research methods

Research Methods

list experimental techniques

• laboratory experiments

• field experiments

• natural experiments

• quasi experiments

list non-experimental techniques

• correlation

• observations

• interviews

• questionnaires

• case studies

• content analysis

• thematic analysis

define the key term ‘validity’

• refers to how ‘real’ or accurate something is

• its an important issue that runs throughout the whole of psychology

define the key term ‘reliability’

• a measure of consistency

• if the results are not consistent- then the measure is not reliable

define the key term ‘Ethics’

• The set of moral principles that psychologists must follow to protect participants in research, ensuring they are treated safely, fairly, and with respect.

statistical analysis

• the use of descriptive statistics, which summarise data and

• inferential statistics- which tell us if the results are likely to be due to a chance or not ( based on probability)

define the term ‘ independent variable’

• the variable that the researcher manipulates → which is assumed to have a direct effect on the dependent variable (DV)

define the term ‘ dependent variable’

• the variable that the research measures → the variable is affected by changes in the independent variable

how many conditions does the independent variable have?

2 conditions

operationalisation

• where you clearly specify/define observable behaviours + how it’ll be measured so that someone else can replicate it exactly

aim

A general statement about the purpose of a study

Hypothesis

A precise and testable statement about the relationship between the variables to be studied.

Stated at the start of a study.

two types of hypothesis

H1 – Research/alternative/experimental hypothesis

H0 – Null hypothesis - useful to know about for Inferential statistics and falsifiability)

Directional hypothesis

states the direction of the difference or relationship. Used when there is previous research to suggest a direction

non-directional hypothesis

• predicts that a difference will exist between two or more variables without predicting the exact direction of the difference.

• This is usually because previous research has been inconclusive, and the specific nature (direction) of the effect of the IV on the DV cannot be predicted confidently

Null Hypothesis

all investigations have a null hypothesis which suggests that any difference or relationship found is due to chance.

sample

A group of people that are drawn from the target population to take part in a research investigation

Target population

The group that the researchers draw the sample from and want to be able to generalise the findings to

• usually too large to study in its entirety, so sampling techniques are used to choose a representative (typical) sample

Representative sample

A sample that closely matches the target population as a whole in terms of key variables and characteristics

Generalise

Applying results to a wider population beyond the research participants

sampling bias

when a sample is compromised of one particular type of person

five common types of sampling

· Random

· Systematic

· Stratified

· Opportunity

· Volunteer

random sampling

• Every member of the target population has an equal chance of being selected.

• Requires a complete list of the population.

• Participants are chosen using:

  • Random number generator

  • Names from a hat

random sampling strengths

• Reduces researcher bias

• Likely to produce a representative sample

• Allows better generalisation

random sampling limitations

• Time-consuming and impractical

• Some selected participants may refuse → becomes closer to a volunteer sample

Systematic Sampling

• Participants are selected using a fixed interval (e.g. every 10th person).

• Requires a list of the population.

Systematic Sampling strengths

• Reduces researcher bias

• Simple and efficient

Systematic Sampling limitations

• Not fully random

• Can be biased if the list has a pattern (e.g. every 10th person shares a characteristic)

• May reduce representativeness

Stratified Sampling

• The population is divided into subgroups (strata) based on characteristics (e.g. gender, job role).

• Participants are selected in proportion to their representation in the population.

• Selection within each stratum is random.

Stratified Sampling strengths

• Most representative sampling method

• Reduces researcher bias

• Improves generalisation

Stratified Sampling limitations

• Time-consuming

• Difficult to identify all relevant strata

• Still cannot account for all individual difference

Opportunity Sampling

• Participants are chosen because they are available and willing.

• Commonly used due to convenience.

Opportunity Sampling strengths

• Quick and cheap

• Easy to carry out

Opportunity Sampling limitations

• High risk of researcher bias

• Sample is often unrepresentative

• Limits generalisation

Volunteer Sampling

• Participants self-select by responding to an advert.

• Researcher does not approach participants directly.

Volunteer Sampling strengths

• Minimal effort for researcher

• Ethical (participants choose to take part

Volunteer Sampling limitations

• Volunteer bias – certain personality types more likely to volunteer

• Often unrepresentative

• Reduced generalisability

Bias

• Occurs when some members of the population are more likely to be selected than others.

• More common in opportunity and volunteer sampling.

Generalisation

• Ability to apply findings from the sample to the target population.

• More valid with random and stratified samples.

Experimental Design

• Experimental design refers to how participants are allocated to the different conditions of an experiment.

what does experimental design affect

• The design chosen affects:

  • Control of participant variables

  • Risk of order effects

  • Cost, time and validity of the research

Participant variables

Individual differences between participants (e.g. age, IQ, personality) that may affect the DV.

Order effects

Changes in performance due to the order of conditions (e.g. practice or fatigue).

Random allocation:

Assigning participants to conditions by chance to control participant variables.

Demand characteristics:

Cues that reveal the aim of the study and alter participants’ behaviour

Counterbalancing

Technique used in repeated measures to reduce order effects by varying condition order.

Independent Groups Design

• Different participants are used in each condition.

• Participants are allocated using random allocation.

• Each participant takes part in one condition only.

Independent Groups Design strengths

• No order effects (participants only complete one condition)

• Reduced risk of fatigue or practice

• Lower risk of demand characteristics

Independent Groups Design limitations

• Requires more participants (time-consuming and costly)

• Participant variables may affect results (e.g. IQ differences)

• Reduces internal validity if groups are not equivalent

Repeated Measures Design

• Same participants take part in all conditions.

• Participants act as their own control.

Repeated Measures Design strengths

• Fewer participants required

• Controls participant variables

• More sensitive comparison between conditions

Repeated Measures Design limitations

• Order effects (practice, boredom, fatigue)

• Increased risk of demand characteristics

How to control order effects :Counterbalancing

• Half the participants complete condition A then B

• Other half complete condition B then A

• Order effects are spread evenly, not eliminated

Matched Pairs Design

• Participants are paired based on key characteristics (e.g. age, IQ).

• One participant from each pair is placed in each condition.

• Treated like independent groups in analysis.

Matched Pairs Design strengths

• Reduces participant variables

• No order effects

• More valid comparison than independent groups

Matched Pairs Design limitations

• Very time-consuming

• Difficult to match participants accurately

• Impossible to control all individual differences

Extraneous variables

the variables that could affect the DV. These are essentially nuisance variables that would want to minimise and therefore CONTROL. Does not vary systematically with the IV.

Confounding variables

Where extraneous variables are important enough to cause a change in the DV, they become confounding variables.

Confounding Variables are any variable (other than the IV) that could affect the DV. CVs change systematically with the IV

Situational Variables

Factors connected to the research situation that could affect the DV e.g. temperature, noise, lighting, distractions

Participant Variables:

Factors connected to the participant that could affect the DV e.g. IQ, age, experience, motivation

Investigator Effects

• occur when the researcher’s behaviour (conscious or unconscious) influences the DV.

• This can happen through:

  • Study design

  • Selection of participants

  • Interaction with participants

what can an investigator effect

• Researchers may unintentionally give cues about the aim or expected behaviour, affecting participant responses.

• Investigator effects can also affect observations, as researchers may interpret behaviour differently.

• The personal characteristics of the investigator (e.g. age, gender, accent, status) can influence participants’ behaviour.

• Investigator effects reduce the validity of the findings.

Control of Investigator Effects

• Controlled using a double-blind procedure.

• Neither the researcher nor participants know the aim of the study or the IV.

• Prevents the researcher from influencing participants.

• Common in drug trials comparing a drug with a placebo

Demand characteristics

• cues from the research situation that allow participants to guess the aim of the study.

• This leads to participant reactivity, where behaviour changes.

• Participants may:

  • Act to support the hypothesis

  • Act against it (“screw-you” effect)

• This reduces the validity of the results as behaviour is unnatural.

Control of Demand Characteristics

• Controlled using a single-blind procedure.

• Participants do not know the aim or IV, but the researcher does.

• Often involves deception.

• Common in studies comparing a drug and a placebo.

Systematic Error

• A consistent bias in a study that affects results in the same way each time.

• It occurs due to flaws in the design or procedure (e.g. faulty equipment, leading questions).

• This reduces the validity of the results because the findings are consistently inaccurate.

random error

• Unpredictable, chance variations that affect results differently each time.

• Caused by uncontrolled variables (e.g. participant mood, distractions).

• This reduces the reliability of results because findings are inconsistent.

Control of Variables: randomisation

The use of chance to reduce the effects of the researcher's unconscious biases when designing an investigation or a task, or allocating participants

This involves organising participants and materials in a way that is randomly generated and is free from bias

Control of Variables: standardisation

• the process in which procedures used in research are kept the same

• more likely that results will be replicated on subsequent occasions when research is standardised which means that data reflects a meaningful pattern and was not a one off chance result

random allocation

• an extremely important process in research

• gently decreases the impact of participant variables - any pp variables should be equally spread out across both conditions

• both conditions are likely to be affected equally

summary of controls of research

pilot study

• is a small-scale trial run conducted before the main study.

• Its purpose is to identify problems or confusions in the research design.

• Results from the pilot study are not included in the final analysis.

• It helps prevent wasting time and money by spotting issues early.

• The same participants should not be used in both the pilot and main study.

what does a pilot study check?

• Whether the procedure works

• If instructions and debrief are clear

• Whether the task is too easy or too difficult

• If anything important has been missed out

• It reduces the risk of participant misunderstanding, which could lead to invalid or meaningless results.

Questionnaires must be piloted to?

• Ensure all questions are clear and answerable

• Check reliability and validity

• Overall purpose: to find and correct errors in methodology or procedure before carrying out the main investigation.

what do pilot studies improve?

Pilot studies improve validity, reliability, and ethical quality of research.

Single blind:

when the pps are not told the true aim of the research. This is an attempt to control for the confounding variable of demand characteristics.

Double blind

• when the pps are not told the true aim of the research and the researcher does not know them either.

• In this case, a third party researcher will conduct the experiment.

• This also helps to reduce demand characteristics and investigator effects.

Experimental group

the group which have the IV altered in some way. For example, in a drug trial, this group would be given the drug.

Control Group

the group which does not have the IV altered in some way. For example, in a drug trial, this group would be given a placebo (a fake drug)

Responsibility of Psychologists

• Most psychological research involves human participants.

• Psychologists have a duty to protect participants’:

  • Psychological well-being

  • Physical health

  • Values

  • Dignity

• Research should be conducted in an ethical manner.

What Are Ethical Issues?

Ethical issues are considerations researchers must address:

• Before the research begins

• During the investigation

• After the study is completed

Purpose of Ethical Considerations

• Ethical issues focus on:

  • The welfare of participants

  • The integrity and credibility of the research

  • The responsible use of data

• Following ethical guidelines ensures research is safe, respectful, and valid.

Ethical Research

research that is appropriate to its circumstances and morally correct

Ethical Issues

arise when there is a conflict between the aim or intentions of the research and the rights and well-being of the participants.

Six of the main ethical guidelines

• Deception

· Right to withdraw

· Informed consent

· Privacy and confidentiality

· Protection from harm

DECEPTION

When information is

deliberately withheld

from participants or

they are knowingly

misled.

WHY IS DECEPTION UNETHICAL? (IF BROKEN)

It prevents participants from giving fully informed consent which means that they might be taking part in research that goes against their views or beliefs.

HOW TO DEAL WITH THE ISSUE OF DECEPTION ? (IF BROKEN)

At the end of the study the participants should be fully debriefed and told the true aim and nature of the research. At this point the participant should be given the right to withdraw the publication of their results. The contact details of the experimenter should be given if participants have any further questions or queries

RIGHT TO WITHDRAW

Participants have the

right to withdraw

(remove themselves or

their data from the

study) at any stage.

This includes after the

research has been

conducted, in which

case the researcher

must destroy any data

or information

collected.

WHY IS RIGHT TO WITHDRAW UNETHICAL? (IF BROKEN)

Participants who are not given the right to withdraw may feel unnecessary or undue stress and are therefore not protected from harm.

HOW TO DEAL WITH THE ISSUE OF RIGHT TO WITHDRAWAL ? (IF BROKEN)

• At the beginning of the study in the consent form the pp should be informed of their right to withdraw.

• At the end of the study the participants should be fully debriefed and told the true aim and nature of the research.

• At this point the participant should be given the right to withdraw the publication of their results.

• The contact details of the experimenter should be given if participants have any further questions or queries

INFORMED CONSENT

When someone

consents to participate

in research, their

consent must be fully

informed which means

the aims of the

research should be

made clear before they

agree to participate.

WHY IS INFORMED CONSENT UNETHICAL? (IF BROKEN)

Lack of informed consent may mean that the participant is taking part in research that goes against their wishes or beliefs. It is possible that the participant may have felt obliged to take part or even coerced into it, especially if they are not fully informed.

HOW TO DEAL WITH THE ISSUE OF INFORMED CONSENT? (IF BROKEN)

Pps should be issued with a consent letter (informed consent form), that details all the relevant information that might affect their decision to participate.

If the pps agrees, they sign the form and the study goes ahead with them taking part.

If they refuse, they walk away and are not included.

what do we need for children under 16 in regards of informed consent

For children under 16, parental consent is needed. It is possible to gain consent from those in ‘loco parentis’ e.g. A teacher.

Presumptive consent:

• involves taking a random sample of the population and introducing them to the research, including any deception which may result.

• If they agree to take part in the research it can be presumed that other future participants would do the same so the consent is generalised.

Prior general consent

involves participants agreeing to take part beforehand in numerous psychological investigations, which may or may not involve deception.

This, in effect, means that they will have given consent for being deceived

Retrospective consent

• involves participants giving consent for their participation after already taking part, for instance, if they were not aware that they were the subject of an investigation.

• Children as participants: involves gaining the consent of the parent(s) in writing for children under the age of 16 to participate in any psychological research.

PRIVACY AND

CONFIDENTIALITY : privacy

is the right of

individuals to decide

how information about

them will be

communicated to

others.

PRIVACY AND

CONFIDENTIALITY : confidentiality

is

where a participant’s

personal information is

protected by law under

the Data Protection Act

both during and after

the experiment.