned to a specific group could bias the study if there are important, unsuspected differences between the subjects in each group.
Mortality refers to the fact that some subjects do not continue throughout the study, but drop out (not necessarily die!) before it is completed. The subjects who drop out may be different from those who complete the study and this could well influence the results.
Regression effect refers to a tendency of extreme scores to move towards the average upon retesting
testing effect implies that subjects may become familiar with the testing procedure or be more aware of certain issues after the pretest.
what is external validity:
extent to which results can be generalised to other populations or circumstances
what is Researcher expectancy
refers to the situation where expectations cause a researcher to behave in a manner that makes the expected event more likely to occur.
what are treatments
This deliberate action on the part of the researcher is called a treatment. Treatments are any intervention that modifies or changes the situation. Treatments could include counselling, showing a video, using specific teaching strategies,
what is a treatment condition
Treatment condition refers to whether a particular group receives the treatment or not, and what kind of treatment it receives.
what is the experimental group:
group that receives the treatment
what is the
what is the control group:
group that does not receive the treatment
what is a pretest
If the dependent variable is measured before the introduction of the treatment, this is called a pretest
what is a posttest
posttest is the measurement of the dependent variable after the treatment has been introduced
what is random assignment
: every subject has an equal chance of being assigned to any treatment condition or group
why should pre experimental designs be avoided
Pre-experimental designs may or may not involve manipulation of treatment conditions, but they do not include randomisation.
what are quasi experimental designs
Quasi-experimental designs resemble true experimental designs in that the researcher aims to establish cause-effect relationships
These designs are better than pre-experimental designs for identifying causal relationships;
quasi-experimental designs do not involve randomisation