Term
|
Definition
| When the observed effects of he independent variable on the dependent variable are real and not caused by extraneous factors. |
|
|
Term
|
Definition
| When the results of a research study can be generalized to groups and settings beyond those of the current experiment. |
|
|
Term
| Threat to internal variablity |
|
Definition
| Extraneous factors that allow for alternative explanations as to what caused a given effect on the dependent variable |
|
|
Term
|
Definition
Threatens INTERNAL validity when evens occur between the pretest and posttest of a study that could affect participants in a way that impacts the dependent variable.
Protect against threat by using a control group. |
|
|
Term
|
Definition
Threatens INTERNAL validity when changes are seems in subjects due to the amount of time that has elapsed since the study began that may not be the result of any program effects.
Protect against threat by using a control group. |
|
|
Term
| Selection Treatment Interaction |
|
Definition
Threatens EXTERNAL validity. Concerned with researcher's ability to generalize study results to the larger population.
Protect against threats by using large random sample that is representative of larger population and not generalizing results to other outside groups. |
|
|
Term
|
Definition
Threatens INTERNAL validity when there are differences in the location where interventions take place.
Protect against threat by making the location the same for all participants or minimize the location differences that could impact the dependent variable. |
|
|
Term
| Selection Maturation Effect |
|
Definition
Threatens INTERNAL validity when there is a selection bias with a maturation effect and the intact group varies in their maturation level.
Protect against threat by pretesting and/or prescreening groups on maturity levels. |
|
|
Term
|
Definition
Threatens INTERNAL validity when program results are due to participants expectations, rather than the provided treatment.
Protect against threat in pharmaceutical studies by using a blind study, where the control group is unknowingly given a placebo (an inactive substance that looks like the treatment), or a double blind study, where the researcher also doesn't know who has taken the placebo. In other studies, give both groups the same information. |
|
|
Term
|
Definition
Threatens INTERNAL validity when the treatment being applied to one group spills over to contaminates another group.
Protect against threat by having the control group be located in an area far from the experimental group, or if this isn't possible, explain the nature of the study to participants, emphasizing the need to keep certain treatments confidential, as to not influence the control group to try to get these treatments on their own. |
|
|
Term
|
Definition
Threatens INTERNAL validity when participants are lost over the course of a study and sample sizes are too small to generalize. Dropouts create bias as only the highly motivated are left in the study.
Protect against threat by using large group sizes, using incentives to encourage participants to stay, and obtaining good demographic information to determine if group makeup has changed in the case of mortality. |
|
|
Term
|
Definition
Threatens INTERNAL validity when measurements are not accurate, when procedures are not standardized, and when researchers ask poorly designed questions.
Protect against threat by using well-designed instrumentation. |
|
|
Term
|
Definition
Threatens INTERNAL validity when individuals are selected for a study in a nonrandom manner.
Protect against threat by randomly assigning volunteers to groups, matching participants with selected characteristics and then randomly assigning them to groups, and pretesting groups on measures of the dependent variable to ensure no pretreatment differences exist between groups. |
|
|
Term
| History Treatment Interaction |
|
Definition
Threatens EXTERNAL validity when a researcher tries to generalize findings o past and future situations, since some experiments may be time-sensitive.
Protect against threat by duplicating historical factors as nearly as possible. |
|
|
Term
|
Definition
Threatens INTERNAL validity when participants attitudes toward being involved in a study affect the way they behave.
Protect against threat by providing control group with special treatment comparable to the experimental group that does not have a direct impact on the dependent variable. |
|
|
Term
| Setting Treatment Interaction |
|
Definition
Threatens EXTERNAL validity. Concerned with the extent to which the environmental conditions or setting under which an experimental study was conducted cant be duplicated in other settings.
Protect against threat by duplicating setting as nearly as possible. |
|
|
Term
|
Definition
Threatens INTERNAL validity when the individuals implementing the experimental treatment inadvertently introduce bias or inequality into the study.
If effect occurs because of differences between implementors that cause some to present information to participants better than others, then protect against threat by trying to make sure that all implementors are equally trained and competent and follow a standardized protocol, or have all implementors present to all groups.
If effect occurs because implementor inadvertently favors one group over another, protect against threat by having someone other than the program developer present the program who is neutral to both the new experimental and old standard programs. Or have a neutral observer watch the presenter to look out for presenter biases. |
|
|
Term
|
Definition
Threatens INTERNAL validity when participants are selected for a study on the basis on their extremely high or low test scores, causing them to regress towards the mean in following studies.
Protect against threat by using random samples that pre resent population. |
|
|
Term
|
Definition
| Group of participants who are exactly like the treatment group, except they receive no treatment |
|
|
Term
|
Definition
| Group receiving treatment |
|
|
Term
|
Definition
| Measurement taken to obtain the status or level of a variable prior to initiating a study. Compared to posttest measurements to determine program effectiveness. |
|
|
Term
|
Definition
| Causes the differences seen from baseline to posttest that are not the result of the independent variable. |
|
|
