Internal/External Validity
What are some threats to internal validity that randomization does not help with?
-interactive effects of testing -test reliability and validity -experimental mortality
What are the methods of control for external validity?
-randomization -physical and selective manipulation -statistical techniques
What are some threats to external validity?
-reaction and interactive effects of testing -interaction of selection bias and experimental treatment -reactive effects of experimental settings -multiple treatment interference
In what two ways is experimental research unique?
1) Only type of research that attempts to influence a particular variable 2) Best type of research for testing hypotheses about cause-and-effect relationships
What three things occur with random assignments?
1) it takes place before the experiment begins 2) process of assigning the groups takes place 3) groups should be equivalent
What are the 10 steps to experimental research?
1) state the research question/problem 2) specify the independent variable and levels 3) specify the dependent variables 4) determine the availability of measures of the dependent variable 5) identify the potential of intervening (extraneous) variables 6) state the research hypothesis 7) design the experiment 8) conduct the study as planned 9) analyze the data and interpret results 10) prepare the research report
What effect is characterized by previous scoring tainting future scoring ("brownie" points)?
Halo effect
What effect is characterized when control subjects trying harder because they are not in the experimental group?
avis effect
How can the research control for possible threats to internal validity?
by ensuring the all subject characteristics that might affect the study are controlled
What question is external validity asking?
can the finding be generalized beyond the subjects or settings studied in the experiment?
What is the outcome variable?
dependent
What effect is characterized when select groups are expected to do better?
expectancy effect
What type of threat to internal validity involves loss of participants from comparison groups due to nonrandom reason?
experimental mortality
What effect is characterized by subjects change due to receiving attention?
hawthrone effect
What type of threat to internal validity involves events occurring during the experiment that are not part of the treatment?
history
What are threats the threats to internal validity?
history, maturation, testing, instrumentation, selection bias, experimental mortality, interaction among factors
What is the treatment variable?
independent
What two variables are involved in experimental research?
independent and dependent variables
What type of threat to internal validity involves changes in testing instruments, raters, or interviewers including lack of agreement within and between observers?
instrumentation
What type of threat to internal validity involves factors that can operate together to influence experimental results?
interaction among factors
What type of threat to internal validity involves biological or psychological processes within participants that may change due to the passing of time?
maturation
What type of method of control for external validity involves the researcher physical controlling all aspects of the subject environment?
physical and selective manipulation
What process means that every individual who is participating in the experiment has an equal chance of being assigned to any of the experimental or control groups?
random assignment
What process means that every member of a population has an equal change of being selected to be a member of the sample?
random selection
What are tactics for controlling internal validity threats?
randomization, placebos, blind, and double-blind setups
What type of threat to internal validity involves identification of comparison groups in other than a random manner?
selection bias
ANCOVA is an example of what method of control for external validity?
statistical technique
What type of threat to internal validity involves the effects of one test upon subsequent administrations of the same test?
testing
What question is being asked by internal validity?
were the changes in the dependent variable the result of the independent variable or were they due to something else?