Ch. 18 Experimental and Quasi-Experimental Research
The A-B-A-B designation refers to which type of research design?
Single subject
A researcher finds that the control group performs above its usual performance when compared with the experimental group. The effect is named the
Avis Effect
Multiple-treatment interference and the interaction of selection bias and experimental treatment are threats to
External validity
Individuals performing well merely because they are being observed (and not necessarily because of any effect of treatment) are considered to be under the influence of the
Hawthrone effect
Discuss the relationship between internal validity and external validity
Internal validity involves controlling all variables so that the researcher can eliminate all rival hypotheses as explanations for the outcomes observed. In controlling and constraining the research setting to gain interval validity, the researcher places the generalization (external validity) of the findings in jeopardy
In experimental design, when comparisons are made of groups that have been selected on the basis of their extreme scores, the posttest means the groups tend to move toward the mean of the entire population from which the extreme groups were selected. This threat to internal validity is called
Statistical Regression
A study is designed to determine whether the addition of programmed instruction will produce greater achievement scores than the traditional lecture-discussion method. Participants are randomly assigned to two (2) instructional groups. Both groups are tested at the end of the experimental period. What statistical test is indicated?
T test
A pretest of knowledge about microcomputers is given to a group of students 5 minutes prior to a film on the subject. A posttest given 10 minutes after the film shows a 10-point gain from the pretest. The researcher concludes that the film produced the gain. Which of the following is likely the threat to internal validity?
Testing
A double-blind experiment is one in which
Neither the researcher nor the participants know which participants receive the experimental treatment
"To what populations, settings, treatment variables, and measurement variables can this effect be generalized?" might most appropriately be asked in relation to
External Validity
A researcher plans to compare the effects of two (2) methods of relaxation training on free-throw shooting. The researcher also wants to know whether the effectiveness of the methods depends on the participants' anxiety. Participants are stratified on the basis of type of training and high or low anxiety scores. What type of experimental design does this represent and what statistical analysis is called for?
Cause and effect
The internal validity of an experimental design is concerned with what question?
Did the independent variable really produce a change in the dependent variable?
A baseline in single subject research
Establishes initial rates of behavior before an intervention
In a research study in which the treatment involved quite intense physical training, 49% of the participants in the treatment group dropped out as compared with 5% of the control group. This threat to internal validity is called
Experimental Mortality
Interviews may become more skilled with practice, which could cause differences between the results of participants interviewed early in the study and those of participants interviewed later. This threat to internal validity is an issue of
Instrumentation
Sometimes it is not possible to actually administer the treatment (e.g., when comparing children who had been in Head Start vs children who had not). However, the researcher is trying to imply causation. This type of design (sometimes called causal comparative) is referred to as
An ex post facto design
Just before the posttest. students in the control group were shown a film in another class that related directly to the subject matter being studied in the treatment group. This represents what kind of internal validity?
History
Issues of internal and external validity are important in designing good studies. A number if factors affect internal and external validity. First, provide a definition of both internal and external validity and explain how each affects the quality of an experimental study. Second, explain and provide an example of how statistical regression, selection maturation, and experimental mortality could affect the quality of the experiment
Internal Validity is the basic minimum without which any experiment is uninterpretable External Validity asks the question of generalizability Statistical Regression can occur when groups are not randomly formed by not selected based on an extreme score on some measure Ex. If someone rates the behavior of a group of children on a playground on an activity scale (very active to very inactive) and two (2) groups are formed -- 1 very active and 1 very inactive -- statistical regression is likely to occur when the children are next observed on the playground Selection Maturation occurs only in designs in which one (1) group is selected because of some specific characteristic, whereas the other group lacks this characteristic Ex.: A study of the differences between 6-year-olds in two (2) school districts; students in one school district from the experimental group that receives a fitness program, and students in the other are a control group Experimental Mortality refers to the loss of participants
It is reasonable to expect volunteer participants to be similar in nature to
Other volunteers from similar populations
The one characteristic of true experimental designs that preexperimental and quasi-experimental designs do not have is
Random assignment to groups
The only experimental design that can specifically evaluate the reactive or interactive effects if testing is the ___________ design
Solomon four-group