Psychology: "Research Methods" by Michael W. Passer Glossary

Likert scale

a rating scale that measures participants' attitudes by combining scores on several items, each of which records how positively or negatively a participant feels about a statement (e.g., "strongly agree," "agree," "neither agree nor disagree").

qualitative case study

a case study in which the central goal is to examine an individual case in depth, within its real-life context, using qualitative methods.

reactivity

a change in behavior that occurs as a result of the process of observing (or otherwise measuring) behavior.

matching variable in a matched-groups design

a characteristic on which sets of individuals are matched as closely as possible.

situational variable

a characteristic that differs across environments or stimuli.

Nuremberg Code

a code established in 1947 by military tribunal judges that sets forth the ethical principles essential if a medical experiment is to be "permissible."

systematic error (also called bias)

a constant amount of error that occurs with each measurement.

bias

a constant amount of error that occurs with each measurement. See systematic error.

debriefing

a conversation with a participant, after data are gathered from that participant, in which the researcher conveys additional information about the study.

falsifiability

a criterion for judging testability; an assertion is testable if we can envision some type of empirical evidence that will reveal it to be false.

habituation

a decrease over time in the strength of a response to a repeated stimulus.

independent replication

a replication conducted by researchers who were not part of the original research group.

replication and extension (also called replication with extension)

a replication that adds a new design element to the original study.

sequential research design

a research design in which several age cohorts are tested longitudinally.

Institutional Review Board (IRB)

a legally mandated independent committee that evaluates whether an institution's proposed research with human participants complies with federal ethics regulations.

frequency polygon

a line graph that shows the distribution of a quantitative variable.

sampling frame

a list—of names, phone numbers, addresses, or other units—from which a sample will be selected.

prospective design

a longitudinal design in which variable X is measured at an earlier point in time than variable Y.

split-half reliability

a method of estimating reliability in which the items that compose a test are divided into two subsets, and the correlation between subsets is determined.

test-retest reliability

a method of measuring reliability determined by administering the same measure to the same participants on two or more occasions, under equivalent test conditions.

parameter

a number that describes a population (e.g., the percentage of Americans who hold a given political opinion).

statistic

a number that pertains to a sample.

social desirability bias in a study

a participant's tendency to respond in a way that the participant feels is socially appropriate, rather than as she or he truly feels.

fatigue effect

a performance decline that results from becoming tired, inattentive, or less motivated to perform well with repeated exposure to a task.

practice effect

a performance improvement due to gaining greater experience with a task.

subject variable

a personal characteristic that differs from one individual to another.

baseline phase

a phase of an experiment during which the treatment or intervention is not presented; often refers to an initial phase in which data are recorded prior to introducing a treatment.

testing

a potential threat to internal validity in which the act of measuring participants' responses affects how they respond on subsequent measures.

selection

a potential threat to internal validity in which, at the start of a study, participants in the various conditions already differ on a characteristic that can partly or fully account for the eventual results.

Beneficence, principle of

a principle in the APA Ethics Code stating that psychologists "should strive to benefit those with whom they work" (APA, 2010a, p. 3).

focus group

a procedure for gathering data in which a moderator leads a group of people through an interview and discussion of a set of topics.

random assignment

a procedure in which each participant has an equal probability of being assigned to any one of the conditions in the experiment.

single-blind procedure in experiments

a procedure in which either the participants or the experimenters, but not both, are kept unaware of who is receiving the actual treatment and who is receiving a placebo.

double-blind procedure in experiments

a procedure in which neither the participants nor the experimenters are aware of who is receiving the actual treatment and who is receiving a placebo.

counterbalancing in a within-subjects design

a procedure in which the order of conditions is varied so that no condition has an overall advantage relative to the other conditions.

masking (also called blinding)

a procedure in which the parties involved in an experiment are kept unaware of the hypothesis being tested and/or the condition to which each participant has been assigned.

blinding

a procedure in which the parties involved in an experiment are kept unaware of the hypothesis being tested and/or the condition to which each participant has been assigned. See masking.

science

a process of systematically gathering and evaluating empirical evidence to answer questions and test ideas.

peer-reviewed journal

a professional journal in which reports submitted for publication first undergo a screening process by several experts.

ethnography

a qualitative research approach that often combines participant observation with interviews to gain an integrative description of social groups.

empirical question (also called empirical claim)

a question or claim that, in principle, can be tested empirically through observation.

loaded question

a questionnaire item containing emotionally charged words that suggest one viewpoint or response is preferable to another, or containing assumptions with which the option to disagree is not provided.

leading question

a questionnaire item presented in an unbalanced way that can overtly or subtly suggest that one viewpoint or response is preferable to another.

double negative (question)

a questionnaire item whose phrasing contains two negative words.

confidence interval (CI)

a range of values within which a population parameter (e.g., a population mean) is estimated to fall, with a particular level of confidence.

margin of sampling error

a range of values within which the true population value is presumed to reside; see also sampling error.

longitudinal research

a research design in which the same participants are tested across different time periods (i.e., data are gathered on the same individuals or groups on two or more occasions over time); compare cross-sectional research.

cross-lagged panel design

a research design that involves three steps: (l) measure X and Y at Time l; (2) measure X and Y again, at Time 2; and (3) examine the pattern of correlations among X1, X2, Y1, and Y2.

descriptive research (also called nonexperimental research)

a research method in which researchers measure variables but do not manipulate them.

nonexperimental research

a research method in which researchers measure variables but do not manipulate them. See descriptive research.

experiment

a research method in which the researcher manipulates one or more variables, attempts to control extraneous factors, and then measures how the manipulated variables affect participants' responses.

survey

a research technique that uses questionnaires and/or interviews to gather information about participants.

nonrepresentative (or biased) sample

a sample that does not reflect important characteristics of the population.

biased sample

a sample that does not reflect important characteristics of the population. See nonrepresentative sample.

representative sample

a sample that reflects the important characteristics of the population.

convenience (or haphazard) sampling

a sampling method in which members of a population are selected nonrandomly for inclusion in a sample on the basis of convenience.

haphazard sampling

a sampling method in which members of a population are selected nonrandomly for inclusion in a sample on the basis of convenience. See convenience sampling.

cluster sampling

a sampling procedure in which units (e.g., geographic regions, schools) that contain members of the population are identified. These units—called "clusters"—are then randomly sampled, and within each sampled cluster either all members or randomly chosen members are selected to participate in the study.

quota sampling

a sampling technique in which a sample is nonrandomly selected to match the proportion of one or more key characteristics of the population.

stratified random sampling

a sampling technique in which a sampling frame is divided into groups (called strata; singular = stratum), and then within each group random sampling is used to select the members of the sample.

situation sampling

a sampling technique in which behavior is observed in a variety of settings.

nonprobability sampling

a sampling technique in which each member of the population either does not have a chance of being selected into the sample, the probability of being selected cannot be determined, or both.

probability sampling

a sampling technique in which each member of the population has a chance of being selected into the sample and in which the probability of being selected can be specified.

simple random sampling

a sampling technique in which every member of the sampling frame has an equal probability of being chosen at random to participate in the survey.

focal sampling

a sampling technique in which researchers select a particular member (or unit, such as a parent-infant dyad) who will be observed at any given time.

time sampling

a sampling technique in which researchers select a representative set of time periods during which observations will occur.

purposive sampling

a sampling technique in which researchers select a sample according to a specific goal or purpose of the study rather than at random.

scan sampling

a sampling technique in which the observer rapidly scans each member of a group at preselected times so that the entire group is observed within a relatively short period.

ordinal scale

a scale in which the different scale values represent relative differences in the amount of some attribute.

diary

a self-report technique in which participants record their behaviors or experiences for defined periods of time or whenever certain events take place.

theory

a set of formal statements that specifies how and why variables or events are related.

changing-criterion design

a single-case experimental design in which an initial baseline phase is followed by a treatment phase that lasts until the target behavior reaches a criterion level and becomes stable; treatment then continues in a series of additional phases, with a new (and typically more demanding) performance criterion set in each phase.

context effects in administering a survey (or questionnaire)

a situation in which responses to a survey item are influenced by the particular items that occur directly or soon before it.

research protocol

a standardized set of procedures that a researcher will follow with each participant.

range

a statistic that describes the highest and lowest scores in a distribution; it can also be expressed as the distance between them. range restriction the artificial limiting of the range of scores obtained for a variable.

Pearson's r (also called Pearson product-moment correlation coefficient)

a statistic that measures the direction and strength of the linear relation between two variables that have been measured on an interval or ratio scale.

z score

a statistic that transforms an original score into a number that represents how many standard deviations that score is from the mean.

Spearman's rho (also called Spearman rank-order correlation coefficient)

a statistic used to measure the relation between two quantitative variables when one or both variables have been measured on an ordinal scale (i.e., the scores represent ranks).

multiple regression

a statistical analysis that explores the linear relation between one variable and a set of two or more other variables.

regression analysis (also called simple linear regression)

a statistical analysis that explores the quantitative linear relation between two variables.

simple linear regression

a statistical analysis that explores the quantitative linear relation between two variables. See regression analysis.

partial correlation

a statistical approach in which a correlation between variable X and variable Y is computed while statistically controlling for their individual correlations with a third variable, Z.

correlation

a statistical association between variables.

Cohen's d

a statistical measure of effect size; commonly used to report effect sizes in experiments.

effect size

a statistical measure of the strength of a relation between two variables. In experiments, effect size measures the strength of a treatment effect.

meta-analysis

a statistical procedure for combining the results of different studies that examine the same topic.

analysis of variance (ANOVA)

a statistical test that determines whether the overall pattern of differences between the means of two or more groups is statistically significant.

field experiment

a study in which researchers manipulate an independent variable in a natural setting and exercise some control over extraneous factors.

quasi-experiment

a study that has some features of an experiment but lacks key aspects of experimental control.

psychophysics

a subfield of the study of sensation and perception that examines the relation between physical properties of stimuli (such as their intensity) and sensory-perceptual responses.

sample

a subset of cases or observations from a population.

double-barreled question

a survey item that asks about two issues within one question, forcing respondents to combine potentially different opinions into one judgment.

ethics

a system of moral principles and standards.

unobtrusive measure

a technique that assesses behavior without making people aware that the behavior is being measured or studied.

hypothesis

a tentative proposition about the causes or outcome of an event or, more generally, about how variables are related.

normal distribution (also called normal curve)

a theoretical distribution for a population of scores; the curve is symmetrical and bell shaped, and has other unique mathematical properties.

pilot study

a trial run, usually conducted with a smaller number of participants, prior to initiating the actual experiment.

anecdotal evidence

a type of evidence in which anecdotes—brief stories or descriptions about personal experiences, other people, or events—are offered as facts to support or refute a claim.

interval scale

a type of measurement in which equal distances between values on the scale reflect equal differences in the amount of the attribute being measured.

nominal scale

a type of measurement that occurs when the scale values represent only qualitative differences (i.e., differences of type rather than amount) of the attribute of interest.

sensitization effect

a type of order effect in which exposure to multiple conditions increases participants' awareness of, or sensitivity to, the variable that is being experimentally manipulated. sequence effects See order effects.

outcome evaluation

a type of program evaluation that assesses a program's effectiveness in achieving its goals.

process evaluation

a type of program evaluation that determines whether a program is being implemented as intended.

program theory and design assessment

a type of program evaluation that examines the rationale for why a program has been, or will be, designed in a particular way.

snowball sampling

a type of purposive sampling in which people contacted to participate in a survey are asked to recruit or to provide contact information (names, locations) for other people who meet the criteria for survey inclusion.

expert sampling

a type of purposive sampling in which researchers identify experts on a topic and ask them to participate.

multiple-baseline design

a type of single-case design in which (l) behavior is repeatedly measured, first during a baseline period and then during a treatment period; (2) this procedure is replicated with at least one other participant or behavior, or in one other setting; and (3) the time at which the treatment is introduced (and thus, typically, the length of the baseline period) varies across the different participants, behaviors, or settings.

multiple-baseline design across settings

a type of single-case design in which the same treatment is applied to the same target behavior in two or more settings, and the switch from baseline to treatment is staggered across settings.

multiple-baseline design across behaviors

a type of single-case design in which the same treatment is applied to two or more distinct behaviors of the same participant, and the switch from baseline to treatment periods is staggered across behaviors.

multiple-baseline design across subjects

a type of single-case design in which two or more participants are exposed to the same treatment, and the switch from baseline to treatment periods is staggered across participants.

withdrawal design (also called reversal design)

a type of single-case design in which, after the initial A phase, the subsequent A phases involve a "withdrawal" of the treatment or a "reversal" of the procedures; see also ABAB design.

ABAB design

a type of single-case design that involves a sequence of phases in which a treatment is either absent or present; see also withdrawal design.

reversal design

a type of single-case design that involves a sequence of phases in which a treatment is either absent or present; see also withdrawal design. See ABAB design; withdrawal design.

criterion variable

a variable that a researcher is trying to estimate or predict.

mediator variable

a variable that provides a causal link in the sequence between an independent variable and a dependent variable.

predictor variable

a variable whose scores are used to estimate scores of a criterion variable.

bar graph

a visual representation of data in which values of a variable are plotted on the x-axis and the descriptive statistic of interest is portrayed by the height of bars plotted along the y-axis.

random-selected-orders design

a within-subjects design in which a subset of orders is randomly selected from the entire set of all possible orders, and each order is administered to one participant.

reverse-counterbalancing design (also called ABBA counterbalancing design)

a within-subjects design in which each participant receives a random order of all the conditions and then receives them again in the reverse order.

ABBA-counterbalancing design

a within-subjects design in which each participant receives a random order of all the conditions and then receives them again in the reverse order. See reverse-counterbalancing design.

block-randomization design

a within-subjects design in which every participant is exposed to multiple blocks of trials, with each block for each participant containing a newly randomized order of all the conditions.

all-possible-orders design (also called complete counterbalancing)

a within-subjects design in which the conditions of an independent variable are arranged in every possible sequence, and an equal number of participants are assigned to each sequence.

complete counterbalancing

a within-subjects design in which the conditions of an independent variable are arranged in every possible sequence, and an equal number of participants are assigned to each sequence. See all-possible-orders design.

population

all the cases or observations of interest in a given study.

bidirectionality problem (also called two-way causality problem)

ambiguity about whether X has caused Y or Y has caused X.

two-way causality problem

ambiguity about whether X has caused Y or Y has caused X. See bidirectionality problem.

confederate

an accomplice of the investigator who is trained to act a certain way.

third-variable problem

an ambiguity in correlational research whereby a third variable, Z, may be the true cause of why X and Y appear to be related.

content analysis

an analysis of the different types of content found within or represented by a set of data.

natural-groups design

an approach in which a researcher measures a subject variable, forms different groups based on participants' level of that variable, and then measures how the different groups respond on other variables.

manipulation check

an approach that seeks to improve the validity of an experiment by determining whether the procedures used to manipulate an independent variable successfully captured the intended construct.

single-case study design

an approach to conducting a case study in which researchers analyze one case in depth.

multiple-case study design

an approach to conducting a case study in which researchers examine two or more cases and perform an in-depth analysis of each case.

mixed-methods case study design

an approach to conducting a case study in which researchers rely substantially on both qualitative and quantitative data and analyses to explore a case.

within-subjects design

an approach to designing experiments in which each participant engages in every condition of the experiment one or more times.

single-case experimental designs

an approach to experimentation that allows researchers to systematically examine how an independent variable influences the behavior of an individual case.

semi-structured interview

an approach to interviewing in which the researcher identifies in advance a set of topics or themes to be discussed with the interviewee, but the way and sequence in which questions are asked remain flexible.

skewed distribution

an asymmetrical distribution of scores on some variable, with scores clustering toward the high or low end of the possible range of values.

three-way interaction

an effect in which the interaction of two independent variables depends upon the level of a third independent variable.

two-way interaction

an effect in which the way that one independent variable influences a dependent variable depends upon the level of a second independent variable.

floor effect

an effect that occurs when scores on a dependent variable bunch up at the minimum score level; compare ceiling effect.

Belmont Report

an ethics code that provides the foundation for U.S. federal regulations governing research on human subjects.

randomized controlled trial (also called randomized clinical trial)

an experiment in which participants are randomly assigned to different conditions for the purpose of examining the effectiveness of an intervention.

between-subjects design

an experimental design in which different participants are assigned to each of the conditions in the experiment.

yoked control group

an experimental design in which each control group member is procedurally linked (i.e., "yoked") to a particular experimental group member whose behavior will determine how both of them are treated.

single-factor design

an experimental design that has only one independent variable.

factorial design

an experimental design that includes two or more independent variables and crosses (i.e., combines) every level of each independent variable with every level of all the other independent variables.

person x situation (or person x environment) factorial design

an experimental design that incorporates at least one subject variable along with at least one manipulated situational variable.

block randomization

an experimental procedure in which researchers conduct a round of all the conditions, then another round, then another, for as many rounds as needed to complete the experiment. Within each round, the order of conditions is randomly determined.

confounding variable

an extraneous factor that covaries with an independent variable in such a way that we can no longer determine which one has caused the changes in the dependent variable; a confounding variable provides a potential alternative explanation for the results.

case study

an in-depth analysis of an individual, social unit, event, or other phenomenon.

chi-square (X2) test for independence

an inferential statistical test most commonly used to determine whether two qualitative variables are independent or associated.

t test

an inferential statistical test often used to determine whether there is a statistically significant difference between the means of two groups of scores for the same variable.

chi-square (X2) goodness-of-fit test

an inferential statistical test used to determine the likelihood that an obtained pattern of results is consistent with the pattern expected from a hypothesized distribution.

open-ended question

an item, as in a questionnaire or survey, that asks participants to respond in their own terms.

closed-ended question

an item, as in a questionnaire or survey, that provides specific response options.

blind observation

an observational technique in which observers are kept unaware of (i.e., "blind" to) the hypotheses being tested and/or any key information about participants that relates to those hypotheses.

naturalistic observation

an observational technique in which researchers passively observe behavior in a natural setting.

undisguised observation

an observational technique in which the individuals being studied are aware that they are being observed; compare disguised observation.

disguised observation

an observational technique in which the individuals being studied are not aware that they are being observed; compare undisguised observation.

participant observation

an observational technique in which the observer becomes a part of the group or social setting being studied.

structured observation

an observational technique in which the researcher fully or partly configures the setting in which behavior will be observed.

skepticism

an outlook that questions the validity of claims before deciding whether to accept them.

variable

any factor or attribute that can assume two or more values.

positive correlation correlation

in which higher scores or levels of one variable tend to be associated with higher scores or levels of another variable.

observational research

research that encompasses different types of nonexperimental studies in which behavior is systematically watched and recorded.

correlational research (also called relational research)

research that involves examining potential associations between naturally occurring variables by measuring those variables and determining whether they are statistically related.

relational research

research that involves examining potential associations between naturally occurring variables by measuring those variables and determining whether they are statistically related. See correlational research.

quantitative research

research that relies primarily on numerical data and numerical (e.g., statistical) analysis to describe and understand behavior.

qualitative research

research that seeks to achieve a relatively holistic or thematic description and understanding of behavior, primarily through the nonstatistical analysis of data.

field study

research that takes place in a real-world ("field") setting.

empiricism

the process of acquiring knowledge directly through observation and experience; the philosophical viewpoint that all knowledge is derived from experience.

needs assessment

the process of determining whether there is a need for a social program and the general steps required to meet that need.

program diffusion

the process of implementing and maintaining effective programs in other settings or with other groups.

measurement

the process of systematically assigning values (numbers, labels, or other symbols) to represent attributes of organisms, objects, or events.

efficiency assessment in program evaluation

the process of weighing the program's benefits and effectiveness in relation to its costs to determine whether it is an efficient method for addressing the problem at hand.

qualitative variables

variables representing properties that differ in "type" (i.e., a type of attribute or quality), such as sex, religious affiliation, eye color, and marital status.

quantitative variables

variables representing properties that differ in amount (e.g., height, weight, degree of shyness, time spent learning a task, or blood alcohol levels on a Saturday night).

full replication

replication that includes all the conditions of the original study. See complete replication.

partial replication

replication that includes only some of the conditions of the original study.

Animal Welfare Act

U.S. federal law that regulates the use of warm-blooded vertebrates (except mice, rats, and birds) in scientific research.

Common Rule

U.S. federal policy that specifies ethics regulations for human subjects research.

matched-groups design

a between-subjects design in which each set of participants that has been matched on one or more attributes is randomly assigned the various conditions of the experiment.

independent-groups design (also called random-groups design)

a between-subjects design in which participants are randomly assigned to the various conditions of the experiment.

random-groups design

a between-subjects design in which participants are randomly assigned to the various conditions of the experiment. See independent-groups design.

collective case study

a case study in which each of several cases is studied in depth for the purpose of learning about a broader phenomenon.

quantitative case study

a case study in which researchers rely primarily on numerical assessments and analysis to describe and understand a case.

instrumental case study

a case study in which the case is analyzed in depth because it is an example of, or otherwise provides information about, a broader phenomenon.

intrinsic case study

a case study in which the case is examined in depth due to some inherent interest in learning about that particular individual or phenomenon.

cross-sectional research design (also called one-shot correlational study)

a descriptive research design in which each person in the study participates on one occasion and all variables are measured at that time; in developmental research, a study in which participants of different ages are compared at the same point in time; compare longitudinal research.

one-shot correlational study

a descriptive research design in which each person in the study participates on one occasion and all variables are measured at that time; in developmental research, a study in which participants of different ages are compared at the same point in time; compare longitudinal research. See cross-sectional research design.

one-group pretest-posttest design

a design in which a dependent variable is measured once before and once after a treatment occurs.

simple interrupted time-series design

a design in which a dependent variable is repeatedly measured at periodic intervals before and after a treatment.

simple interrupted time-series design with a nonequivalent control group

a design in which a series of pre- and posttreatment scores are obtained for a treatment group and a non-equivalent control group.

one-group posttest-only design

a design in which a treatment occurs and afterward the dependent variable is measured once.

switching replication design

a design in which one group receives a treatment and a nonequivalent group initially does not receive the treatment but is then exposed (i.e., "switched") to it at a later point in time.

posttest-only design with a nonequivalent control group

a design in which participants in one condition are exposed to a treatment, a nonequivalent group is not exposed to the treatment, and scores from both groups are obtained after the treatment ends.

pretest-posttest design with a nonequivalent control group

a design in which pre- and posttreatment scores are obtained for a treatment group and a nonequivalent control group.

cohort sequential research design

a design in which several cohorts are tested longitudinally.

relative frequency distribution

a distribution that depicts the proportion or percentage of times that each value occurs within a data set.

relative cumulative frequency distribution

a distribution that depicts the total proportion or percentage of cases that occur at or below (or, at or above) each value in a data set.

frequency distribution

a distribution that portrays how often each value of a variable occurs within a set of data.

cumulative frequency distribution

a distribution that portrays the total number of cases that occur at or below (or, at or above) each value in a data set.

American Psychological Association (APA) Ethics Code

a document that describes general ethical principles and specific ethical standards to guide psychologists' professional behavior.

moderator variable

a factor that alters the strength or direction of the relation between an independent and a dependent variable.

extraneous variable

a factor that is not the focus of interest in a particular study, but that could influence the outcome of the study if left uncontrolled.

within-subjects factorial design

a factorial design in which each participant engages in every condition.

between-subjects factorial design

a factorial design in which each subject engages in only one condition.

mixed-factorial design

a factorial design that includes at least one between-subjects variable and at least one within-subjects variable.

single-stage cluster sampling

a form of probability sampling in which all the participants in the randomly selected clusters are chosen to participate in the survey.

scatter plot (also called scattergram)

a graph in which data points portray the intersection of X and Y values.

histogram

a graph that uses bars to portray the distribution of a quantitative variable.

wait-list control group

a group of randomly selected participants who do not receive a treatment, but expect to and do receive it after treatment of the experimental group(s) ends.

law of parsimony

a guiding rule stating that explanations should use the minimum number of principles necessary to account for the greatest number of facts.

alternative hypothesis (Ha)

a hypothesis that is contrary to the null hypothesis; used in inferential statistical tests.

Institutional Animal Care and Use Committee (IACUC)

a legally mandated committee that reviews animal research proposals for compliance with federal regulations.

interviewer effects

aspects of the interviewer's presence that distort participants' responses.

nonresponse bias

bias that occurs when people who were selected but didn't participate in a survey would have provided significantly different answers (or other data) from those provided by participants.

observer bias

bias that occurs when researchers have expectations or other predispositions that distort their observations.

abstract

brief, one-paragraph summary of the report (typically mentions details about study purpose such as hypothesis, methodology, findings, and conclusions)

measures of dispersion (also called measures of variability)

calculations that assess how much the scores in a distribution are spread out; the range, variance, and standard deviation are three common measures of dispersion.

measures of central tendency

calculations that identify the typical values or "center" of a distribution of scores; the mode, mean, and median are three common measures of central tendency.

negative correlation

correlation in which higher scores or levels of one variable tend to be associated with lower scores or levels of another variable.

experimental condition

in an experiment, the circumstance in which participants receive the treatment or "active" level of the independent variable; see also experimental group.

sampling variability

chance fluctuations in the characteristics of samples that occur when randomly selecting samples from a population.

sampling error

chance fluctuations that introduce a degree of error when using sample statistics to estimate population parameters; see also margin of sampling error.

progressive effects

changes in participants' responses that result from their cumulative exposure to prior conditions.

instrumentation (as a potential confounding variable)

changes that occur in a measuring instrument during the course of data collection (e.g., pretest to posttest changes in the observer's criteria for rating depression).

dependent variable

in an experiment, the behavior or outcome that the researcher measures to determine whether the independent variable has produced an effect. In a cause—effect relation between two variables, the dependent variable is the presumed effect.

plausible alternative explanations

credible reasons for why something has occurred, that differ from our belief or conclusion about it.

demand characteristics

cues that influence participants' beliefs about the hypothesis being tested and the behaviors expected of them.

minimal risk

defined as risk in which "the probability and magnitude of harm or discomfort anticipated in the research are not greater in and of themselves than those ordinarily encountered in daily life or during the performance of routine physical or psychological examinations or tests" (U. S. Department of Health and Human Services, 2009, Section 46.102.i); compare at risk.

operationism

defining a concept in terms of the specific procedures (or "operations") used to represent it.

at risk

describes participants in a proposed study that involves more than minimal risk; compare minimal risk.

order effects (also called sequence effects)

effects that occur when participants' responses are affected by the order of the conditions to which they are exposed.

history (with regard to a study)

events that occur while a study is being conducted and that are not a part of the experimental manipulation or treatment.

Type Il error

failing to reject the null hypothesis when, in fact, the null hypothesis is false.

tenacity (as a method of knowing)

holding a belief simply because it is what has long been believed.

proximal (or proximate) causes

immediate causes; in a chain of interrelated events that lead to a given result, the events that are close to the result; compare distal causes.

main effect

in a factorial design, occurs when an independent variable has an overall effect on a dependent variable.

simple main effect

in a factorial experiment, the effect of one independent variable at a particular level of another independent variable.

Latin Square

in a single-factor experiment with n conditions, an n (number of positions in a series) x n (number of orders) matrix in which each condition will appear only once in each column and each row.

evidence-based treatments (also called empirically supported treatments)

interventions that scientifically controlled studies have demonstrated to be effective in treating specific conditions.

empirical knowledge

knowledge that is based on the senses—on experiences with the world.

quantitative analysis

mathematical analysis of data, which typically involves using statistics to aid in summarizing and interpreting those data.

ratio scale

measurement in which equal distances between values on the scale reflect equal differences in the amount of the attribute being measured and the scale has a true zero point.

observer rating and ranking scales

measures in which observers record their own quantitative judgments that evaluate participants' behavior or other characteristics.

physical trace

measures unobtrusive measures in which researchers examine traces of behavior that people create or leave behind. pie chart a circular graph that is divided into segments.

qualitative analysis

nonmathematical analysis of data, which often involves identifying, classifying, and describing different types of characteristics, outcomes, or behaviors.

contamination (in a study)

occurs when knowledge, services, or other experiences intended for one group are unintentionally received by another group (e.g., when future participants learn information from previous participants that they are not supposed to know until after data collection is completed).

internal replication

occurs when researchers follow up their initial study with one or more replications and present this series of studies in a single research report.

interaction (also called interaction effect) in a factorial design

occurs when the way in which an independent variable influences behavior differs depending upon the level of another independent variable.

carryover effects

order effects that occur when participants' responses in one condition are uniquely influenced by the particular condition or conditions that preceded it.

experimental group

participants who are exposed to a treatment or "active" level of the independent variable; see also experimental condition.

plagiarism

presenting someone else's work or ideas as one's own.

complete replication (also called full replication)

replication that includes all the conditions of the original study.

archival records

previously existing documents or other data that were produced independently of the current research.

respect

principle of a principle in the APA Ethics Code calling for psychologists to "respect the dignity and worth of all people, and the rights of individuals to privacy, confidentiality, and selfdetermination" (APA, 2010a, p. 3).

justice

principle of a principle in the APA Ethics Code calling upon psychologists to recognize that the benefits of their research, and of psychological science as a whole, should be made available to all persons.

nonmaleficence

principle of a principle in the APA Ethics Code stating that psychologists should be careful not to cause harm.

integrity

principle of a principle in the APA Ethics Code stating that psychologists should be honest and truthful, and should not engage in fraud.

fidelity

principle of a principle in the APA Ethics Code stating that psychologists should behave in a trustworthy manner.

responsibility

principle of a principle in the APA Ethics Code that calls for adhering to professional codes of conduct and not exploiting participants.

assent evidence

provided by a participant of willingness to participate in a study even though the participant might not be able to comprehend details of the study to the degree listed on the consent form.

random measurement error

random fluctuations in the measuring situation that cause the obtained scores to deviate from a true score.

Type I error

rejecting the null hypothesis when, in fact, the null hypothesis is true.

authority (as a method of knowing)

relying on other people as the source of our knowledge and beliefs.

distal causes

remote causes; in a chain of interrelated events that lead to a given result, the events that are remote from the result; compare proximal causes.

direct (or "exact") replication

replication in which the researchers follow the procedures used in the original study as closely as possible.

exact replication

replication in which the researchers follow the procedures used in the original study as closely as possible. See direct replication.

conceptual replication

replication that examines the same question investigated in the original study but operationalizes the constructs differently.

scales of measurement

rules for assigning scale values to measurements.

applied research

scientific inquiry that directly focuses on helping to solve or evaluate a specific real-world problem; compare basic research.

basic research

scientific inquiry that examines the fundamental nature of phenomena; compare applied research.

differential attrition

significantly different rates of or reasons for participants' discontinuing a study across the various conditions in that study.

inferential statistics

statistics that allow researchers to draw conclusions about a population on the basis of data from a sample.

descriptive statistics

statistics that organize and summarize a set of data.

behavioral coding

systems classifications of participants' responses into mutually exclusive categories; a component of many observational studies.

sensitivity (of a measure)

the ability of a measure to detect an effect that actually is present.

experimental control

the ability to (l) manipulate one or more independent variables; (2) choose the types of dependent variables that will be measured, and how and when they will be measured, so that the effects of the independent variables can be assessed; and (3) regulate other aspects of the research environment, including the manner in which participants are exposed to the various conditions in the experiment.

control

the ability to regulate research settings and procedures and to guide the application of scientific knowledge.

applied behavior analysis

the application of principles from the experimental analysis of behavior to socially significant problems.

mean

the arithmetic average of a distribution of scores.

deviation score

the arithmetic difference between each score in a distribution and the mean of that distribution (i.e., X — M).

variance

the average of the squared deviations about the mean; variance measures how much the scores in a distribution are spread out in relation to their mean. See also standard deviation.

target behavior

the behavior that a treatment is designed to change.

control condition in an experiment

the circumstance in which participants do not receive the treatment of interest or are exposed to a baseline level of an independent variable; see also control group.

risk/benefit ratio

the comparison of risks and benefits. To approve a study, an IRB first must be convinced that the researcher has minimized any scientifically necessary risks to participants; and, second, regardless of the level of risk, that such risk is outweighed by the study's potential benefits.

causal inference

the conclusion that variable X caused variable Y.

treatment phase (also called intervention phase) in applied research

the condition that involves the presentation of a specific treatment or other intervention; the experimental condition.

intervention phase

the condition that involves the presentation of a specific treatment or other intervention; the experimental condition. See treatment phase.

confidence level

the degree of confidence that a true population value resides within a particular margin of sampling error.

reliability (of a measure)

the degree of the consistency of measurement. replication the process of repeating a study to determine whether the original findings will be upheld.

criterion validity

the degree to which a measure predicts an outcome that it is expected to predict.

validity

the degree to which a measure truly assesses what it is claimed to assess.

accuracy (of a measure)

the degree to which a measure yields results that agree with a known standard.

interobserver reliability (also called interrater reliability)

the degree to which independent observers show agreement in their observations. It occurs, for example, when different raters using the same coding system agree in how they classify or otherwise score participants' responses.

ecological validity

the degree to which responses obtained in a research context generalize to behavior in natural settings; also refers to how well a research setting (e.g., tasks, procedures) corresponds to what people encounter in daily life.

construct validity

the degree to which the constructs (the conceptual variables) that researchers claim to be studying are, in fact, the constructs that they are manipulating and measuring.

content validity

the degree to which the items on a measure adequately represent the entire range or set of items that could have been appropriately included.

face validity

the degree to which the items on a measure appear to be reasonable.

statistical conclusion validity

the degree to which the statistical treatment of data is proper and the researchers' statistical conclusions are sound. statistically significant describes a result that is unlikely to be due to chance.

internal validity

the degree to which we can be confident that a study demonstrated that one variable had a causal effect on another variable.

placebo effect

the effect that occurs when participants' expectations about how a treatment will affect them influence their responses (on the dependent variable) to that treatment.

ceiling effect

the effect that occurs when scores on a dependent variable bunch up at the maximum score level; compare floor effect.

anonymity in a study

the fact that a participant's identity is unknown, even to the researcher.

confidentiality in a study

the fact that participants' identities will not be released without their consent, and data from the study will be reported in a way that does not identify individual participants.

external validity

the generalizability of the findings beyond the circumstances of the present study.

placebo control group

the group of participants in an experiment who do not receive the core treatment but are led to believe that they are (or may be) receiving it.

null hypothesis (Ho)

the hypothesis that is directly examined by a statistical test.

experimental analysis of behavior

the intensive study, under controlled conditions, of how environmental stimuli and consequences regulate an individual organism's behavior.

deception

the intentional withholding by researchers of information from potential participants that might influence their decision to provide informed consent (so-called passive deception) or intentionally misleading participants about some aspect of a study (so-called active deception).

selection interactions

the interaction of selection with another threat to internal validity.

attrition (also called subject loss)

the loss of participants in the course of a study when they fail to complete it.

subject loss

the loss of participants in the course of a study when they fail to complete it. See attrition.

independent variable

the manipulated variable in an experiment; a factor that the researcher manipulates, or systematically varies. In a cause-effect relation between two variables, it is the presumed causal factor.

median

the midpoint of a distribution.

mode

the most frequently occurring score in a distribution.

raw scores

the original individual scores obtained for a particular variable.

control group

the participants in an experiment who do not receive the treatment of interest or are exposed to a baseline level of an independent variable; see also control condition.

percentile rank

the percentage of scores in a distribution that fall below a particular score.

response rate (of a survey)

the percentage of those who participate in a survey out of all those who were selected to participate.

informed consent

the principle that prospective participants have the right to make a voluntary, informed decision about whether or not to participate in a study.

convergent validity

the principle that scores on a measure should correlate highly (i.e., converge) with scores on other measures of the same construct.

discriminant validity

the principle that scores on a measure should not correlate too strongly with scores on measures of other constructs.

alpha (a) level

the probability level below which a result is considered to be sufficiently unlikely to be due to chance.

significance level (also called alpha (a) level)

the probability level below which a result is considered to be sufficiently unlikely to be due to chance.

power (of a statistical test)

the probability of correctly rejecting the null hypothesis (Ho); that is, rejecting Ho when it indeed is false. power analysis examines the relation between power, effect size, and sample size for a given statistical test and alpha level.

probability value (also called p value)

the probability that an outcome or one more extreme is due simply to chance.

self-selection

the selection that results when participants place themselves into a sample rather than being chosen for inclusion by a researcher.

operational definition

the specific procedures (i.e., the specific "operations") used to measure or manipulate a variable in a particular study; refers to defining a variable in terms of the procedures used to measure or manipulate it.

standard deviation

the square root of the variance; the standard deviation measures how much the scores in a distribution are spread out in relation to their mean as expressed in the original units of measurement. See also variance.

standard error of the mean (SEM)

the standard deviation of a sampling distribution of the mean.

regression to the mean

the statistical concept that when two variables are not perfectly correlated (e.g., scores on a pretest and posttest), more extreme scores on one variable will be associated overall with less extreme scores on the other variable. In experimental design, regression to the mean refers to the fact that when a group is selected because of their above- or below-average scores on a measure, the group's average score on a retest (or on another related measure) will tend to regress toward (i.e., become closer to) the mean score of the overall population.

sum of squares (SS)

the sum of squared deviations of scores from the mean of their distribution.

confirmation bias (also called congeniality bias)

the tendency to selectively seek information that supports one's views and avoid disconfirming information.

congeniality bias

the tendency to selectively seek information that supports one's views and avoid disconfirming information. See confirmation bias.

reason

the use of logic and rational (i.e., intellectually sound) argument to reach a conclusion about how things "must be."

program evaluation

the use of research methods to assess the need for, and the design, implementation, and effectiveness of, a social intervention.

multistage sampling

the use of two or more stages to select progressively smaller samples.

maturation

the ways in which people naturally change over time, independent of their participation in a study.

Three Rs in nonhuman animal research

three general principles to which many federal ethical standards and regulations pertain: reduction, refinement, and replacement.

hypothetical construct

underlying characteristics or processes that are not directly observed but instead are inferred from measurable behaviors or outcomes.

experimenter expectancy effects

unintentional ways in which researchers influence their participants to respond in a manner consistent with the researchers' hypothesis.

deductive reasoning

using a general principle to reach a more specific conclusion.

inductive reasoning

using specific facts to reach a general conclusion or general principle.

discrete variables

variables for which no intermediate values are possible between any two adjacent values (e.g., number of children).

continuous variables

variables for which, in principle, intermediate values are possible between any two adjacent scale values.