Glossary of Research

| A | B | C | D | E | F | G | I | M | P | Q | R | S | T | U | V |

A

Aggregate - A group of persons that have certain traits or characteristics in common without necessarily having any direct social connection with one another. For example, "all female physicians" is an aggregate; so is "all European cities with populations over 20,000." Gross National Income is an aggregation of data about individual incomes.

Applied research - Research undertaken with the intention of applying the results to some specific problem, such as studying the effects of different methods of law enforcement on crime rates. One of the biggest differences between applied and basic research is that in applied work the research questions are most often determined, not by researchers, but by policy makers or others who want help. Types of applied research include evaluation research and action research.

B

Bivariate Analysis - Pertaining to two variables only.

C

Construct - (a) Something that exists theoretically but is not directly observable. (b) A concept developed (constructed) for describing relations among phenomena or for other research purposes. (c) A theoretical definition in which concepts are defined in terms of other concepts. For example, intelligence cannot be directly observed or measured; it is a construct.

Control Group - In experimental research, a group that, for the sake of comparison, does not receive the treatment the experimenter is interested in.

Correlation - The extent to which two or more things are related ("co-related") to one another. This is usually expressed as a correlation coefficient.

Covariation - (a) A state that exists when two things - such as the price and the sales of a commodity - vary together. Measures of association are designed to capture the degree of covariation.

Crossbreaks - Also called cross-tabulation ("crosstabs") and cross partitions. A way of arranging data about categorical variables in a matrix so that relations can be more clearly seen. This is not to be confused with a factorial table, in which two or more variables are related to a third. While not all researchers make these distinctions in the terms, the concepts are quite distinct.

For example, Table 1 is a 2x2 crossbreak table. It shows the relation between race and high school dropout rates. Table 2, on the other hand, is a 2x2 factorial table where the influence of two variables (race and education) on a third, average annual income, is shown. (Figures for both tables are approximate for 1990.)

D

Data base - a collection of data organized for rapid search and retrieval, usually by a computer; often a consolidation of many records previously stored separately.

Data set - a collection of related data items, such as answers given by respondents to all questions on a survey.

Data - information collected by a researcher. (Data is the plural term; datum the singular). Data are often thought of as statistical or quantitative, but they may take many other forms as well--such as transcripts of interviews or videotapes of social interactions. Nonquantitative data such as transcripts or videotapes are often coded or translated into numbers to make them easier to analyze.

Dependent variable - (a) The presumed effect in a study; so called because it "depends" on another variable. (b) The variable whose values are predicted by the independent variable, whether or not caused by it. For example, in a study to see if there is a relationship between students' drinking of alcoholic beverages and their grade point averages, the drinking behavior would be the presumed cause (independent variable); the grade point average would be the effect (dependent variable).

Descriptive Statistics - statistics that summarize a data set, e.g., mean, median, mode, standard deviation.

E

Error - The difference between an observed score and a predicted or estimated score. Symbolized as e or E.

Experiment - A study undertaken in which the researcher has control over some of the conditions in which the study takes place and control over some aspects of the independent variables being studied. Random assignment of the subjects to control and experimental groups is usually thought of as a necessary criterion of a true experiment. For example, if you interviewed moviegoers as they exited a theater to see if what they saw influenced their attitudes, this would not be experimental research; you had no control over who the subjects were or what film they watched or the conditions under which they watched it. On the other hand, if you chose a room, a film, and subjects to assign randomly to control and experimental groups and interviewed these subjects about the effects of the film on their attitudes, that would be an experiment.

Experimental Group - A group receiving some treatment in an experiment. Data collected about people in the experimental group are compared with data about people in a control group (who received no treatment) and/or another experimental group (who received a different treatment).

Experimental design - The art of planning and executing experiments. The greatest strength of an experimental research design, due largely to random assignment, is its internal validity: One can be more certain than with any other design about attributing cause to the independent variables. The greatest weakness of experimental designs may be external validity: It may be hard to generalize results beyond the laboratory.

External validity- the extent to which the findings of a study are relevant to subjects and settings beyond those in the study. Another term for generalizability.

F

Factor - (a) in analysis of variance, an independent variable, that is, a variable presumed to cause or influence another variable. (b) in factor analysis, a cluster of related variables that are distinguishable components of a larger set of variables. c) a number by which another number is multiplied, as in the statement: real estate values increased by a factor of three, meaning they tripled.

G

Generalizability - the extent to which you can come to conclusions about one thing (often a population) based on information about another (often a sample).

I

Independent variable - The presumed cause in a study. Also a variable that can be used to predict the values of another variable. Compare dependent variable. Some authors use the term "independent variable" for experimental research only; for nonexperimental research, they use predictor variable.

Internal validity - the extent to which the results of a study (usually an experiment) can be attributed to the treatments rather than a flaw in the research design; in other words, the degree to which one can draw valid conclusions about the causal effects of one variable on another.

M

Multivariate Analysis - Any of several methods for examining multiple variables at the same time. Usage varies. (a) Stricter usage reserves the term for designs with two or more independent variables and two or more dependent variables. (b) More loosely, multivariate analysis applies to designs with more than one independent variable or more than one dependent variable or both. Whichever usage you prefer, either allows researchers to examine the relation between two variables while simultaneously controlling for the influence of other variables. Examples include path analysis, factor analysis, multiple regression analysis, MANOVA, LISREL, canonical correlations, and discriminant analysis.

Mutually exclusive - said of two events, conditions, or variables which cannot occur at the same time. For example, one cannot be both male and female, or both Protestant and Catholic. Thus, the categories male and female, or Catholic and Protestant are said to be mutually exclusive.

P

Population - a group of persons that one wishes to describe or about which one wishes to generalize. To generalize about a population, one often studies a sample that is meant to be representative of the population. Also called "universe."

Q

Qualitative Research - (a) When referring to variables, "qualitative" is another term for categorical or nominal. (b) When speaking of kinds of research, "qualitative" refers to studies of subjects that are hard to quantify, such as art history. Qualitative research tends to be a residual category for almost any kind of nonquantitative research.

Quantitative Research - Said of variables or research that can be handled numerically. Usually (too sharply) contrasted with qualitative variables and research.

Quasi-experiment - A type of research design for conducting studies in field or real-life situations where the researcher may be able to manipulate some independent variables but cannot randomly assign subjects to control and experimental groups. The procedures of quasi-experimentation were developed mainly in the context of evaluation research projects. For example, you cannot cut off someone's unemployment benefits to see how well he or she could get along without them or to see whether an alternative job-training program would be more effective for some unemployed persons. But you could try to find volunteers for the new program. You could compare the results for the volunteer group (experimental group) with those of people in the regular program (control group). The study is quasi-experimental because you were unable to assign subjects at random to treatment and control groups. Questionnaire - A group of written questions to which subjects respond. Some restrict the use of the term "questionnaire" to written responses.

R

Reliability - the consistency or stability of a measure or test from one use to the next. When repeated measurements of the same thing give identical or very similar results, the measure is said to be reliable.

Research Design - the science and art of planning procedures for conducting studies so as to get the most valid findings. Called "design" for short. When designing a research study, one draws up a set of instructions for gathering evidence and for interpreting it.

S

Sample - A group of subjects selected from a larger group in the hope that studying this smaller group (the sample) will reveal important things about the larger group.

Scale - a group of related measures of a variable. The items in a scale are arranged in some order of intensity or importance. A scale differs from an index in that the items in an index need not be in a particular order, and each item usually has the same weight or importance.

Subject - an individual who is studied.

Survey - A research design in which a sample of subjects is drawn from a population and studied (usually interviewed) to make inferences about the population. This design is often contrasted with the true experiment in which subjects are randomly assigned to conditions or treatments.

T

Treatment - In experiments, a treatment is what researchers do to the subjects in the experimental group, but not to those in the control group. A treatment is thus an independent variable.

U

Univariate Analysis - studying the distribution of cases of one variable only--for example, studying the ages of welfare recipients but not considering their gender, ethnicity, and so on.

V

Validity - a term to describe a measurement instrument or test that measures what it is supposed to measure; the extent to which a measure is free of systematic error. For example, a bathroom scale provides a reliable measure cannot give a valid measure of height.

Variance - A measure of the spread of scores in a distribution of scores, that is, a measure of dispersion. The larger the variance, the further the individual cases are from the mean. The smaller the variance, the closer the individual scores are to the mean.

Primary Source: Vogt, P. W. (1993). Dictionary of statistics and methodology. A non-technical guide for the social sciences. Newbury Park, CA: Sage Publications.