Model NITI Aayog, 24-27 Dec, online. Write an original white paper.

Methods of Psychology | ISC Class 11 Psychology Notes

30 min read

On this page

This note covers the methods of psychology: how scientific method is applied to behaviour, scientific observation and field study, longitudinal and cross-sectional studies, the case study method, the experimental method with its variables, controls and steps, surveys, interviews and questionnaires, population and samples, psychological tests, ethical issues, and the use of statistics, frequency distributions, central tendency and dispersion.

How is scientific method applied to the study of behaviour?

Like all scientists, psychologists seek to describe, predict, explain and control what they study. They rely on formal, systematic observations, and it is this methodology that makes psychology a scientific endeavour. Questions about behaviour are numerous, so no single method can answer all of them.

Science is defined less by what it investigates than by how it investigates. The scientific method studies an event in an objective, systematic and testable manner.

Objectivity means that if two or more persons independently study the same event, they should, to a great extent, arrive at the same conclusion. If you and a friend measure a table with the same measuring device, you are likely to agree on its length.

What are the goals of psychological enquiry?

  • Description: describing a behaviour as accurately as possible, for example defining what "study habits" include.
  • Prediction: forecasting that a behaviour may occur under certain conditions within a margin of error.
  • Explanation: identifying the causes or antecedent conditions of a behaviour.
  • Control: making a behaviour happen, reducing it or enhancing it; therapy is a good example.
  • Application: bringing about positive changes in people's lives, such as using yoga and meditation to reduce stress.

What are the steps in scientific research?

  1. Conceptualising a problem: select a topic, narrow it to specific research questions, and form a hypothesis, a tentative answer to the problem.
  2. Collecting data: prepare a research design deciding the participants, the methods, the tools and the procedure, and then collect the data.
  3. Drawing conclusions: analyse the data with statistical procedures and graphs, such as pie-charts and bar diagrams, to verify the hypothesis.
  4. Revising research conclusions: confirm the hypothesis if the data support it; if not, state an alternative and test it again with new data.

Draw and label

Steps in conducting scientific enquiry

Draw four boxes in a cycle joined by arrows: 1 Conceptualising a Problem (selecting a topic for study), 2 Collecting Data (participants, methods, tools and procedure), 3 Drawing Conclusions (using statistical methods), 4 Revising Research Conclusions (restating the existing hypothesis or formulating a revised or new theory), with an arrow from 4 back to 1.

What is scientific observation?

Observation is a very powerful tool of psychological enquiry and an effective method of describing behaviour. In daily life we see but we do not observe. Scientific observation differs from day-to-day observation in three ways.

  1. Selection: psychologists select a particular behaviour to observe, such as how Class XI students spend their time in school.
  2. Recording: the selected behaviour is recorded by marking tallies, taking detailed notes in short hand or symbols, photographs or video recording.
  3. Analysis of data: the records are analysed to derive meaning from them.
  4. Skill: a good observer knows what to look for, whom to observe, when and where, how to record it and how to analyse it.

How does controlled observation differ from uncontrolled observation?

In naturalistic observation, the observer watches behaviour in a natural or real-life setting, such as a hospital, home, school or day care centre, and makes no effort to control or manipulate the situation. This is uncontrolled observation, carried out in the field.

In controlled laboratory observation, factors that are not the focus of the study are controlled. It is obtained in laboratory experiments; in one well-known study, smoke could only be introduced in a controlled laboratory situation.

How does participant observation differ from non-participant observation?

In non-participant observation, the observer watches from a distance, for example by sitting in a corner of a class or installing a video camera. The danger is that an outsider's presence may change the behaviour of students and the teacher.

In participant observation, the observer becomes part of the group, taking time to build rapport until the group accepts her or him. The degree of involvement varies with the focus of the study.

What are the advantage and disadvantage of observation?

Its advantage is that people can be studied in a naturalistic situation, as behaviour occurs. Its disadvantage is that it is labour intensive, time consuming and open to the observer's bias: "We see things as we are and not as things are". So the observer should record behaviour as it happens and not interpret it at the time.

How do longitudinal and cross-sectional studies differ?

Some research questions are about change over time, such as how a skill grows with age. Two designs are used to study such change.

What is a longitudinal study?

A longitudinal study follows the same group of people over a long period, often several years, and measures them again and again. It shows how the same individuals actually change.

Its advantage is that real change within each person can be traced. Its disadvantage is that it is slow and costly, and some participants drop out or move away before the study ends.

What is a cross-sectional study?

A cross-sectional study compares groups of different ages at one point in time, for example 6-year-olds, 10-year-olds and 14-year-olds tested in the same month.

Its advantage is that results are obtained quickly and cheaply. Its disadvantage is that the age groups differ in more than age: they grew up at different times and in different conditions, so differences may not be due to age alone.

FeatureLongitudinal studyCross-sectional study
ParticipantsThe same group, studied repeatedlyDifferent age groups, studied once
Time takenLong, often yearsShort
Main advantageTraces real change in the same individualsQuick and less expensive
Main disadvantageCostly; participants drop outAge groups differ in background, not only in age

What is the case study method?

A case study, or case history method, is an in-depth study of a particular case. Researchers choose cases that can provide critical information or new learning on less understood phenomena. The cases chosen are unique and therefore rich in information.

A case can be an individual with distinguishing characteristics, such as a patient showing psychological disorders; a small group with something in common, such as the creative writers Rabindra Nath Tagore and Mahadevi Verma; an institution, such as a school; or a specific event, such as children exposed to a tsunami.

A case study uses multiple methods, such as interview, observation and psychological tests, with a variety of respondents linked to the case. It gives a narrative or detailed description of events in a person's life, including feelings, fantasies, hopes, fears, traumatic experiences and parental upbringing.

Where have case studies been used?

Case studies are valuable in clinical psychology and human development. Freud's insights that led to psychoanalytic theory emerged from careful records of individual cases. Piaget built his theory of cognitive development on observations of his three children.

Minturn and Hitchcock studied the socialisation of children among Rajputs of Khalapur, and S. Anandalakshmy studied childhood in a weavers' community in Varanasi.

What are the advantage and disadvantage of a case study?

Its advantage is a detailed, in-depth depiction of people's lives. Its disadvantage is that one must be very cautious in generalising from individual cases, and validity in a single case is challenging. Information should be collected by several investigators, using multiple strategies, while keeping a chain of evidence.

What is the experimental method?

An experiment is conducted to establish a cause-effect relationship between two sets of events or variables in a controlled setting. One factor is changed, its effect on another factor is studied, and other related factors are kept constant. The cause is the event changed; the effect is the behaviour that changes.

What is a variable?

A variable is any stimulus or event which varies, that is, takes different values, and can be measured. An object is not a variable, but its attributes are. A pen is not a variable, but pens of different shapes, sizes and colours are. Intelligence, height and hair colour are variables.

  • Independent variable (IV): the variable manipulated or altered by the researcher; it is the cause.
  • Dependent variable (DV): the variable on which the effect of the IV is observed; it is the effect the researcher wants to explain.
  • Extraneous variables: other relevant variables that influence the DV but are not of interest; they must be controlled.

How do experimental and control groups differ?

An experimental group is exposed to the manipulation of the independent variable. A control group is treated in every way like it, except that the manipulated variable is absent.

In 1970 Bibb Latane and John Darley sent Columbia University students into a waiting room to fill a questionnaire while smoke poured in through a wall vent. In the control group students sat alone. In two experimental groups two other people were present: naive students, or confederates told to do nothing.

The IV was the presence or absence of other persons; the DV was how often students reported the smoke. Most (75 per cent) of those waiting alone reported it; groups of three naive students reported it only 38 per cent of the time; with two passive confederates only 10 per cent did.

How are variables controlled, and what are the steps in an experiment?

Relevant variables are of three major types: organismic variables such as anxiety and intelligence, situational variables such as noise and temperature, and sequential variables, which cause fatigue or practice effects when people are tested in several conditions.

Which control techniques are used?

  • Elimination: removing the variable, for example testing in a sound-proof, air-conditioned room.
  • Constancy: holding a variable constant when it cannot be eliminated.
  • Matching: equating groups on variables such as fear, motivation or socio-economic status by using matched pairs.
  • Counter-balancing: changing the order of tasks (half get A then B, half get B then A) to minimise the sequence effect.
  • Random assignment: giving each person an equal chance of being placed in any group, which removes systematic differences between groups.

What are the steps in an experiment?

  1. State the problem and form a hypothesis linking an independent and a dependent variable.
  2. Define how the independent variable will be varied and how the dependent variable will be measured.
  3. Select participants and assign them randomly to experimental and control groups.
  4. Control extraneous variables by elimination, constancy, matching or counter-balancing.
  5. Manipulate the independent variable for the experimental group only.
  6. Measure the dependent variable in all groups and compare them using statistics.
  7. Accept or revise the hypothesis and draw conclusions.

What are field and quasi experiments?

A field experiment is done in the natural setting, such as comparing demonstration and lecture teaching in a school. It generalises better, but control is less, and it is more time-consuming and expensive.

In a quasi experiment (quasi is Latin for "as if"), the IV is selected rather than manipulated, using naturally occurring groups, such as children who did or did not lose parents in an earthquake.

A well-designed experiment gives relatively convincing evidence of cause and effect. However, laboratory experiments have low external validity, some problems cannot be studied ethically (no one can be starved to study nutrition), and it is difficult to know and control all relevant variables.

How are surveys, interviews and questionnaires used?

Survey research came into existence to study opinions, attitudes and social facts, such as voting intentions, literacy rates and attitudes towards family planning. It has now become a sophisticated technique that helps in inferring causal relationships.

In December 2004 a magazine survey of 817 persons aged 25 to 55 in eight big cities asked what makes people happy. About 47 per cent said they were extremely happy, and about 80 per cent said money cannot buy happiness.

How are interviews conducted?

An interview is a purposeful, usually face-to-face activity in which an interviewer asks questions and an interviewee answers them. In a structured interview, questions in the interview schedule are fixed in wording and order, often with close-ended answers. In an unstructured interview, the interviewer is flexible and uses open-ended questions.

Interviews may be individual to individual, individual to group (such as a Focus Group Discussion), group to individual (as in a job interview) or group to group. Interviews give in-depth information and suit children and non-literate persons, but they take time and may not be cost-effective.

How are questionnaires and self-reports used?

The questionnaire is the most common, simple, versatile and low-cost self-report method. Respondents read a predetermined set of questions and mark answers on paper. Questions may be open-ended or closed-ended, such as Yes/No, multiple choice or a rating scale of 3, 5 or more points.

Questionnaires collect background information, past behaviour, attitudes, knowledge and aspirations. The main problem of a mailed questionnaire is poor response. Telephone surveys save time but suffer from uncooperativeness and superficial answers.

Surveys gather information quickly from thousands of persons. However, people may give inaccurate information because of memory lapses, or offer responses they think the researcher wants to hear.

What are population and samples?

A population is the whole group of people about whom a researcher wants to draw conclusions, such as all Class 11 students in a city. A population is usually too large to study in full.

A sample is the smaller group actually selected and studied from that population. Conclusions about the population are drawn from the sample, so the way the sample is chosen matters.

What are random, biased and representative samples?

  • Random sample: every member of the population has an equal chance of being selected, for example by drawing names by lottery.
  • Representative sample: a sample whose make-up, in age, gender, income and other relevant features, matches that of the population.
  • Biased sample: a sample in which some kinds of people are more likely to be included than others, so it does not reflect the population.

Bias can creep in easily. In a telephone survey, those who respond may differ from those who do not on age, gender, income or education, leading to very biased results. A questionnaire circulated only on the Internet reaches only people who use it.

Note: Random is not the same as careless. A random sample is chosen by a fixed rule that gives everyone an equal chance; picking whoever is nearby is not random and usually produces a biased sample.

What are psychological tests?

Assessment of individual differences has been an important concern of psychology from the beginning. Tests assess intelligence, aptitude, personality, interest, attitudes, values and educational achievement.

Definition: Psychological test. A psychological test is a standardised and objective instrument which is used to assess an individual's standing in relation to others on some mental or behavioural characteristics.

What are the characteristics of a good test?

  • Objectivity: two or more researchers testing the same group get more or less the same values; items, instructions, administration and scoring are fixed in advance.
  • Reliability: consistency of scores on two occasions. Test-retest reliability shows stability over time; split-half reliability shows internal consistency, by correlating odd and even items.
  • Validity: the test measures what it claims to measure, such as mathematics achievement and not language proficiency.
  • Norms: the normal or average performance of a large group, set by age, sex and place of residence; a test with norms is standardised.

What are the uses of tests?

Tests are used for personnel selection, placement, training, guidance and diagnosis, in educational institutions, guidance clinics, industries and defence establishments. Decision makers should not rely on any single test, and should combine test data with a person's background, interests and past performance.

What are the types of tests?

BasisTypesKey feature
LanguageVerbal, non-verbal, performanceVerbal tests need literacy; non-verbal items use symbols or pictures; performance tests need movement of objects in a particular order
Mode of administrationIndividual, groupIndividual tests suit children and those who do not know the language but take time; group tests are quick but answers may be fake
Difficulty levelSpeed, powerSpeed tests have a time limit and items of equal difficulty; power tests have no time limit and items of increasing difficulty

It is difficult to construct a pure speed or power test, and the majority of tests combine both.

How do the methods of psychology compare?

Each method has its own advantages and limitations, so a researcher should not depend on only one. If two or more methods give the same results, one can be more confident. The table gives one advantage and one disadvantage of each method.

MethodOne advantageOne disadvantage
ObservationStudies behaviour in a naturalistic situation as it occursLabour intensive and open to observer's bias
Laboratory experimentRelatively convincing evidence of cause and effectLow external validity; results may not apply to real situations
Field experimentResults generalise betterLess control; more time-consuming and expensive
Case studyDetailed, in-depth picture of a lifeMust be very cautious in generalising
InterviewIn-depth, flexible; usable with children and non-literate personsTakes time and may not be cost-effective
QuestionnaireSimple, versatile and low-costPoor response when mailed
Psychological testStandardised, objective comparison with othersGroup tests may get fake or unmotivated answers
Longitudinal studyTraces real change in the same peopleSlow, costly; participants drop out
Cross-sectional studyQuick and less expensiveAge groups differ in background too

Psychological measurement also has general limits. It lacks a true zero point, since no one has zero intelligence, so scores have relative value. Tools are relative to their context, and qualitative data involve subjective interpretation.

What ethical issues must researchers respect?

Psychological research deals with human beings, so researchers follow ethics, or moral principles: respect for privacy and the choice to participate, beneficence (protecting participants from harm) and justice (sharing the benefits of research). Five aspects matter most.

  1. Voluntary participation: people decide freely whether to take part, without coercion or excessive inducement, and may withdraw without penalty once the research has begun.
  2. Informed consent: participants are told what will happen during the study before data are collected, especially when electric shock, unpleasant stimuli, private questions or deception are involved.
  3. Debriefing: after the study, participants receive information to complete their understanding. It ensures they leave in the same physical and mental state as they entered, and removes anxiety caused by deception.
  4. Sharing the results: the researcher is obliged to go back and share the results. This meets participants' expectations, and their opinions may give new insights.
  5. Confidentiality: information is kept in strict confidence and used only for research. Identities are best not recorded; otherwise code numbers are used, and the identification list is destroyed when the research is over.

Note: Deception and debriefing. In some studies participants are given false feedback, such as "you are incompetent". Debriefing is particularly important in such studies, because it offers reassurance and undoes the effects of the deception.

Why is statistics used in psychology?

After data are collected, the researcher must draw conclusions. In the quantitative method, answers to tests, questionnaires and structured interviews are turned into numbers, such as "1" for right and "0" for wrong answers, and added into an aggregate score. Statistics then gives meaning to these scores.

Statistics is the branch of mathematics that collects, organises, analyses and interprets numerical data. The term also refers to the numbers, such as an average, computed from a sample. A sample statistic is used to estimate the corresponding value for the population.

What does statistics help psychologists do?

  • Describe and summarise data: turn a long list of scores into a few clear numbers and graphs.
  • Compare individuals or groups: compare a person's score with that of the group, or compare two groups.
  • Investigate relationships: find whether two variables are associated, using the correlation coefficient, which ranges from +1.0 through 0.0 to -1.0.
  • Predict: use a known relationship to forecast behaviour, such as predicting good marks from study time.

A correlation of +.85 between study time and achievement shows a strong positive association. As study hours increase, hours spent on other activities may decrease, a negative correlation. Values close to zero, such as -.02 or +.03, show that two variables are unrelated.

How do descriptive and inferential statistics differ?

FeatureDescriptive statisticsInferential statistics
PurposeSummarise and describe the scores actually collectedDraw conclusions about a population from a sample
Key questionWhat do these scores look like?Is an observed difference between groups likely or unlikely to have occurred by chance?
ExamplesFrequency distribution, mean, median, mode, range, standard deviationTests of whether the difference between an experimental and a control group is significant

How are scores grouped and summarised?

A long list of raw scores is hard to read. A frequency distribution is a table that shows how many times each score, or each group of scores, occurs.

  1. Find the highest and lowest scores.
  2. Divide this span into equal class intervals, such as 10 to 19, 20 to 29 and so on.
  3. Go through the scores and put a tally mark against the interval each one falls in.
  4. Count the tallies to get the frequency of each interval, and check that the frequencies add up to the total number of scores.
Class interval (anxiety score)Frequency (number of students)
10 to 193
20 to 296
30 to 398
40 to 493
Total20

What are the measures of central tendency?

A measure of central tendency is a single score that represents the centre of a distribution.

  • Mean = ΣX ÷ N, where ΣX is the sum of all scores and N is the number of scores. It is used when scores are fairly evenly spread with no extreme values, since it uses every score.
  • Median: the middle score when scores are arranged in order; with an even number of scores, it is the average of the two middle ones. It is used when there are extreme scores or when data are ranks.
  • Mode: the score that occurs most often. It is used for categories, such as the most popular answer, or for a quick estimate.

Worked example 1. Ten students score 12, 15, 11, 15, 18, 14, 15, 10, 13 and 17 on a 20-item test. Find the mean, median and mode.

Answer: ΣX = 140 and N = 10, so the mean = 140 ÷ 10 = 14. In order the scores are 10, 11, 12, 13, 14, 15, 15, 15, 17, 18; the two middle scores are 14 and 15, so the median = (14 + 15) ÷ 2 = 14.5. The score 15 occurs three times, so the mode = 15.

Worked example 2. Five people take 4, 5, 5, 6 and 30 minutes to solve a puzzle. Which average describes them best?

Answer: The mean = 50 ÷ 5 = 10 minutes, but four of the five took 6 minutes or less. The median = 5 minutes and the mode = 5 minutes. The one extreme score of 30 pulls the mean up, so the median is the better measure here.

How is the spread of scores measured?

Dispersion, or variability, is the extent to which scores are spread out around the centre. Three measures are used.

  • Range = Highest − Lowest. It is quick to find but depends on only the two extreme scores.
  • Variance = Σ(X − M)² ÷ N, where M is the mean. It is the average of the squared deviations of the scores from the mean.
  • Standard deviation (SD) is the square root of the variance. It is the most widely used measure of spread and is in the same units as the scores.

Worked example 3. For the ten scores in Worked example 1 (mean 14), find the range, variance and standard deviation.

Answer: Range = 18 − 10 = 8. Deviations from 14 are −4, −3, −2, −1, 0, 1, 1, 1, 3, 4; their squares add up to 16 + 9 + 4 + 1 + 0 + 1 + 1 + 1 + 9 + 16 = 58. Variance = 58 ÷ 10 = 5.8. SD = √5.8, about 2.41 marks.

Why do both central tendency and variability matter?

An average alone can mislead. Group A scores 9, 10, 10 and 11; Group B scores 2, 6, 14 and 18. Both groups have a mean of 10, yet Group A's range is 2 and Group B's is 16.

Group A is alike; Group B contains both very weak and very strong performers. A teacher or counsellor would plan very differently for the two. So psychologists report a measure of central tendency together with a measure of variability, such as the mean with the SD.

Draw and label

Same mean, different spread

On one number line from 0 to 20, mark Group A's scores (9, 10, 10, 11) as dots bunched around 10 and Group B's scores (2, 6, 14, 18) as dots spread widely, with a vertical line at the shared mean of 10.

Glossary

  • Hypothesis: A tentative answer to a research problem, stated so that it can be tested and proved true or false with data.
  • Naturalistic observation: Observation of behaviour in a natural or real-life setting with no attempt to control or manipulate the situation.
  • Participant observation: Observation in which the observer becomes part of the group being studied after building rapport with its members.
  • Longitudinal study: A study that follows the same group of people over a long period, measuring them repeatedly to trace change.
  • Cross-sectional study: A study that compares people of different ages at one point in time.
  • Case study: An in-depth study of one person, group, institution or event, using several methods such as interview, observation and tests.
  • Independent variable: The variable that the researcher manipulates or alters in an experiment; it is treated as the cause.
  • Dependent variable: The variable on which the effect of the independent variable is observed; it is treated as the effect.
  • Control group: A comparison group treated exactly like the experimental group except that the manipulated variable is absent.
  • Population: The whole group of people about whom a researcher wants to draw conclusions.
  • Representative sample: A sample whose make-up in relevant features, such as age, gender and income, matches that of the population.
  • Reliability: The consistency of scores obtained by an individual on the same test on two different occasions.
  • Validity: The extent to which a test measures what it claims to measure.
  • Debriefing: Giving participants full information after a study so they leave in the same physical and mental state as they entered.
  • Standard deviation: The square root of the variance; the most widely used measure of how far scores spread around the mean.

Common errors and misconceptions

  • Misconception: An object, such as a pen, is a variable. Correct: An object is not a variable; its attributes, such as shape, size and colour, are.
  • Misconception: The control group receives no treatment at all and is handled differently. Correct: It is treated in every way like the experimental group except that the manipulated variable is absent.
  • Misconception: A correlation shows that one variable causes the other. Correct: Correlational research only shows whether two variables are associated; experiments are used to establish cause and effect.
  • Misconception: A large sample is always a good sample. Correct: A sample must be representative; a large sample drawn only from one kind of people is still biased.
  • Misconception: A reliable test must be valid. Correct: Reliability is consistency of scores; validity asks whether the test measures what it claims to measure. Both must be checked.
  • Misconception: The mean is always the best average. Correct: Extreme scores pull the mean; the median is better when there are extreme scores or ranks.
  • Misconception: Two groups with the same mean performed alike. Correct: Their spread may differ widely, so a measure of variability such as the SD must also be reported.

Exam-style questions with model answers

Q1. In an experiment, students waited in a room alone or with two other people while smoke filled the room, and the researchers counted how often students reported the smoke. The dependent variable was: (a) the presence of other people (b) the frequency of reporting the smoke (c) the amount of smoke (d) the waiting room [1 mark]
  1. (b) The frequency of reporting the smoke, because it is the behaviour on which the effect of the presence of others was observed.
Q2. Assertion: Debriefing is particularly important when deception has been used in a study. Reason: Debriefing ensures that participants leave the study in the same physical and mental state as when they entered. Choose: (a) both true and Reason explains Assertion (b) both true but Reason does not explain Assertion (c) Assertion true, Reason false (d) both false. [1 mark]
  1. (a) Both are true and the Reason explains the Assertion: debriefing reassures participants and removes anxiety caused by the deception.
Q3. Distinguish between a speed test and a power test. [2 marks]
  1. A speed test has a time limit within which all items must be answered, and its items are of the same degree of difficulty.
  2. A power test has no time limit and assesses underlying ability; its items are generally arranged in increasing order of difficulty.
Q4. A researcher wants to know the reading habits of all Class 11 students in a city, and questions only students found in one library. Identify the population and the sample, and explain why the sample may be biased. [2 marks]
  1. The population is all Class 11 students in the city; the sample is the students questioned in the library.
  2. The sample is biased because library users are more likely to be keen readers, so it does not represent all Class 11 students.
Q5. The scores of five students on a memory test are 6, 8, 8, 9 and 14. Calculate the mean, median, mode and range. [4 marks]
  1. Mean = ΣX ÷ N = (6 + 8 + 8 + 9 + 14) ÷ 5 = 45 ÷ 5 = 9.
  2. Median: the scores in order are 6, 8, 8, 9, 14, so the middle (third) score, 8, is the median.
  3. Mode: 8 occurs twice, more often than any other score, so the mode is 8.
  4. Range = Highest − Lowest = 14 − 6 = 8.
Q6. Explain any four ethical principles that a psychologist must follow while conducting research. [4 marks]
  1. Voluntary participation: people choose freely whether to take part, without coercion, and may withdraw without penalty.
  2. Informed consent: participants are told what will happen in the study before any data are collected.
  3. Debriefing: after the study, participants are given full information and reassurance so that they leave in the same state as they entered.
  4. Confidentiality: information is kept in strict confidence and used only for research, with code numbers in place of names.
Q7. Group A scores 9, 10, 10 and 11 on a test, and Group B scores 2, 6, 14 and 18. Using these data, explain why both central tendency and variability are important in psychology. [4 marks]
  1. Both groups have the same mean: Group A = 40 ÷ 4 = 10 and Group B = 40 ÷ 4 = 10.
  2. Their spread differs: Group A's range is 11 − 9 = 2, while Group B's range is 18 − 2 = 16.
  3. So the mean alone suggests the groups are alike, while the range shows Group A is uniform and Group B has very weak and very strong performers.
  4. Psychologists therefore report a measure of central tendency together with a measure of variability, such as the mean with the standard deviation.
Q8. A researcher wants to find out whether noise affects people's problem-solving ability. Describe the steps she should follow in conducting an experiment. [7 marks]
  1. State the problem and a hypothesis, for example "people solve fewer problems in a noisy room than in a quiet room".
  2. Identify the variables: noise is the independent variable and the number of problems solved is the dependent variable.
  3. Select participants and assign them randomly to an experimental group (noise) and a control group (no noise), so that each person has an equal chance of being in either group.
  4. Control extraneous variables: keep the problems, time, temperature and lighting the same for both groups, and use matching for variables such as motivation.
  5. Manipulate the independent variable by playing noise only in the experimental group's room.
  6. Measure the number of problems solved by each group and compare the groups using statistics.
  7. Accept the hypothesis if the data support it; otherwise revise it and test again with new data.
Q9. What is a psychological test? Explain its characteristics and its types. [7 marks]
  1. A psychological test is a standardised and objective instrument used to assess an individual's standing in relation to others on some mental or behavioural characteristic.
  2. Objectivity: different researchers testing the same group get more or less the same values, because items, instructions, administration and scoring are fixed in advance.
  3. Reliability: scores are consistent on two occasions, checked by test-retest reliability or by split-half reliability using odd and even items.
  4. Validity: the test measures what it claims to measure, such as mathematics achievement rather than language proficiency.
  5. Norms: the average performance of a large group, set by age, sex and place of residence, allows an individual's score to be interpreted.
  6. By language, tests are verbal, non-verbal or performance; by mode of administration, they are individual or group tests.
  7. By difficulty, tests are speed tests, with a time limit and items of equal difficulty, or power tests, with no time limit and items of increasing difficulty.

Key takeaways

  • Psychological enquiry aims at description, prediction, explanation, control and application, and follows four steps from conceptualising a problem to revising conclusions.
  • Scientific observation involves selection, recording and analysis; it may be naturalistic or controlled, participant or non-participant.
  • Longitudinal studies follow the same people over time; cross-sectional studies compare different age groups at one time.
  • Case studies give an in-depth picture of one case using several methods, but generalising from them needs great caution.
  • Experiments manipulate an independent variable, measure a dependent variable, and compare experimental and control groups while controlling extraneous variables.
  • Surveys use interviews, questionnaires and telephone methods; their results depend on a representative, not a biased, sample from the population.
  • A psychological test is standardised and objective, and must be reliable and valid with norms; tests differ by language, administration and difficulty.
  • Researchers must ensure voluntary participation, informed consent, debriefing, sharing of results and confidentiality.
  • Descriptive statistics summarise scores; inferential statistics judge whether group differences are likely to have occurred by chance.
  • Mean, median and mode show the centre of scores; range, variance and standard deviation show their spread, and both are needed.

Test yourself

What does objectivity mean in scientific research?

If two or more persons independently study the same event, they should, to a great extent, arrive at the same conclusion.

What is the danger in non-participant observation?

The very presence of an outsider observing may change the behaviour of the people being observed, such as the students and teacher.

What is counter-balancing?

Changing the order of tasks, so half the group does task A then B and half does B then A, to minimise the sequence effect.

How does a quasi experiment differ from a laboratory experiment?

In a quasi experiment the independent variable is selected, using naturally occurring groups, rather than manipulated by the experimenter.

What is split-half reliability?

A measure of a test's internal consistency, found by correlating scores on the odd-numbered items with scores on the even-numbered items.

What is a random sample?

A sample in which every member of the population has an equal chance of being selected.

What does a correlation coefficient of -0.02 tell you?

It is close to zero, so there is no significant relationship between the two variables; they are unrelated.

Find the median of 3, 9, 4, 7 and 5.

Arranged in order the scores are 3, 4, 5, 7, 9, so the middle score, and the median, is 5.

Write about it

Turn a question from this chapter into a paper.

The Writing Studio has a structure guide, a rubric and citation tools for 15 formats, from essays to research papers. A free account keeps up to five drafts. Learnacy Essential adds feedback from an AI writing coach and submission to The OYI Review.

Publication depends on review and is not guaranteed.