research methods definitions

Abstract

The abstract is the first section in a psychological report or journal. It includes a summary of the aims, hypothesis, method, results and conclusions, and thus provides an overview of the entire report.

Aim

The aim of a study is a general statement that explains the purpose of the research.

Bar Chart

A bar chart is used to show frequency data for discrete (separate) variables. For example, bar charts are used to plot mean scores for conditions A & B separately.

Behavioural Categories

When conducting structured observations, psychologists have to decide which specific behaviours should be examined. They need to operationalise the behaviour through the use of behavioural categories. This involves breaking the target behaviour (e.g. aggression) into components that can be observed and measured (e.g. hitting, kicking).

Bias

Bias means to influence, typically in an unfair direction. In the context of sampling, it means that certain groups may be under- or over-represented in the sample. This then limits the extent to which the findings of the study can be generalised.

BPS Code of Ethics

The BPS Code of Ethics is a document produced by the British Psychological Society, which details the general principles that apply to the use of human participants in all research contexts. It focuses on four major principles: respect, competence, responsibility and integrity.

Case Studies

Case studies are very detailed investigations of an individual or small group of people, usually regarding an unusual phenomenon or biographical event of interest to a research field. Due to a small sample, researchers using the case study method can conduct an in-depth analysis of the individual/group  under examination.

Chi-Squared

The chi-squared test is a non-parametric statistical test of difference or association that allows researchers to see if their results are significant. It is used for studies that have an independent groups design, where the data collected is nominal (in categories).

Closed Questions

Closed questions, in a questionnaire or interview, restrict the participant to a predetermined set of responses and generate quantitative data.

Coding: Content Analysis

Coding is when the researcher places qualitative data into categories. For example, if the researcher wanted to examine how males and females are portrayed in TV advertisements, they could create a list of categories (e.g. product user, product voice-over) and then count how many occurrences there were, for each gender in each category.

Concurrent Validity

Assessing concurrent validity involves comparing a new test with an existing test (of the same nature) to see if they produce similar results. If both tests produce similar results, then the new test is said to have concurrent validity.

Content Analysis

Content analysis is a method used to analyse qualitative data (non-numerical data). In its most common form, it is a technique that allows a researcher to take qualitative data and to transform it into quantitative data (numerical data). The technique can be used for data in many different formats, for example, interview transcripts, film, and audio recordings.

Correlation Co-Efficient

Psychologists use a statistic called a correlation co-efficient to measure the strength of a correlation (the relationship between two or more variables). A correlation coefficient can range between -1.0 (perfect negative) and +1.0 (perfect positive).

Correlational Study

A correlational study is a non-experimental method used to measure how strong the relationship is between two or more variables. There are two types of correlation: positive correlation (as one variable increases/decreases, so the other variable increases/decreases); and negative correlation (as one variable increases, so the other variable decreases). Psychologists use a statistic called a correlation coefficient to measure this strength.

Counterbalancing

Counterbalancing is a technique used to deal with order effects when using a repeated measures design. With counterbalancing, the participant sample is divided in half, with one half completing the two conditions in one order and the other half completing the conditions in the reverse order. E.g., the first 10 participants would complete condition A followed by condition B, and the remaining 10 participants would complete condition B and then A. Any order effects should be balanced out by this technique.

Critical Values

Critical values are a numerical value which researchers use to determine whether or not their calculated value (from a statistical test) is significant. Some tests are significant when the observed (calculated) value is equal to or greater than the critical value, and for some tests the observed value needs to be less than or equal to the critical value.

Demand Characteristics

Demand characteristics occur when the participants try to make sense of the research and act accordingly to support the aim of the research. Demand characteristics are an issue, as the participants may behave in a way to support the hypothesis, making the results less valid. Conversely, the participant may deliberately try to disrupt the results, a phenomenon known as the 'screw-you' effect.

Dependent Variable

In an experiment, the dependent variable (DV) is the variable that the researcher measures. It is the variable that is affected by the manipulation of the independent variable (IV).

Descriptive Statistics

Descriptive statistics analyse data to help describe, show or summarise it in a meaningful way. Examples are measures of central tendency and measures of dispersion.

Directional Hypothesis

A directional hypothesis is a one-tailed hypothesis that states the direction of the difference or relationship (e.g. boys are more helpful than girls).

Discussion

The discussion is the section in a report of an investigation where the researcher interprets the results of the study; makes criticism of the methodology used; considers the implications of the results for future research, and suggests real-world applications.

Ecological Validity

Ecological validity is a type of external validity that refers to the extent to which the findings can be generalized to a real-life setting.

Empirical Method

An empirical method involves the use of objective, quantitative observation in a systematically controlled, replicable situation, in order to test or refine a theory.

Event Sampling

Event sampling is used to sample behaviour in observational research. It is where an observer records the number of times a certain behaviour occurs.

Experimental Design

Experimental design describes the way participants are allocated to experimental groups. Types of experimental design include repeated measures, independent groups, and matched pairs designs.

Extraneous Variable

Extraneous variable (EV) is a general term for any variable, other than the IV, that might affect the results (the DV). Where EVs are important enough to cause a change in the DV, they become confounding variables.

Face Validity

Face validity is a simple way of assessing whether or not something measures what it claims to measure, which is concerned with its face value. e.g. does an I0 test look like it tests intelligence? This is often assessed by consulting specialists within that particular area.

Falsifiability

Falsifiability is an important feature of science. It is the principle that a proposition or theory could only be considered scientific if in principle it was possible to establish it as false. One of the criticisms of some branches of psychology, e.g. Freud's theory, is that they lack falsifiability.

Field Experiment

Field experiments are carried out in natural conditions, in which the researcher manipulates the independent variable (IV) to measure the effect on the dependent variable (DV).

Generalisation

Generalisation is the application of the results from a study, to the wider target population. It is based on the assumption that the findings from the original sample will be the same for everyone else in the target population.

Histogram

Histograms are a type of graph used for continuous data (e.g. age). There should be no space between the bars, because the data is continuous (e.g. 1-9, 10-19, 20-29, etc.)

Hypothesis

A hypothesis is a testable prediction about the variables in a study. The hypothesis should always contain the independent variable (IV) and the dependent variable (DV). A hypothesis can be directional (one-tailed) or non-directional (two-tailed).

Hypothesis Testing

Hypothesis testing is an important feature of science, as this is how theories are developed and modified. A good theory should generate testable predictions (hypotheses), and if research fails to support the hypotheses, then this suggests that the theory needs to be modified in some way.

Independent Groups

Independent groups design is an experimental design where different participants are used in each condition of the experiment.

Random allocation should be used to decide to which condition each participant should be allocated, as this ensures that each participant has an equal chance of being assigned to one group or another.

Independent Variable

In an experiment, the independent variable (IV) is the variable that the researcher manipulates and is assumed to have a direct effect on the dependent variable (DV).

Inter-Observer Reliability

It is very important to establish inter-observer reliability when conducting observational research. It refers to the extent to which two or more observers are observing and recording behaviour in the same way.

Interval

Interval level data is data measured in fixed units with equal distance between points on the scale. For example, temperature measured in centigrade.

Interviews

Interviews are a type of self-report technique that involve an interviewer asking questions (generally on a one-to-one basis) and recording responses. There are different types of interviews: structured (where the interviewer has a set list of questions with which to lead the conversation and a framework which will be rigidly adhered to); semi-structured (where the interviewer may have a list of topics or questions, but has extra flexibility to develop the conversation further, should participant responses lead to deeper/more detailed discussion); and unstructured (which are more like a conversation with no set questions).

Introduction

The introduction is the section in a report/journal where the researcher reviews previous research (theories and studies) to provide background information and a rationale for the current research. It should be structured like a funnel (moving from the general to the specific) so that it leads logically to the aims and hypotheses of the current study.

Investigator Effects

Investigator effects are where a researcher (consciously or unconsciously) acts in a way to support their prediction. This can be a particular problem when observing events that can be interpreted in more than one way. (For example, one researcher might interpret children fighting as an act of violence, while another might interpret this as rough and tumble play).

Laboratory Experiment

Laboratory experiments are conducted under controlled conditions, in which the researcher manipulates the independent variable (IV) to measure the effect on the dependent variable (DV).

Levels of Measurement

In psychology, there are different ways that variables can be measured and psychologists typically group measurements into one of four scales: nominal, ordinal, interval or ratio. The simplest level of measurement is nominal data (frequency count data), followed by ordinal (scores in rank order), then interval (a continuous scale with no absolute zero) and finally, ratio (a continuous scale with an absolute zero).

Mann-Whitney

The Mann-Whitney test is a non-parametric statistical test of difference that allows psychologists to determine if their results are significant. It is used in studies that have an independent groups design, where the data collected is at least ordinal.

Matched Pairs

Matched pairs design is an experimental design where pairs of participants are matched in terms of key variables, such as age and I0. One member of each pair is then placed into the experimental group and the other member into the control group.

Mean

The mean is a measure of central tendency that is calculated by adding all of the scores in a data set and dividing by the total number of scores. It is the most sensitive measure of central tendency as it includes all of the scores in its calculation. However, it is easily distorted by extreme values.

Measures of Central Tendency

Measures of central tendency are descriptive statistics that depict the overall 'central' trend of a set of data. There are three key measures: mean, median and mode.

Measures of Dispersion

Measures of dispersion describe the spread of data around a central value (mean, median or mode). They tell us how much variability there is in the data. There are two measures of dispersion: range (where you subtract the lowest score from the highest score) and standard deviation (SD) - which calculates the spread of scores around the mean.

Median

The median is a measure of central tendency that is calculated by finding the middle score when the data set is placed in numerical order. If there is an even number of data, then the median is the sum of the two middle numbers, divided by two. The median is not affected by extreme scores but is less sensitive than the mean, as not all scores are included in the calculation.

Meta-Analysis

A meta-analysis is where researchers combine the findings from multiple studies to draw an overall conclusion.

Method

The method is the section of a report/journal that contains a detailed description of the methodology. This needs to be detailed enough to allow someone else to replicate the study, and includes details of the design, participants, apparatus/materials, procedure and ethical considerations.

Mode

The mode is a measure of central tendency which is calculated by reporting the most frequently occurring number in a data set. While it is easy to calculate, it is of little use where the data set includes many different values of the same frequency, i.e. there are many modes.

Natural Experiment

Natural experiments are carried out in natural conditions; however, the research is unable to manipulate the IV and therefore examines the effect of a naturally occurring variable on the dependent variable (DV).

Negative Correlation

A negative correlation occurs when two variables are related and as one variable increases the other decreases. For example, you might expect to find a negative correlation between the school performance of high school students and the amount of time they are absent from school.

Nominal

Nominal level data is frequency or count data that consists of the number of participants falling into categories. (e.g. 7 people passed their driving test the first time and 6 people didn't.)

Non-Directional Hypothesis

A non-directional hypothesis is a two-tailed hypothesis that does not predict the direction of the difference or relationship (e.g. girls and boys are different in terms of helpfulness).

Normal Distribution

A normal distribution is an arrangement of data that is symmetrical and forms a bell-shaped pattern where the mean, median and/or mode falls in the centre at the highest peak.

Objectivity

Objectivity is a feature of science, and if something is objective it is not affected by the personal feelings and experiences of the researcher. The researcher should remain value-free and unbiased when conducting their investigations.

Observational Study

An observational study is one that involves observing (watching) actual behaviours, which are subsequently scored. There are many types of observations, such as naturalistic and controlled observations; covert and overt observations; participant and non-participant and structured and unstructured observations.

Open Questions

Open questions are used in questionnaires and interviews. They do not have fixed responses, and so they allow the participant to answer however  they wish. They generate qualitative data.

Operationalisation

Operationalisation is the term used to describe how a variable is clearly defined by the researcher. The term operationalisation can be applied to independent variables (IV), dependent variables (DV) or co-variables (in a correlational design).

Opportunity Sampling

Opportunity sampling is a sampling technique used to select participants from a target group to take part in a research study. It consists of the researcher selecting anyone who is available and willing to take part in the study.

Ordinal

Ordinal level data is data that is presented in rank order (e.g. places in a beauty contest, or ratings for attractiveness).

Paradigm

A paradigm consists of the basic assumptions, ways of thinking, and methods of study that are commonly accepted by members of a discipline or group.

Paradigm Shift

A paradigm shift, as identified Thomas Kuhn (1962), is an important change in the basic concepts and experimental practices of a scientific discipline. It is a change from one way of thinking to another and is also referred to as 'scientific revolution'. Examples of paradigm shifts are the movement of scientific theory from the Ptolemaic system (the earth at the centre of the universe) to the Copernican system (the sun at the centre of the universe), and the movement from Newtonian physics to the theory of relativity and to quantum physics.

Pearson's r

The Pearson's r test is a parametric statistical test of correlation that allows a psychologist to determine significance. It is used in correlational research, where the data meets the requirements for a parametric test (level of measurement is interval or better, data is drawn from a population that has a normal distribution, and the variances of the two samples is not significantly different).

Peer Review

Peer review is a process that takes place before a study is published to check the quality and validity of the research, and to ensure that the research contributes to its field. The process is carried out by experts in that particular field of psychology.

Percentages

Percentages are a way of summarising nominal level data (frequencies in categories). A percentage is a portion of a whole expressed as a number between 0 and 100 (instead of as a fraction).

Pilot Studies

Pilot studies are small-scale prototypes of investigations to find out if there are any problems with the experimental design; instructions for participants; and measuring instruments (including the behavioural categories in observational research and questions when using questionnaires). After conducting a pilot study, the researcher is able to make any necessary modifications before the actual study is carried out.

Positive Correlation

A positive correlation occurs when two variables are related and as one variable increases/decreases the other also increases/decreases (i.e. they both move in the same direction). For example, you might expect to find a positive correlation between height and shoe size.

Primary Data

Primary data refers to data that has been collected directly by the researcher, solely for the purpose of their investigation.

Probability

Probability and significance are very important in relation to statistical testing. Probability refers to the likelihood of an event occurring. It can be expressed as a number (0.5) or a percentage (50%). Statistical tests allow psychologists to work out the probability that their results could have occurred by chance, and in general psychologists use a probability level of 0.05. This means that there is a 5% probability that the results occurred by chance.

Psychology and the Economy

The implications of psychological research for the economy are concerned with how the knowledge and understanding gained from psychological research (theories and studies) may contribute towards our economic prosperity. For example, if more effective treatments can be developed for psychological health problems, then this means that people will be able to return to work and this reduces the burden on the employers, NHS and tax payer.

Qualitative Data

Qualitative data is non-numerical language-based data collected through interviews, open questions and content analysis. It allows researchers to develop insights into the nature of subjective experiences, opinions and feelings.

Quantitative Data

Quantitative data is numerical data that can be statistically analysed. Experiments, observations, correlations and closed/rating scale questions from questionnaires all produce quantitative data.

Quasi Experiment

Quasi-experiments contain a naturally occurring IV. However, in a quasi-experiment the naturally occurring IV is a difference between people that already exists (i.e. gender, age). The researcher examines the effect of this variable on the dependent variable (DV).

Questionnaire

Questionnaires are a type of 'self-report' technique, where participants fill in the answers for themselves, providing information on their thoughts, feelings and behaviours.

Random Allocation

Random allocation of participants to experimental and control conditions is an extremely important process in research. Random allocation greatly decreases systematic error, so individual differences in responses or ability are far less likely to affect the results.

Random Sampling

Random sampling is a sampling technique where every member of the target population has an equal chance of being selected. This involves identifying everyone in the target population and then selecting the number of participants you need, in a way that gives everyone an equal chance of being selected (e.g. pulling names from a hat).

Randomisation

Randomisation is used in the presentation of trials in an experiment to avoid any systematic errors that might occurs as a result of the order in which the trials take place.

Range

The range is a measure of dispersion. It is the distance between the lowest and the highest value in a set of scores.

Referencing

Referencing is an important aspect of psychological reports/journals. The reference section of a journal includes full details of any sources, such as journal articles or books, that are used when writing a report. There is a set format depending on whether the information comes from a book, journal article etc. and there are different conventions for references (e.g. Harvard, APA, etc.)

Related t-test

The related t-test is a parametric statistical test of difference that allows psychologists to assess significance. It is used in studies with a repeated measures or a matched pairs design, where the data meets the requirements for a parametric test (level of measurement is interval or better, data is drawn from a population that has a normal distribution, the variances of the two samples are not significantly different).

Reliability

Reliability refers to the consistency of research study or measuring test. Reliability can be divided into two categories: internal and external reliability. Internal reliability describes the internal consistency of a measure, such as whether the different questions (known as 'items') in a questionnaire are all measuring the same construct. External reliability assesses consistency of a measure from one use to another. For example, if a participant took an I0 test one year, and then took the same test a year later and gained a very similar score, this would show external reliability.

Repeated Measures

Repeated measures design is an experimental design where the same participants take part in each condition of the experiment. This means that each condition of the experiment uses the same group of participants.

Replicability

Replicability is an important feature of science. It means that a study should produce the same results if repeated exactly, either by the same researcher or by another.

Results

The results are a section in a report of an investigation where the researcher includes details about what they found in their investigation. It includes descriptive statistics (e.g. summary tables, graphs, measures of central tendency and dispersion) and inferential statistics (e.g. results of statistical tests, including calculated values and significance levels). If qualitative research has been conducted, the results section would involve description of the categories and themes, along with examples.

Sampling

Sampling involves selecting participants from a target group/population. The target group/population is the desired population subgroup to be studied, and to which the research findings will be generalised. A target population is usually too large to study in its entirety, so sampling techniques are used to choose a representative sample from the target group.

Scattergram

A scatter graph is a graphical display that shows the correlation or relationship between two sets of data (or co-variables) by plotting dots to represent each pair of scores. A scatter graph indicates the strength and direction of the correlation between the co-variables.

Secondary Data

Secondary data is information that someone else has collected e.g. the work of other psychologists that has been published in journals or government statistics. They are sometimes used by other researchers, as they are often cheaper and more convenient than gathering one's own primary data.

Semi-Structured Interview

Semi-structured interviews contain mostly prepared questions that can be supplemented with additional questions. The interviewer can deviate from the original questions and therefore this type of interview typically produces rich qualitative data.

Sign Test

The sign test is a non-parametric statistical test of difference that allows a researcher to determine the significance of their investigation. It is used in studies that have used a repeated measures design, where the data collected is nominal.

Significance

If the statistical tests show that there is a less than a 5%, 2.5%, 1% (whatever level has been chosen) probability that the results were obtained by chance, then these results are said to be significant, and show a significant difference, or correlation, depending on what was being tested. The null hypothesis is then rejected.

If the statistical tests show that there is more than this probability that the results were obtained by chance, then they are said to be not significant, and there is no significant difference or correlation. In this case the null hypothesis is rejected.

Skewed Distribution

A skewed distribution is one where frequency data is not spread evenly (i.e. normally distributed); the data is clustered at one end. Data that is positively skewed has a long tail that extends to the right. Data that is negatively skewed have a long tail that extends to the left. As a general rule, when data is skewed to the right (positively skewed), the mean will be greater than the median and when data is skewed to the left (negatively skewed), the median will typically be greater than the mean.

Spearman's rho

Spearman's rho is a non-parametric statistical test of correlation that allows a researcher to determine the significance of their investigation. It is used

in studies that are looking for a relationship, where the data is at least ordinal.

Standard Deviation

Standard deviation is a measure of dispersion that shows the spread of scores around the mean. The greater the standard deviation the great the spread of scores around the mean.

Standardisation

Standardisation refers to the process in which procedures used in research are kept the same. Great attention is taken to keep all elements of a procedure identical. Under these circumstances, changes in data can be attributed to the IV. In addition, it is far more likely that results will be successfully replicated on subsequent occasions.

Statistical Tables

Statistical tables provide information to help psychologists make decisions in relation to the significance of their results. Statistical tables contain 'critical values' that are used when assessing significance.

Stratified Sampling

Stratified sampling is a sampling technique where the researcher divides or 'stratifies' the target group into sections, each representing a key group (or characteristic) that should be present in the final sample. For example, if a class has 20 students, 18 male and 2 female, and a researcher wanted a sample of 10, the sample would consist of 9 randomly chosen males and 1 randomly chosen female, to represent this population.

Structured Interview

Structured interviews are a type of interview where the questions are decided in advance and asked in the same order for each interviewee.

Systematic Sampling

Systematic sampling is a sampling technique that uses a predetermined system to select the participants from a target group. For example, every fourth person in a list could be used in the sample. It differs from random sampling in that it does not give an equal chance of selection to each individual in the target group.

Tables

Tables are a way of presenting quantitative data in a summary format. When tables appear in the results section of a report, they normally do not show raw scores, but instead show descriptive statistics (e.g. measures of central tendency, measures of dispersion).

Temporal Validity

Temporal validity is a type of external validity that refers to the validity of the findings in relation to the progression of time. For example, do the findings of conformity research (e.g. Asch, 1951) still apply today?

Test-Retest

Test-retest is a way of assessing the external reliability of a research tool. It involves presenting the same participants with the same test or questionnaire on two separate occasions, and seeing whether there is a positive correlation between the two.

Thematic Analysis

Thematic analysis is a method for analysing qualitative data that involves identifying and reporting patterns within the material to be analysed. The material to be analysed might be a diary, TV advertisements, or interview transcripts.

Theory Construction

Theory construction is an important feature of any science. In psychology, a theory is a proposed explanation for the causes of behaviour. To be scientific, a theory needs to be a logically organized set of propositions that defines events, describes relationships among events, and explains and predicts the occurrence of events. A scientific theory should also guide research by offering testable hypotheses that can be rigorously tested.

Time Sampling

Time sampling is a method of sampling behaviour in an observation study and is where an observer records behaviour at prescribed intervals. For example, every 10 seconds.

Type I Error

A type I error is a false positive. It is where you accept the alternative/experimental hypothesis when it is false (e.g. you believe the building is on fire, and run outside, but it is not).

Type II Error

A type II error Is a false negative. It is where you accept the null hypothesis when it is false (e.g. you think the building is not on fire, and stay inside, but it is burning).

Unrelated t-test

The unrelated t-test is a parametric statistical test of difference that allows a researcher to determine the significance of their findings. It is used in studies that have an independent groups design, where the data meets the requirements for a parametric test (level of measurement is interval or better, data is drawn from a population that has a normal distribution, the variances of the two samples are not significantly different).

Unstructured Interview

Unstructured interviews are more like a conversation and the interviewer only facilitates the discussion. Very little is decided in advance (only the topic and some of the questions) and therefore this type of interview typically produces rich qualitative data.

Validity

Validity refers to whether something is true or legitimate. Internal validity is a measure of whether results obtained are solely affected by changes in the variable being manipulated (i.e. by the independent variable) in a cause-and-effect relationship. External validity is a measure of whether data can be generalised to other situations outside of the research environment.

Volunteer Sampling

Volunteer sampling is a sampling technique where participants self-select to become part of a study because they volunteer when asked, or respond to an advert.

Wilcoxon

The Wilcoxon test is a non-parametric statistical test of difference that allows a researcher to determine the significance of their findings. It is used in studies that have a repeated measures or matched pairs design, where the data collected is at least ordinal.

Zero Correlation

Zero correlation means that there is no relationship between the co-variables in a correlation study.