Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
74 Cards in this Set
- Front
- Back
What type of research is conducted in most disciplines? |
experimental research. It is virtually the only type of research performed in the sciences. |
|
why is experimental research conducted? |
to increase the body of knowledge in a discipline and to suggest what procedures should be followed in the future. |
|
What does experimental research always involve? |
manipulation of the experimental unit. |
|
what is the purpose of experimental research? |
investigate the cause-and-effect relationship by subjecting experimental groups to treatment conditions and comparing the results to control groups not receiving the treatment. |
|
List the 14 systematic stages used in experimental research. |
1. state research problem 2. determine if the experimental approach is appropriate 3. specify the independent variable(s) and the levels of the independent variable(s). 4. specify all the potential dependent variables. Dependent variables 5. state the tentative hypothesis 6. determine the availability of measures for the potential dependent variables 7. pause to consider the success potential of the research 8. ID the full potential of intervening variables 9. make a formal statement of the research hypothesis 10. design the experiment 11. make a final estimate of the success potential of the study 12. conduct the study as planned in number 1 and 11. 13. analyze the data according to the data analysis plan 14. prepare a research report. |
|
define internal validity |
validity of the findings within or internal to the research study. |
|
define external validity |
validity of generalizing the findings in a research study to other groups and situations. |
|
list two classifications of validity |
1. internal validity 2. external validity |
|
what type of validity is concerned with whether the findings for the sample of participants in the study can be inferred to the population they represent and to other populations? |
external validity |
|
list the types of threats to internal validity |
1. History 2. Maturation 3. Testing 4. Instrumentation 5. Statistical regression 6. Selection 7. Experimental Mortality 8. Interaction of Selection and Maturation or History |
|
list the types of threats to external validity |
1. Interaction Effect of testing 2. Interaction Effects of Selection Bias and Experimental Treatment 3. Reactive Effects of Experimental Setting 4. Multiple-Treatment Interference |
|
define the meaning of history in internal validity |
refers to specific things that happen while conducting the research study that affect the final scores of the participants in addition to the effect of the experimental treatment.
ex. participant workout out outside of the experimental treatment and study could effect final results. |
|
define maturation in internal validity |
because participants grow older during the experimental period, performance levels change.
|
|
define testing in internal validity |
the act of taking a test can affect the scores of the participants on a second or later testing. Participants may do better on a posttest because they learn from the first test. |
|
define instrumentation in internal validity |
changes in adjustment or calibration of the measuring equipment or use of different standards among scorers may cause differences among groups in final score.
check accuracy of measuring equipment routinely, and make sure standard scoring procedure is used. Testing and score procedures must be held constant. |
|
define statistical regression in internal validity. |
the tendency for groups with extremely high or low scores on one measure to score closer to the mean score of the population on a second measure. |
|
what can eliminate the threat of statistical regression? |
random sampling |
|
define selection in terms of internal validity. |
the way that participants were selected or assigned to groups can be biased. |
|
what controls for the selection threat in internal validity? |
random selection or participants and random assignment of participants to groups. |
|
define experimental mortality in internal validity |
created with excessive loss of participants so that experimental groups are no longer representative of a population or similar to each other.
when groups become different in size, it is a concern. |
|
define internal selection and maturation or History in internal validity. |
the maturation effect or history effect is not the same for all groups selected for the research study, and this influences final scores. |
|
what are the threats to external validity? |
1. Interaction Effect of Testing 2. Interaction Effects of Selection Bias and Experimental Treatment 3. Reactive Effects of Experimental Setting 4. Multiple-Treatment Interference |
|
define interaction effect of testing in external validity |
occurs when the pretest changes the groups response to the experimental treatment, thus making the group unrepresentative of any particular population. |
|
define interaction effects of selection bias and experimental treatment in external validity. |
participants or groups selected in biased manner react to the experimental treatment in a unique way so they are not representative of any particular population.
can easily occur when convenience is used. |
|
define reactive effects of experimental treatment. |
the experimental setting is such that the experimental treatment has a unique effect on the participants or groups that would not be observed in some other setting.
examples: - participants react to researcher in unique manner - conducting research in a lab, rather than natural setting |
|
define multiple-treatment interference in external validity |
the effect of prior treatments on the response of the participants or groups to a present treatment.
|
|
how should the multiple-treatment interference threat be controled? |
researchers should check on the background and experiences of potential participants to control this threat to external validity. |
|
define designs |
the ways a research study may be conducted. |
|
what types of experimental designs are listed in the book? |
1. Preexperimental design 2. true experimental design 3. Quasi-experimental design |
|
define pre-experimental design |
designs that have poor control often due to no random sampling. |
|
define true experimental design |
the best type of design because there is good control with sufficient random sampling. |
|
define control goup |
in a research study, the group which received no treatment which should change its ability. |
|
define quasi-experimental design |
an acceptable design but with some loss of control due to lack of random sampling. |
|
what is a better design? preexperimental or quasi-experimental design? |
quasi-experimental. |
|
what is an example of a quasi-experimental design? |
the nonequivalent control group design. Like pretest/posttest control group design but except participants are not assigned to groups by using random sampling. |
|
What does a quasi-experimental control for? |
threats to validity of history, maturation, testing, instrumentation, selection, and experimental mortality. |
|
what threats does a quasi-experimental design not control for? |
threats to validity of the interaction effects of maturation and history, or the interaction effect of testing. |
|
designs can be discussed in terms of what two things? |
1. complexity 2. ability to answer research questions. Simple designs answer one question and more complex designs answer several research questions. |
|
why are preexperimental designs weaker than true experimental designs in terms of control? |
1. no random sampling of participants 2. are usually one group or two unequated groups 3. control few threats to validity |
|
give an example of a preexperimental design. |
1.one-group pretest/posttest design 2.the use of intact classes |
|
if the treatment groups are unequal at the end of the study in a preexperimental design, it could be due to... |
1. treatment were not equally effective 2. the groups were unequal at the start of the study 3. some combination of the two |
|
A design must do what? |
- control for major threats to validity. - allow the researcher to answer the research question - Follow KISS principle - design must be adequate, but don't make the design any more complicated than it needs to be. |
|
what is the basic procedure, from the design stand point, if there are two or more groups? |
1. define the target population 2. ID the accessible population 3. randomly select participants 4. randomly assign participants to groups |
|
is maximal internal or external validity obtained in most studies? |
no, due to constraints on finances, time, participants, the research setting or other resources. |
|
what is a must in order to have good external validity. |
good internal validity |
|
True of false: Sometimes minor threats and threats that are hard to eliminate may have to be left uncontrolled. |
True |
|
In an experimental design, what does a research want to control? |
Control the effect of all variables except the experimental variable. |
|
List the ways in which the control of variables can be obtained? |
1. Physical manipulation 2. Selective manipulation 3. Matched pair design 4. Block design 5. Counterbalanced design 6. statistical techniques |
|
define selective manipulation |
method of gaining control by selectively manipulating certain participants or situations |
|
define matched pairs design |
a form of selective manipulation by which participants are matched to gain control |
|
define block design |
an extension of matched pairs design for three or more groups |
|
define statistical techniques |
method of gaining control if other control techniques are not possible |
|
define analysis of covariance (ANOVA) |
a statistical technique to gain control by adjusting for initial differences among groups |
|
define covariate |
score used to adjust for initial differences among groups in ANCOVA |
|
define variate |
the score adjusted in ANCOVA |
|
what are forms of selective manipulation? |
1. Matched Pairs 2. block design 3. counterbalance design |
|
what is an example of a counterbalance design? |
comparison of the effectiveness of two drugs. |
|
when are statistical techniques employed in order to gain control? |
when physical manipulation or selective manipulation of variables is not possible.
the researcher knows at the beginning of a study that the experimental groups differ in terms of one or more variables. |
|
what is the basic purpose of the ANCOVA? |
adjusts for the differences among the groups in scores at the end of the study based on differences in initial ability. |
|
When using the ANCOVA technique, what is obtained at the beginning of the study? |
- a covariate - used to adjust differences among groups in terms of a score, called the variate, collected at the end of the study |
|
list the common sources of error in research. |
1. Hawthorne Effect 2. Placebo Effect 3. "John Henry" Effect 4. Rating Effect 5. Experimenter Bias Effect 6. Participant-Researcher Interaction Effect 7. Post Hoc Error |
|
define hawthorne effect |
participants in an experiment may perform in an atypical manner due to the newness or novelty of the treatment and because they realize that they are participating in an experiment. |
|
define placebo effect |
participants in an experimental treatment may believe the treatment is supposed to change them so they respond to the treatment with a change in performance. |
|
define placebo |
a treatment that can have no effect on any dependent variable of participants in a control group. |
|
define "john henry" effect |
in studies with an experimental group and a control group, the control group knows it is not supposed to be better than the experimental, so it tries harder and outperforms the experimental group |
|
define rating effect |
1. halo effect 2. central tendency error |
|
define halo effect |
the tendency to let initial impressions influence future ratings or scores of a participant |
|
define central tendency error |
a tendency to rate most participants in the middle of the rating scale. |
|
what can the halo effect cause? |
1. overrater error 2. underrater error
- researcher tends to overrate or underrate participants |
|
define experimenter bias effect |
the bias of a researcher can affect the outcome of study. The bias often favors the experimental treatment |
|
define single-blind study |
a study in which participants are unaware of the purpose of the study and their role in the study. |
|
define double-blind study |
a study in which participants and those conducting the study are unaware of the purposed of the study and group membership participants. |
|
define participant-researcher interaction effect |
- whether participants respond better to the same gender - whether or not a certain setting may influence a participant |
|
define post hoc error |
caused by assuming a cause-and-effect relationship between two variables when such a relationship does not exist.
ex. most people die in bed than any other place; therefore, beds are dangerous. |