| |
Quantitative Research Designs
Key Terms
|
- comparative studies
- Studies in which intact groups are compared on some dependent variable. The researcher is not able to manipulate the independent variable, which is frequently some inherent characteristic of the subjects, such as age or educational level.
- comparison group
- A group of subjects in an experimental study that does not receive any experimental treatment or receives an alternate treatment such as the "normal" or routine treatment.
- control group
- A group of subjects in an experimental study that does not receive the experimental treatment (see comparison group).
- correlation
- The extent to which values of one variable (X) are related to the values of a second variable (Y). Correlations may be either positive or negative.
- correlation coefficient
- A statistic that presents the magnitude and direction of a relationship between two variables. Correlation coefficients range from -1.00 (perfect negative relationship) to +1.00 (perfect positive relationship).
- correlational studies
- Research studies that examine the strength of relationships between variables.
- descriptive studies
- Research studies in which phenomena are described or the relationship between variables is examined; no attempt is made to determine cause-and-effect relationships.
- experimenter effect
- A threat to the external validity of a research study that occurs when the researcher's behavior influences the subjects' behavior in a way that is not intended by the researcher.
- explanatory studies
- Research studies that search for causal explanations; usually experimental in nature.
- exploratory studies
- Research studies that are conducted when little is known about the phenomenon that is being studied.
- ex post facto studies
- Studies in which the variation in the independent variable has already occurred in the past, and the researcher, "after the fact," is trying to determine if the variation that has occurred in the independent variable has any influence on the dependent variable that is being measured in the present.
- external validity
- The degree to which study results can be generalized to other people and other research settings.
- extraneous variable
- A type of variable that is not the variable of interest to a researcher but that may influence the results of a study. Other terms for extraneous variable are intervening variable and confounding variable.
- field studies
- Research studies that are conducted "in the field" or real-life setting.
- Hawthorne effect
- A threat to the external validity of a research study that occurs when study participants respond in a certain manner because they are aware that they are involved in a research study.
- history
- A threat to the internal validity of an experimental research study; some event besides the experimental treatment occurs between the pretreatment and posttreatment measurement of the dependent variable, and this event influences the dependent variable.
- instrumentation change
- A threat to the internal validity of an experimental research study that involves changes from the pretest measurements to the posttest measurements as a result of inaccuracy of the instrument or the judges' ratings rather than as a result of the experimental treatment.
- internal validity
- The degree to which changes in the dependent variable (effect) can be attributed to the independent or experimental variable (cause) rather than to the effects of extraneous variables.
- laboratory studies
- Research studies in which subjects are studied in a special environment that has been created by the researcher.
- manipulation
- The independent or experimental variable is controlled by the researcher to determine its effect on the dependent variable.
- maturation
- A threat to the internal validity of an experimental research study that occurs when changes that take place within study subjects as a result of the passage of time (growing older, taller) affect the study results.
- methodological studies
- Research studies that are concerned with the development, testing, and evaluation of research instruments and methods.
- mortality
- A threat to the internal validity of an experimental research study that occurs when the subject drop-out rate is different or characteristics are different between those who drop out of the experimental group and those who drop out of the comparison group.
- negative relationship (inverse relationship)
- A relationship between two variables in which there is a tendency for the values of one variable to increase as the values of the other variable decrease.
- nonequivalent control group design
- A type of quasiexperimental design; similar to the pretest-posttest control group experimental design, except that there is no random assignment of subjects to groups.
- one-group pretest-posttest design
- A type of preexperimental design; compares one group of subjects before and after an experimental treatment.
- one-shot case study
- A type of preexperimental design; a single group of subjects is observed after a treatment to determine the effects of the treatment. No pretest measurement is made.
- positive relationship (direct relationship)
- A relationship between two variables in which the variables tend to vary together; as the values of one variable increase or decrease, the values of the other variable increase or decrease.
- posttest-only control group design
- True experimental design in which subjects in the experimental and comparison groups are given a posttest after the experimental group receives the study treatment.
- preexperimental design
- A type of experimental design in which the researcher has little control over the research situation; includes the one-shot case study and the one-group pretest-posttest design.
- pretest-posttest control group design
- True experimental design in which subjects in the experimental and comparison groups are given a pretest before and a posttest after the administration of the study treatment to the experimental group.
- prospective studies
- Studies in which the independent variable or presumed cause (use of birth control pills, for example) is identified at the present time and then subjects are followed for some time in the future to observe the dependent variable or effect (thrombophlebitis or myocardial infarctions, for example).
- quasiexperimental design
- A type of experimental design in which there is either no comparison group or no random assignment of subjects to groups; includes the nonequivalent control group design and time-series design.
- random assignment
- A procedure used in an experimental study to ensure that each study subject has an equal chance of being placed into any one of the study groups.
- reactive effects of the pretest
- A threat to the external validity of a research study that occurs when subjects are sensitized to the experimental treatment by the pretest.
- retrospective studies
- Studies in which the dependent variable is identified in the present (e.g., a disease condition) and an attempt is made to determine the independent variable (e.g., cause of the disease) that occurred in the past.
- Rosenthal effect
- The influence of interviewers on respondents' answers.
- selection bias
- A threat to the internal validity of an experimental research study that occurs when study results are attributed to the experimental treatment when, in fact, the results may be due to pretreatment differences between the subjects in the experimental and comparison groups.
- simulation studies
- Laboratory studies in which subjects are presented with a description of a case study or situation that is intended to represent a real-life situation.
- Solomon four-group design
- True experimental design that minimizes threats to internal and external validity.
- survey studies
- Research studies in which self-report data are collected from a sample to determine the characteristics of a population.
- testing
- A threat to the internal validity of a research study that occurs when a pretest is administered to subjects; the effects of taking a pretest on responses on the posttest.
- time-series design
- Quasiexperimental design in which the researcher periodically observes subjects and administers an experimental treatment between two of the observations.
- true experimental design
- An experimental design in which the researcher (a) manipulates the experimental variable, (b) includes at least one experimental and one comparison group in the study, and (c) randomly assigns subjects to either the experimental or comparison group; includes the pretest-posttest control group design, posttest-only control group design, and Solomon four-group design.
|
