Key science skills and research methods

accuracy how close a measure relates to the ‘true’ value of the quantity being measured

aim a statement outlining the purpose of the investigation

anecdote an informal verbal report of an event that has been casually observed

bar chart a graph which uses a series of separate bars or rectangles next to, but not touching one another, to enable comparisons of different categories of data

behaviour any action made by a living person (or animal) that can be observed or measured

beneficence in relation to research ethics, the commitment to maximising benefits and minimising the risks and harms involved in taking a particular position or course of action

between subjects an experimental design in which each participant is assigned to only one group or condition and provides only one score for data analysis; also called independent groups and between groups

biased sample a research sample that does not adequately represent the key characteristics of its population

case study an intensive, in-depth investigation of some behaviour, event or problem of interest in a single individual, group, organisation or situation

conclusion in relation to research, a decision about what the results obtained from a research study mean

confidentiality ethical guideline for research involving the privacy, protection and security of a participant’s personal information, including results

confounding variable a variable other than the independent variable that has affected the results (the dependent variable) and whose effect(s) cannot be separated from that of the independent variable, thereby providing an alternative explanation(s) for the results; compare with extraneous variable

control condition in an experiment, the standard against which the experimental condition can be compared; involves the control group who are not exposed to the independent variable

control group the group in an experiment not exposed to the independent variable

controlled experiment an experimental investigation of the relationship between an independent variable and a dependent variable, whilst controlling all other variables

controlled variable a variable that is considered to have an effect on the dependent variable so it is held constant to remove its potential effect

correlation the degree of a relationship between two variables

correlational study a research method used to investigate the relationship between variables without any control over the setting in which the relationship occurs or any manipulation by the researcher

correlation coefficient a statistic used to describe the relationship between two variables

counterbalancing systematically changing the order of treatments or tasks for participants in a ‘balanced’ way to ‘counter’ the unwanted effects on performance of any one order

data information collected through research; see also primary data, secondary data, quantitative data and qualitative data

debriefing ethical guideline requiring that at the end of the experiment, the participant leaves understanding the experimental aim, results and conclusions including wellbeing checks where appropriate

deception (in research) when a researcher deliberately conceals the true purpose of the experiment from participants by misleading or misinforming them

demand characteristic a cue in an experiment that may influence or bias a participant’s response, thereby distorting the results

dependent variable (DV) the variable the researcher measures, after selecting the independent variable that is assumed to have an effect on the independent variable

double blind procedure a procedure in which both the participants and the experimenter(s) interacting with them are unaware of the conditions to which the participants have been allocated; compare with single blind

ethical concept moral or philosophical idea that focuses on the concept of what is right and wrong

ethical guideline enforceable standards that psychologists use to guide ethical decisions in practice, research, and education

ethics in relation to research, standards that guide researchers to identify good, desirable or acceptable behaviour

experimental condition the condition in an experiment in which participants are exposed to the independent variable; involves the experimental group; sometimes used to mean any or all groups or conditions in an experiment, including the control group (or conditions)

experimental group the group in an experiment exposed to the independent variable

experimenter effect any influence on the results produced by the person carrying out the research; also called experimenter bias

external validity the extent to which the results obtained for a study can be applied beyond the sample that generated them, specifically to individuals in a different setting and over time; compare with internal validity

extraneous variable any variable other than the independent variable that can cause a change in the dependent variable and therefore affect the validity of the results in an unwanted way; compare with confounding variable

field experiment a psychological experiment that is conducted outside the laboratory in a ‘real-world’ setting

fixed-response question a question that presents a number of fixed alternative answers from which participants are required to choose; also called fixed alternative question or fixed-choice question

free-response question a question which allows participants to answer entirely as they want to; also called open ended question

generalisation in research, a decision about how widely the findings of an investigation can be applied, particularly to other members of the population from which the sample was drawn

independent variable (IV) variable that is manipulated (controlled, selected or changed) in order to test its effects on the dependent variable

informed consent ethical guideline requiring that participants understand the nature and purpose of the experiment, including potential risks, before agreeing to participate

integrity in relation to research ethics, the commitment to searching for knowledge and understanding, the honest reporting of all sources of information and results, whether favourable or unfavourable, in ways that permit scrutiny and contribute to public knowledge and understanding

internal validity the extent to which an investigation actually investigated what it set out to investigate and/or claims to have investigated; compare with external validity

interview asking questions to obtain self-report data

justice in relation to research ethics, moral obligation to ensure that there is fair consideration of competing claims; that there is no unfair burden on a particular group from an action; and that there is fair distribution and access to the benefits of an action

laboratory experiment a psychological experiment that is conducted within a laboratory setting

line graph uses points connected by lines to show how one variable changes as another variable changes

mean the arithmetical average of all the individual scores (or values) in a set of scores

measure of central tendency a score that indicates the central or average value of a set of scores; see also mean, median, mode

measure of variability a statistic that indicates how widely scores (or values) are distributed or scattered around the central point

median the middle score (or mid-point) of a set of scores (or values)

mental process generally refers to a person’s thoughts, feelings and other mental activities that cannot be directly observed; compare with behaviour

mixed design an experimental design that combines the features of the within subject and between subjects designs

mode the most frequently occurring score (or value) in a set of scores

model a body of interrelated concepts (‘ideas’) that attempt to explain interrelated observations and make predictions about future events; also called theory; in observational learning who or what is being observed.

naturalistic observation when the researcher views and records behaviour of interest in the natural, ‘real life’ environment where it would ordinarily occur

negative correlation when two variables change in opposite directions — as one variable increases, the other variable tends to decrease (and vice versa)

non-maleficence in relation to research ethics, avoiding the causations of harm

non-participant observation when the researcher tries to conceal their presence so that their observations are made in entirely inconspicuous manner

objective data information that is observable, measurable, verifiable and free from the personal bias of the researcher; compare with subjective data

observational study collection of data by carefully watching and recording behaviour as it occurs without any intervention or manipulation of the behaviour being observed

operationalise define how variables will be manipulated as measured in a research investigation

opinion a point of view that is not necessarily based on verifiable evidence and can be disputed

order effect when performance on the dependent variable is influenced by the specific order in which an experimental task is presented rather than the independent variable

outlier an extreme measurement, one that significantly differs from all others in a data set

participant observation when a trained investigator studies a pre-existing group by joining it as a member, while avoiding a conspicuous role that would change what occurs in the group and bias the data

participant variable a personal characteristic of a research participant that could influence their responses

percentage a statistic that expresses a number as a proportion (or fraction) of 100

personal error a fault or mistake by the researcher; also called human error

placebo a fake treatment that is like the independent variable treatment but which is actually neutral or has no known effect

placebo effect when there is a change in a participant’s behaviour due to their belief that they are receiving some kind of experimental treatment and they respond in accordance with that belief, rather than to the effect of the independent variable

population in relation to research, the entire group of research interest from which a sample is drawn

positive correlation when two variables change in the same direction

precision how closely a set of measurement values agree with each other

primary data information collected directly by the researcher (or through others) for their own purpose; compare with secondary data

qualitative data non-numerical information involving the ‘qualities’ or characteristics of a participant’s experience of what is being studied

quantitative data numerical information on the ‘quantity’ or amount of what is being studied

questionnaire data collection tool with a written set of questions or other prompts designed to collect self-report data

random allocation procedure used to place participants in experimental and control groups (or conditions) so that they are as likely to be in one group as the other; ensures uniform distribution of participant characteristics; also called random assignment

random error an error due to some chance factor or chance variation in a measurement

random sampling sample selection technique that ensures every member of the population of research interest has a genuinely equal chance of being selected to be part of the sample; helps achieve a representative sample

rating scale data collection tool with fixed-response questions or statements for which participants rank each item by selecting from a number of choices

reliability the extent to which a measure produces results that are consistent, dependable and stable

repeatability the degree to which a specific research investigation obtains similar results when it is conducted again under the same conditions on all occasions

representative sample a sample that closely resembles the population from which it is drawn in key characteristics

reproducibility how close the results are to each other when an investigation is replicated under changed conditions

research hypothesis a testable prediction of the relationship between two or more variables

research method a particular way of conducting a research study or investigation to collect accurate and reliable data on a question or problem of interest

research question a specific inquiry which the research seeks to provide a response to

respect in relation to research ethics, consideration of, and due regard to, the extent to which living things have an intrinsic value and/or instrumental value

sample the subset or part of the population that is selected for a research investigation

sampling process of selecting participants from a population of research interest; see also random sampling, stratified sampling and convenience sampling

sampling bias occurs when some members of a population are systematically more likely to be selected in a sample than others

scatter plot a graph that shows the scores (or other values) on two different variables measured in a correlational study

secondary data information that was not collected directly by the current researcher but was collected at an earlier time by someone else; compare with primary data

self-report a participant’s responses to questions presented by the researcher

simulation study reproducing situations of research interest in a realistic way to investigate the behaviour and/or mental processes of individuals in that environment

single blind procedure a procedure in which participants are unaware of (‘blind’ to) the experimental condition they are in

situational variable an external factor associated with the experimental setting that may influence participant responses and therefore the results

standard deviation statistic that summarises how far scores within a set of scores spread out, or deviate, from the mean for those scores

stratified sampling a sampling technique involving sampling from different subgroups in the same proportions as they occur in the population of interest

subjective data information that is based on personal opinion, interpretation, point of view or judgment; compare with objective data

systematic error a measurement error produced by some factor that consistently favours one condition rather than another

theory a body of interrelated concepts (‘ideas’) that attempt to explain interrelated observations and make predictions about future events; also called model

triple blind procedure a procedure in which the participants, experimenters, and research assistants only doing data analysis are all unaware of the particular experimental conditions

uncertainty when something (e.g. a particular outcome) is not accurately or precisely known

voluntary participation ethical guideline requiring that no coercion or pressure is put on the participant to partake in an experiment, and they freely choose to be involved

withdrawal right ethical guideline requiring a participant being able to discontinue their involvement in an experiment at any time during or after the conclusion of an experiment

validity the extent to which a measure accurately measures what it is supposed to be measuring; see also internal validity and external validity

variable something in which individuals, animals or objects differ among themselves, can change in amount or kind, and is measurable

variability the degree to which measures or values differ from one another

within subjects experiment an experimental design in which each participant is in both the experimental and control groups or all the treatment conditions (if there is no control group)

zero correlation no relationship between two variables