Applied researchresearch that is conducted for the purpose of applying the results to a specific problem; research that seeks to apply scientific knowledge to the solution of practical problems and investigates problems that have practical value. See: basic research.
Baseline evaluationgathering information from research participants prior to the administration of an intervention in order to measure what is being evaluated (such as number of drinks consumed per day), and typically to compare any changes before and after exposure to the intervention. Such evaluations are often in the form of a researcher-led interview or a self-administered survey. See: intervention.
Basic researchresearch that seeks to advance knowledge and theoretical understandings of the relationships among variables; research that seeks to discover general laws that influence certain behaviors. See: applied research.
Case studyan in-depth examination of individuals, groups, or institutions that is conducted and designed to result in a thorough and well-organized snapshot of the subject being examined.
Comparison groupin a quasi-experimental research design, this is the group of research subjects that, for the sake of comparison, does not receive the treatment or intervention given to the intervention group. Comparison group subjects are typically not randomly assigned to their condition, as would be true of control group subjects in an experimental design study. See: control group, experimental group.
Control groupin an experimental research design, this is the group of research subjects that, for the sake of comparison, does not receive the treatment or intervention given to the intervention group. Control group subjects are randomly assigned to their condition, as are their intervention group counterparts. See: comparison group, experimental group.
Correlationthe extent to which two or more things are related to one another. The degree to which things are related to one another (correlated) is typically expressed in a number called the correlation coefficient (which ranges from -1.0 to +1.0). See positive correlation, negative correlation.
Dependent variablethe presumed effect (an outcome) of a research study; the variable whose values are predicted by the independent variable. See: variable, independent variable.
Epidemiologythe study of diseases or conditions as they affect groups (not individuals). It involves the study of various factors influencing the occurrence, distribution, prevention, and control of disease.
Experimental research designalso called a "true experiment," this is the most robust of all research designs because it includes random assignment to an intervention (treatment) and a control (no treatment comparison) group, and testing of both groups before and after the intervention. See: nonexperimental research design, quasi-experimental research design.
Experimental groupalso called intervention group, this is a group of research subjects that receives some form of treatment or intervention. See: comparison group, control group.
External validitythe extent to which observed effects that are attributable to an intervention are generalizable or can be expected in other settings and populations with similar or different characteristics. See: internal validity, validity.
Factor analysisseveral types of statistical approaches that can be used to analyze interrelationships among a large number of variables and to explain these variables in terms of their underlying dimensions (factors). It involves finding patterns among the variations in the values of several variables. See: variable.
Field researchvarious types of naturalistic research conducted in real-life settings, not in a laboratory or controlled environment. In field research, researchers observe but do not manipulate the study subjects. See: laboratory research.
Hypothesisan explanation for observations noted by researchers; a statement or a conjecture about the relationships among the variables that a researcher wants to study.
Incidencethe number of new or newly diagnosed cases of a disease that occurs during a given period. An incidence rate is the number of new cases of a disease divided by the number of persons at risk for the disease.
Independent variablethe variable that has been identified (from theory or elsewhere) as the possible cause of the phenomenon being researched. The level or strength of the independent variable is manipulated or changed by the researcher to identify whether the intervention had an expected effect. See: variable, dependent variable.
Internal validitythe extent to which an observed effect can be attributed to an intervention, rather than to flaws in the research design; the degree to which researchers can draw valid conclusions about what caused changes in the variables. See: external validity, variable.
Interventionin research, the treatment provided to research subjects that is the subject of the evaluation. Examples include a type of group therapy, a new medication, or a psychoeducation counseling program.
Intervention groupalso called the experimental group, the group of research subjects that receives some form of treatment or intervention. See: comparison group, control group, intervention.
Laboratory researchalso called clinical trials, research in which the researcher seeks to control conditions and variables to determine whether a clinical intervention produced the desired effects or if other factors were responsible for the desired effects. See: field research.
Negative correlationa direct relationship between two variables in which an increase in one variable is always accompanied by a decrease in the other variable, and vice versa. See: variable, correlation, positive correlation.
Nonexperimental research designa type of research design that does not include a comparison group or does not include a baseline evaluation. Thus, several factors prevent the attribution of an observed effect to the intervention. See: experimental research design, quasi-experimental research design.
Positive correlationa direct relation between two variables in which an increase in one variable is always accompanied by an increase in the other variable. See variable, correlation, negative correlation.
Populationa group of individuals (or institutions, programs, or other subjects being studied) about whom a researcher seeks to generalize. To generalize about a population, researchers study a sample that is meant to be representative of the population. See: sample.
PrevalenceThe total number of cases of a disease in existence at any one time in a defined population, including old and new cases. A prevalence rate is the total number of cases of a disease existing in a population divided by the total population.
Qualitative researchderived from the word quality, this form of research is designed to understand a human or social problem, based on building a complex, holistic picture, formed with words, reporting detailed views of informants, and conducted in a natural setting. It is the collection and analysis of subjective information. See: quantitative research.
Quantitative researchderived from the word quantity, this form of research focuses on evaluating a human or social problem, and is based on testing a theory that is composed of variables, measured with numbers, and analyzed with statistical processes to determine whether the predictive generalizations of the theory hold true. See: qualitative research.
Quasi-experimental research designa type of research design in which there is an intervention group receiving treatment and a comparison group not receiving treatment, both of which receive a baseline and post-intervention evaluation, but the study subjects are not randomly assigned to condition. See: experimental research design, nonexperimental research design.
Random assignmentthe process of placing research subjects into either intervention or control groups in such a way that each individual in each group is assigned entirely by chance. That is, each subject has an equal probability of being placed in each group.
Samplea group of study subjects (individuals, institutions, or programs) taken from a larger group in the hope that studying the smaller group (the sample) will reveal important things about the larger group (the population). See population.
Statisticssets of tools and techniques for describing, organizing, and interpreting information and data; numerical summaries of data obtained by measurement and computation; a branch of mathematics that deals with the collection and analysis of numerical data.
True experimentalso called experimental research design, this is the most robust of all research designs because it includes random assignment to an intervention (treatment) and a control (no treatment comparison) group, and testing of both groups before and after the intervention. See: nonexperimental research design, quasi-experimental research design.
Variablean attribute or characteristic that can change (vary) or that can be expressed in various values or categories. Examples of variables are height, age, amount of alcohol consumed per day, number of abstinent days following treatment, and different treatment approaches. See: dependent variable, independent variable.