Research Methods Exam 2

independent variable

a variable manipulated by the researcher to observe its effect on a dependent variable

dependent variable

the factor of interest being measured in the study that changes in response to manupulation of the independent variable

stereotype threat

the prompt of a stereotypical belief that leads an individual to fulfill the expectations of that stereotype

conditions

The intervention or treatment in an experiment given to a particular group of participants.

level

a possible condition in the experimental variable

internal validity

An assessment of whether a particular variable is the actual cause of a particular outcome.

external validity

A measure of the degree to which the conclusions drawn from a particular set of results can be generalized to other samples or situations

quasi-independent variable

A preexisting characteristic (e.g., sex, age or race) to which a participant cannot be randomly assigned.

attention control group

A type of control in which participants receive everything the experimental group receives (e.g., the same amount of time and attention), with the exception of the “active ingredient” of the intervention or treatment.

quasi random assignment

The researcher assigns equal numbers of participants with key characteristics (e.g., sex, age, or race) across the experimental and control conditions.

between subjects design

A type of experimental design in which the researcher assigns individual participants or groups of participants to one of several conditions to detect differences between groups of participants, with each group exposed to a separate condition.

within-subject designs/ repeated measures

A type of experimental design in which the researcher assigns each participant to all possible conditions.

order effect

A potential effect of a within-subjects design in which the order that participants receive different experimental conditions may influence the outcome.

simple order effect

the particular order of the experimental conditions influence the results

fatigued/ boredom effect

Participants begin to perform more poorly as the experiment goes on as a consequence of repeated exposure to experimental conditions in a within-subjects design.

carryover effect

The result of a participant’s performance in one experimental condition affecting his or her performance in a subsequent condition

matched group designs

A type of experimental design in which researchers assign separate groups of participants in each condition and “twin” a participant in each group with a participant in another group. It contains elements of both between-subjects and within-subjects designs

confounds

Uncontrolled variables that change with the independent variable(s) in your experimental design and could account for effects that you find.

Extraneous variables

Uncontrolled variables that vary with the independent variable(s) in your experimental design and could account for effects that you find

hawthorne (or observer effect)

Participants in a study modify their behavior as a result of knowing they are being observed.

demand characteristics

Features of the experimental design itself that lead participants to make certain conclusions about the purpose of the experiment and then adjust their behavior accordingly, either consciously or unconsciously.

Blind or blinded design

The experimenter measuring the behavior of interest does not know what intervention (if any) the individuals being observed have received

single-blind design

Either the participants or the experimenters collecting the data are unaware of the condition to which participants have been assigned.

double-blind design

Both participants and experimenters collecting the data are unaware of the condition to which participants have been assigned

statistical control

In analyzing study results, the researcher makes a statistical adjustment that accounts for the influence of a specified third variable and allows for the analysis of results with the influence of that third variable eliminated

randomization

the researcher arranges the presentation of conditions or stimuli for each participant in a random way to ensure that no one particular order influences the results.

counterbalancing

a strategy that ensures control for the order of experimental interventions. The researcher calculates all the possible orders of interventions and confirms even distribution of the different order combinations across participants.

Latin Square

A type of counterbalancing technique in which each participant receives different experimental conditions in a systematically different order.

ceiling effect

This occurs when a bounded response measurement results in scores that cluster at the upper end (the “ceiling”) of the measurement scale because of a constraint in the measure itself

floor effect

This occurs when a bounded response measurement results in scores that cluster at the lower end (the “floor”) of the measurement scale because of a constraint in the measure itself.

confederate

A person who is part of an experiment and plays a specific role in setting up the experimental situation.

single-case experimental design

A design in which experimental methodology (e.g., implementing experimental and control conditions) is applied to a single subject.

Reversal design (or aBa design)

A type of single-case experimental design in which baseline measurements are initially taken (A), a treatment/intervention is then implemented and measurements are taken (B), and finally the treatment/ intervention is removed and measurements are taken one last time (A).

multiple baseline design

An approach that uses a varying time schedule to help determine whether the treatment itself is actually leading to the change (as opposed to just the passage of time). In this design, measurements are made at baseline, then after an intervention or treatment, and then again when the intervention is completed or the treatment withdrawn (return to baseline).

Quasi-experimental design

a design that includes some elements of experimental control without being a true experiment

factorial design

an experimental design that has more than one independent variable

factor

a variable manipulated by the experimenter

levels

The values taken on by an independent variable or factor. For example, in a drug effectiveness study, you may have a factor of “treatment,” which has levels of “placebo” and “drug.”

cell

A combination of one level from each factor in the experiment. The number of cells in a factorial design equals the number of levels of the different factors multiplied by each other. For example, a 2 × 2 design would have 4 cells, whereas a 3 × 4 design would have 12 cells.

main effect

the overall effect of a single factor on the dependent variable, ignoring the effects of or averaging over the levels of all other factors.

interaction

A situation that arises when the effect of one factor (independent variable) on the dependent variable is contingent on the levels of at least one other factor.

interaction chart

a diagram that represents different combinations of the presence of absece of main and interaction effect

mixed factorial design

a design that includes both within subjects and between subjects factors

higher-order factorial design

A design that includes more than two independent variables. For example, a 2 × 2 × 2 design, with three factors, two levels for each factor, and eight cells or conditions.