research methods

aqa psychology

reliability

consistency

validity

accuracy

objective

Free from bias or preconceived ideas. Opposite of subjective.

systematic

Research is carried out in an orderly + consistent way. It uses standardised procedures

Standardised

Same for every person.

Replicable

Research can be repeated by others to determine whether the same results can be obtained. If the same results are obtained then they have reliable.

Empirical evidence-

Research evidence based on the collection and analysis of data.

Standardised procedures

Carried out in an unvarying way

strengths of questionnaires

• Allows participants to describe their own experiences rather than a psychologist inferring this from observing participants.

• large amounts of data can be collected fairly quickly and cheaply, which can increase representativeness and generalisability

weaknesses of questionnaires

• Social desirability bias may occur where participants may lie to present themselves in a socially acceptable manner, this can reduce validity

• Questions can often be leading, The researchers may be forcing the participant to give a particular reply

• Questions/scales may be interpreted differently by different participants.

open questionnaires

• Do not have a fixed range of answers and respondents are free to answer in any way they wish e.g. what do you think of A-level psychology

• Open questions tend to produce qualitative data that is rich in depth and detail but may be difficult to analyse.

strengths of open questionnaires

May provide unexpected answers, allowing the researchers to gain new insights into people’s feelings and attitudes.

Better validity as respondents can answer fully rather than being forced to respond in a particular way.

weaknesses of open questionnaires

Open questions are very time consuming and expensive to interpret and analyse.

They are hard to analyse and interpret and so it is difficult to compare responses.

closed questionnaires

•  Offers a fixed number of responses e.g. we might ask participants if they feel more talkative as a result of drinking an energy drink and restrict their options to 'yes' or 'no' or we could get participants to rate how talkative they were on a sale from 1 to 10

• Closed questions provided numerical data by limiting he answers respondents can give- quantitative data which is usually easy to analyse but it may lack depth and detail associated with open answers.

strengths of closed questions

They provide quantitative data and so the results can be easily summarised, presented and compared between respondents.

 

weaknesses of closed questionnaires

Respondents may be forced to select answers that don’t represent their real thoughts or behaviour, lowering validity.

Participants may often select ‘don’t know’ meaning data collected is not informative.

evaluation of questionnaires

• Cost effective

• Can be distributed easily which allows for large samples which produce large amounts of data

• Can be completed with or without the researcher being present

• Less effort to distribute and conduct than other RMs

• Produce quantitative data which is easy to analyse and compare

Negatives

• Respondents can lie (which renders data invalid)

• Respondents can cat in a socially desirable fashion (a form of bias)

• Questionnaires often produce a response bias

• Respondents may not answer the questions properly as they might rush the questionnaire or fail to read questions properly

• Susceptible to acquiesce bias (some people just like to agree)

Unstructured interviews

• Works  like a conversation

• there are no set questions

• There is a general aim that a certain topic will be discussed, and interaction tends to be free-flowing.

• The interviewee Is encouraged to expand on their answers as prompted by the interviewer.

strengths of unstructured interviews

Highly replicable due to their standardized format

The format also reduces differences between interviews

weakness of unstructured interviews

Respondents can not elaborate on their points which may make them feel frustrated, nut also valuable information may be lost

Structured interviews

• Made up of a pre-determined set of questions that are asked in a fixed order

• Like a questionnaire but conducted face-to-face (or over the phone) and in real time. I.e. the interviewer asks the questions and waits for a response.

Strengths of structured interviews

More flexible

The interviewer can follow up on points to gain insight into the worldwide of the interviewee

weakness of structured interviews

Analyzing data Is difficult (irrelevant data collected+ drawing conclusions can be difficult)

Respondents can act in a socially desirable manner

Respondents can lie

Semi-structured interviews

• Many interviews are likely to fall somewhere in-between the two types described above

• A job interview is a good example of a semi-structured interview as there is a list of questions that have been worked out in advance but interviewers are also free to ask follow-up questions when they feel it is appropriate.

designing questionnaires

• Questionnaires could include two types of questions: open questions and closed questions

• It is also the case that closed questions can be further divided into different types

• It makes sense to refer to the following examples as 'items'

rating scales

• a rating scale works in a similar way but gets respondents to identify a value that represents their strength of feeling about a particular topic

 

Likert scale

a rating scale works in a similar way but gets respondents to identify a value that represents their strength of feeling about a particular topic

fixed choice option

A fixed choice option item includes a list of possible options and respondents are required to indicate those that apply to them.

Designing interviews

• Most interviews involve an interview schedule which is the list of questions that the interviewers intends to cover

• This should be standardized for each participant to reduce the contaminating effect of interviewer bias

• Typically the interviewer will take notes or may recorded the interview to be analyzed later.

Designing one –to-one interviews

• In the case of a one-to-one interview, the interviewer should conduct the interview in a quiet room, away from other people, as this will increase the likelihood that the interviewee will open up

• It is good practice to begin the interview with some neutral questions to make the participants feel relaxed and comfortable, and as a way of establishing rapport

• Interviewees should be reminded on several that their answers will be treated in the strictest confidence. This is especially important if the interview includes topics that may be sensitive

writing good questions

• Clarity is key when designing questionnaires and interviews.

• if respondents are confused by or misinterpret particular questions, this will have a negative impact on the quality of the information received

Double barrelled question and double negatives

• a double barrelled question contains two questions in one; the issue being that respondents may agree with one half of the question and not the other

• Finally, questions that include double negatives can be difficult for respondents to decipher

independent group design

Different participants doing different conditions of the experiment.

weakness

• twice as many participants neeeded

• important differences between groups, than those deliberately manipulated by experimenter (Uncontrolled participant variables)

• can be minimised through random allocation of participants to each condition.

repeated measures

The same participants doing all the conditions

 weaknesses

• order effects, may do better or worse on the second attempt (boredom, fatigue, practice)

• can be controlled by counterbalancing where half participants start with experimental condition then control and other half do control then experimental

Matched pairs design

Different participants in different conditions, but they are matched with each other on one or more variables.

• time consuming

• difficult to find appropriate combination of participants to match on all important characteristics

participant variables

• Variation between participants can affect dependent variables

  • Can hide an effect

  • Can show an effect where none exists.

This is a problem with independent measures

• Control for this by random allocation to groups or

• Use repeated measures design or matched participants instead.

random allocation

• Random allocation of participants to experimental and control conditions is an extremely important process in research.

• Random allocation greatly decrease systematic errors, as every participant has equal chance of being chosen for either condition, so individual differences in responses or ability are far less likely to affect the results

order effects

Carrying out a task repeatedly leads to changes in performance:

• Deterioration as participants become tired/ bored

• Improvement due to practice

• Increase in demand characteristics

demand characteristics

These are cues in the research setting which can reveal the aims of the study and influence a participants behaviour. They help the participant work out what the researcher expects to find.

Counterbalancing

• Important control when using repeated measures

• Reduces order effects

• Half the participants do condition a/ then b

• Fully counterbalanced :ABBA

• Any order effects are then controlled for as they are balanced across the both conditions

attrition

• When participants drop out of a study data is lost

Fewer data - less powerful study

This can be a problem with matched participants (and repeated measures if there is a gap between conditions)

Loss of participants in these designs means losing data from both conditions

Representational generalisability

• The target population- is the group of people that the researchers want to investigate

• A group selected from a target population is a sample

• The findings can only be generalised to the population from which the sample is drawn.

Why is the sampling technique important?

• The sample should be representative of the population that you are trying to study

• If the sample is representative, then the findings can be generalised to that population. This is called population validity ( a type of external validity)

• Avoids selection bias. When participants for a study are not representative of the larger population being studied.

3 ways selection bias can occur

1. Participants self-select in the study

2. The researcher intentionally or unintentionally chooses certain types of people

3. Certain groups are excluded from the sample due to how participants are recruited.

the experimental method (CAUSALITY)

• In psychology, causality is the study of cause-and- effect relationships

• It involves understanding how one event, behaviour, or variable ( the cause) produces or influences another (the effect)

• By manipulating and independent variable and observing its effect on a dependent variable while controlling for other factors, they can gather evidence for a causal relationship

• Experiments aim to establish causality 

Extraneous variable

unwanted, outside influence that can affect the dependent variable (results)

• The participant

• The environment

• The experimenter

Dependent variable

The factor which the experimenter measures and expects to vary between the two groups or conditions as a result of the independent variable

Independent variable

-cause

The factor which the experimenter deliberately makes sure is different(manipulates) between the two groups or conditions.

confounding variables

If an extraneous variable is not controlled for and then affects the data of one of the conditions, then all the findings of that condition are affected, it has become a confounding variable.

Operationalisation variables

A lot of behaviours psychologists are interested in are abstract and hard to define. Therefore, the researcher must ensure that  the variables being investigated are measurable and defined. That is, they must be operationalised

The Null Hypothesis:

A null hypothesis states that there will be no difference or relationship between the variables.

The Alternate Hypothesis

A statement that makes a prediction that something will happen in a study is called an “alternate hypothesis”. A hypothesis should be TESTABLE (it includes the IV and the DV).

A directional (or one-tailed) hypothesis

states the direction of the difference between the two conditions or two groups of participants. It will include words like more or less, higher or lower, faster or slower etc.

A non-directional (two-tailed) hypothesis

does not state the direction, it merely states that there WILL be a difference.

 

random sampling

every memeber of the target population has equal chance of being selected

• finds a random sample without bias from researcher

• larger variation of participants

however

• time consuming

opportunity sampling

• means selecting individuals from population the research is focused on, but those that are willing and available to take part

• easy

• convenient

• useful when limited time

however

• bias is high risk

volunteer sampling

• participants are self-selected. they volunteer

systematic sampling

• nth number of target population is selected, every 3rd person on a register

sampling frame

list of people in target populationm organised into order.

stratified sampling

• composition of sample reflects proportions of people in a certain sub group (strata) within the target population to the wider population

Laboratory Experiment

controlled environment within which the researcher manipulates the IV and records the effect on the DV, whilst maintaining strict control on the extraneous variables

strengths of lab experiment

 - high control on extraneous variables which ensures any effect on the dependent variable so likely to be the result of an manipulation of the IV. HIGH ENTERNAL VALIDITY

 

-Replication is possible, as it is vital to see if the results are valid and not a one off

weaknesses of lab experiment

- may lack generalisability, as the environment is artificial. (low external validity)

• High chance of unnatural behaviour

• Doesn't represent real-life experience  so low mundane realism

field experiment

natural setting within which the researcher manipulates the IV and records the effect on the DV

strengths of field experiment

- high mundane realism than lab experiments as environment is more natural

-Behaviour will be more valid and authentic

• High external validity

weaknesses of field experiment

 -loss of extraneous variables, this means that the cause and effect between the IV and the DV may be more difficult to establish and precise replication may not be possible

• Ethical issues, if participants are unaware of being studied they cant give consent and therefore may be an invasion of privacy

Natural Experiment   

the change in the IV is not brought about by the researcher but would have happened even if the researcher had not been there. The researcher records the effect on the DV

Natural Experiment   strengths

- allows for research that may not be practical or ethical, such as studies of institutionalised Romanian orphans

• High external validity as they involve the study of real life issues and problems

Natural Experiment   weaknesses

 natural occurring event may happen very rarely which decrease opportunities for research and limit the scope for generalising findings

-Participants may not be randomly allocate to experimental conditions, only applies when there is an independent group design

-the research is less sure whether the IV affected the DV

Quasi Experiment 

almost an experiment. The IV has not been determined by anyone, the 'variables' simply exist, such as being old or young

Quasi Experiment strengths

• carried out under controlled conditions and therefore share the strengths of a lab experiments

•  high control on extraneous variables which ensures any effect on the dependent variable so likely to be the result of an manipulation of the IV. HIGH ENTERNAL VALIDITY

   

  -Replication is possible, as it is vital to see if the results are valid and not a one of

Quasi Experiment weaknesses

Like natural experiments, they cannot randomly allocate participants to conditions and therefore there maybe confounding variables 

internal valdiity

is the level to which we are confident that the independent variable affected the dependent variable.

external validity

is whether we are able to generalise beyond the research – being able to apply the findings from an experiment to other situations, people and other times.

Different places or setting ecological validity

Different people or populations population validity

Different times e.g. 1950s temporal validity 

correlation

assocation - extent to which two variable are related

used to establish whether there is a relationship between 2 co-variables

It involves the measurement of two variables (co-variables) and does NOT involve any manipulation of these

Experiment

IV is deliberately manipulated to see the effect on the DV. Without this no cause and effect can be established

Correlation

variables are not deliberately manipulated but simply measured

Therefore, no cause and effect can be established. No conclusion can be made about one variable causing the other.

Correlational hypotheses

Unlike an experimental hypothesis, there is no IV and DV, so the hypothesis needs to predict the RELATIONSHIP  between two variable

curvilinear correlation

The curvilinear correlation starts off positive, to a certain point and then becomes a negative one.  It is still a predictable one.

correlation co-efficient

-1 is the perfect negative correlation

+1 is the perfect positive correlation

Above 0.80 and -0.81 is a strong relationship

strengths of correlation

• It can be a USEFUL technique in psychological research as there are so many variables that cannot be manipulated for either ethical or practical reasons.

• It can also act as a starting point for research, in that once relationships have been established, more research can be conducted (such as an experiment) to investigate them further.

• Can be replicated to confirm findings.

Weakness of the Correlation:

A correlation ONLY demonstrates the strength and direction of the relationship.

• It CANNOT establish a cause-and-effect relationship, that is changes to one variable causes an effect on the other variable.

• There may be intervening variables that can explain why the co-variables are linked.

 

For example, what other factors may contribute to a relationship between memory recall and anxiety, other than the co-variables?

• Locational factors- noise, temperature, light intensity

• Concentration

• Age

• IQ

• stress

observation

• Involves watching and recording peoples behaviour

• Usually carried out in peoples natural behaviour in their natural environment, but not always

• Observations are conducted in a more systematic way that everyday observations of life.

 

Researcher must have a clear idea of what type of behaviour to observe in order for findings to be valid- operationalised behavioural categories

Behavioural categories

• Observable, measurable and self-evident as well as being exclusive with no overlaps

• Or they may use a scale to indicate a degree of behaviour

Operationalisation

breaking the behaviour studied into a set of components

Objective

the researcher should not have to make inferences about the behaviour

Naturalistic observation

Naturalistic observation - where lab studies are difficult or less useful, researchers can observe subjects in their real-life environment

• Natural environment without control over variables

• No interference from researcher

• People make their own choices about how they behave

Naturalistic observation strength

• High degree of natural degree- finding can be generalised to everyday life

• Likely to be high in ecological validity

Naturalistic observation weakness

• Hard to replicate

• Less reliable as variables are not controlled

• No manipulation of variables means that the cause and effect relationship cannot be established

• Because of lack of control, extraneous variables may account for the behaviour observed

Controlled environment

The have been organised by the researcher for observation

• participants are likely to know they are being studied, but not always

• Reduces the naturalness of the environment and the naturalness of the behaviour being investigated

 

Ainsworth add in from PPT

Controlled environment strength

• high level of control

• Easier to establish cause and effect relationships

• Can be easily replicated - easy to test its reliability

Controlled environment weakness

• The environment is artificial- participants may not show natural behaviour - lack validity

• Demand characteristics if they are aware of being studied

Overt observations

Observations that takes place with the full knowledge and awareness of participants

• They know that their behaviour is being watched and recorded

• Since this is likely to have an effect on the naturalness of participants behaviour, researchers try to be unobtrusive

Overt observations strengths

Ethically sound as participants know that they are being observed and have given consent

Overt observations weaknesses

Participants may not behave naturally - demand characteristics

Covert observation

Without the knowledge or awareness of participants knowing they are being observed

• Hidden viewpoints, secret cameras or two way mirrors

• Such behaviour must be public and happen anyway for the observation to be ethical

Covert observation strength

More valid results from participants as natural behaviour is being observed

Covert observation weakness

• Not ethically sound to observe participants behaviour in private settings

• Lack of informed consent means that there are ethical issues

Participant observations

Data is gathered by psychologists whilst being part of the observed group or situation

• In both covert and overt observations, the researcher may be a participants, but often this is unknown to the other participants

Participant observations strengths

• Greater insights into behaviour gained by being in group

• Increased validity of findings