Psychology - research methods

What is the aim of the experiment

A general statement about what the researcher intends to investigate; the purpose of the study

e.g. to investigate whether drinking energy drinks makes people more talkative

Define the experimental method

involves manipulating one variable to determine if these changes cause changes in another variable. this method relies on high levels of control to test a hypothesis

What is a hypothesis

A clear, precise, testable statement that is made at the start of the study that clearly states the relationship between variables to be investigated.

e.g. drinking an energy drink causes people to become more talkative

What are the two types of hypothesis

• Directional

  • states the direction of the difference or relationship

  • include words like more or less, higher or lower, faster or slower etc

  • e.g. people who drink water are less talkative than those who drink an energy drink

  • used when the findings of previous research suggest a particular outcome

• Non-directional

  • simply states that there is a difference between conditions or groups of people - nature of difference is not specified (does not state the direction)

  • e.g. people who drink an energy drink differ in terms of talkativeness compared with people who don’t drink energy drinks

  • used when there is no previous research or findings from earlier studies are contradictory

What variable does the researcher manipulate in an experiment

Independent variable

Measures the effect of this change on the dependent variable

Define operationalisation

Clearly defining variables in terms of how they can be measured

What is an operational hypothesis

Clearly defines what the variables of interest are and how the different variables are related to each other

e.g. the group that drinks an energy drink will be chattier than the group that drinks water —> after drinking 300ml of energy drink participants say more words in the next five minutes than the participants who drink 300ml of water

What is a independent variable

An aspect of the research situation that is manipulated by the researcher, or that changes naturally

What is a dependent variable

The variable in the experimental situation that is measured by the researcher, and should be caused by the independent variable

What is an extraneous variable

Any variable other than the IV, that might potentially interfere with the DV if it is not controlled

• participant variables - any individual differences between participants that may affect the DV

• situational variables - features of the experimental situation that may affect the DV

What is a confounding variable

Any variable other than the IV that may HAVE affected the DV so that we can not be sure of the true source of the changes to the DV - these have not been controlled and are found after the study (a systematic error)

What are demand characteristics

Any cue from the researcher or from the research situation that may be interpreted by participants as revealing the purpose of the investigation. This may lead to the participant changing their behaviour within the research situation

What are investigator effects

Any effect of the researchers behaviour (conscious or unconscious) on the research outcome (the DV). This may include everything from the design of the study, to the selection of, and interaction with, the participants during the process

What is randomisation

The use of chance in order to control the effects of bias when designing materials and deciding the order of conditions. Steps we can take to minimise the effect of EV’s and CV’s on the DV

What is standardisation

Using exactly the same, formalised procedures and instructions for all participants in a research study

What is internal validity

How much do the findings of the dependent variable have to do with the independent variable and not other factors

• did you participants respond to demand characteristics and act the way that people expected them to

• e.g. CBT helps reduce depression - however this may be the client-patient relationship and not the CBT itself (lack of internal validity)

What is external validity

All about whether our results can be generalised beyond the study e.g. other settings, other populations of people or even other eras in time

• population validity - can the results be generalised to the general population

• ecological validity - whether or not the environment in which the research was conducted in can be generalised to real life

There is a lack of mundane realism when the task that the participants are asked to perform is not something that would be asked of them during every day life so the truth of the findings is limited

What is temporal validity

The idea that the findings of a study or concepts of a particular theory hold true over time

• e.g. Asch’s research on conformity was originally tested in a very conformist time in American history so lacks temporal validity

What are the two tests for testing validity

• face validity - when an independent expert looks at the measures being used and assesses whether it will measure what it has set out to measure

• concurrent validity - comparing the new procedure with a similar procedure that has been done before where validity has already been established (if the scores correlate as a strong positive correlation [+0.8] then the test is probably valid)

How can we improve validity

• Experimental research

  • using a control group gives the experimenter something to compare the changes in the dependent variable due to the effects of the independent variable

  • procedures may be standardised to minimise effects of participant and investigator effects

  • use of single blind trials and double blind trials reduce demand characteristics

• Observations

  • observations with minimal input from observer increases validity - better if observer is covert

  • ensure that behavioural categories are not too broad, not overlapping or ambiguous to increase validity

• Questionnaires

  • many questionnaires include a lie scale within questions - may consist of repetitions of the same or closely similar items to check for consistency of responses (reduces effects of social desirability bias)

  • ensure all responses are anonymous

• Qualitative methods

  • can be seen as more valid than quantitative methods, because depth and details associated with case studies and interviews better reflects the participants reality

  • validity is further enhanced by triangulation - the use of a number of different sources as evidence e.g. data from interviews with family, friends, personal diaries, observations etc.

What is reliability

if a measure can be repeated and the same result is found, the that measure is reliable

What is the difference between validity and reliability

• reliability - The extent to which the results can be reproduced when the research is repeated under the same conditions.

• validity - The extent to which the results really measure what they are supposed to measure.

How do we assess reliability

• 1st measure

  • external reliability - produce same results each time test is carried out

  • test-retest method - do the same test with the same participants again at a different time (enough time to prevent pps remembering og answers but not so much time that results would be affected by a change in attitude/opinion/ability)

  • correlation between two sets of scores (+0.8 = high correlation co-efficient = reliable)

• 2nd measure

  • inter-observer reliability - relevant to observational research, more than one person has seen the behaviours and believe there is a consistency on what was seen. may use behavioural categories to ensure they are looking at the same behaviours

  • can be used with content analysis and interviews

  • 
    

  • (content analysis is a research tool used to determine the presence of certain words, themes or concepts within some qualitative data)

(content analysis is a research tool used to determine the presence of certain words, themes or concepts within some qualitative data)

What is internal reliability

describes the internal consistency of a measure, such as whether the different questions in a questionnaire are all measuring the same construct

this type of reliability refers to the extent to which a measure is consistent within itself

• if a test has people scoring really high on one part but not on the other then it has low internal consistency

How can we improve reliability

• Questionnaires

  • should be measured with test-retest method and then data compared

  • correlation coefficient needs to be +0.8 to be reliable

• Interviews

  • best way is to use same interviewer each time

  • each interviewer has to be trained in order to avoid asking leading or ambiguous questions

  • easier done in structured interviews due to fixed questions whereas unstructured are less likely to be reliable

• Experiments

  • lab experiments more reliable due to controls over other variables due to standardised procedure

  • reliability may be affected if people are tested under even slightly different conditions

• Observations

  • improved by operationalising behavioral categories - making sure they are measurable and self-evident

  • categories should not overlap

What is experimental design

The different ways in which the testing of participants can be organised in relation to the experimental conditions

Describe the independent group design

• when two separate groups of participants experience two different conditions of the experiment

• e.g. one group drinks water and the other drinks an energy drink

• strength - order effects are not a problem

• weakness - the participants who occupy the different groups are not the same - individual differences

Describe the repeated measures design

• all participants experience both conditions of the experiment

• e.g. each participant experiences condition A (the energy drink condition - experimental condition) and then later, condition B (the water condition - control condition)

• strength - participant variables are controlled and fewer participants needed

• weakness - order effect arise because repeating two tasks could create boredom or fatigue so may cause deterioration in performance on the second task, so it matters what order the tasks are in

Describe the matched pairs design

• participants are together on a variable or variables relevant to the experiment

• e.g. participants in a memory study may be matched on their IQ

• strength - order effects and demand characteristics are less of a problem

• weakness - matching may be time consuming and expensive (especially is a pre-test is needed) so this is less economical than other designs

Describe the laboratory experiment

• conducted in highly controlled environments - not always a lab

• strength - high control over extraneous variables, replication is more possible due to the high level of control

• limitations - experiments may lack generalisability - lab environment is artificial and not like everyday life (low external validity), participants are usually aware they are being tested and therefore there are demand characteristics

Describe field experiments

• the IV is manipulated in a natural, more everyday setting

• strength - higher mundane realism - more genuine, authentic behaviour, high external validity as participants may be unaware they are being studied

• limitation - loss of control of extraneous variables, ethical issues - participants being unaware means they cannot consent

Describe natural experiments

• when the researcher takes advantage of a pre-existing independent variable - natural as the variable would have changed even if the experimenter was not interested

• strength - high external validity - involve study of real-life issues and problems as they happen (e.g. effects of a natural disaster on stress levels), provide opportunity for research that may not otherwise be undertaken for practical or ethical reasons

• limitations - a naturally occurring event may only happen very rarely - may limit scope for generalising findings, participants may not be randomly allocated so researcher is less sure whether the IV affected the DV

Describe quasi experiments

• have an IV that is based on an existing difference between people e.g. age or gender - no one has manipulated this variable, it simply exists

• e.g. if anxiety levels of phobic and non-phobic patients were compared, the IV of having a phobia would not have come about through any experimental manipulation

• strength - controlled conditions (like lab experiment)

• limitation - confounding variables due to inability to randomly allocate participants to conditions

What is the difference between objectivity and subjectivity

Objectivity

• facts rather than opinion

• true for everyone

• dispassionate

Subjectivity

• opinion rather than fact

• not universal

• emotive

Describe the empirical method

• objectivity = base of empirical method

• empirical methods emphasise the importance of data collection based on direct, sensory experience

• e.g. experimental method and observational method

• a theory cannot claim to be scientific unless it has been empirically tested and verified

What is replicability

findings must be shown to be repeatable across a number of different contexts and circumstances - allows us to see the extent to which findings can be generalised

replication has an important role in determining the validity of a finding

What is falsifiability

Genuine scientific theories should hold themselves up for hypothesis testing and the possibility of being proven false

• Karl Popper drew a line between ‘good science’ in which theories are constantly challenged and ‘pseudosciences’ which couldn’t be falsified e.g. astrology

Define paradigm and paradigm shift

Paradigm = a clear, distinct concept accepted by most people in a scientific field e.g. evolution or the planets orbit the sun

Paradigm shift = when there is too much contradictory evidence to ignore so a group of researchers begin to question the accepted paradigm e.g. it used to be accepted that the sun revolves around the earth

What types of sampling is there

1. random sample - list of members is obtained, all names on list are assigned a number, sample generated through use of a lottery method

2. systematic sample - every nth member of the target population is selected

3. stratified sample - researcher identifies the different strata that make up a population, proportions are worked out for the sample to be representative, participants to make up each stratum are selected using random sampling

4. opportunity sample - taking anyone who is willing and available

5. volunteer sample - participants selecting themselves to be part of the sample

What is an evaluation for each type of sampling

random

• strength - free from researcher bias

• weakness - difficult and time consuming

systematic

• strength - avoids researcher bias

• weakness - greater risk of data manipulation

stratified

• strength - avoids researcher bias, produces representative sample - generalisation of findings is possible

• weakness - cannot reflect all the ways people are different - complete representation is not possible

opportunity

• strength - convenient, saves time and effort

• weakness - unrepresentative of target population, researcher bias

volunteer

• strength - easy, minimal input from researcher, less time consuming

• weakness - volunteer bias, may attract a certain ‘profile’ of person

What are ethical issues

these arise when a conflict exists between the rights of the participants in research studies and the goals of the research to produce authentic, valid and worthwhile data

What are the four ethical issues

Informed consent

• participants need to know what they are getting themselves into

• they should be told: the aims, the procedure, their rights, what their data will be used for and by whom

Deception

• deliberately misleading or withholding information from a participant at any stage of a study

• if a participant has not received adequate info about the study they cannot have said to be given informed consent

Protection from harm

• participants should NEVER be placed at any more risk than they would in their every day lived - should be protected from physical and psychological harm at all times

• psychological harm includes: being embarrassed, made to feel inadequate, being placed under undue stress or put under pressure

Privacy and confidentiality

• participants have the right to control info about themselves - right of privacy

• if this right is breached then confidentiality must be protected

• confidentiality is the participants right, under the Data Protection Act, to have any personal data protected

• privacy clause extends to the place the experiment is carried out in, so that institutions or geographical locations are not named

What are alternative ways of getting consent

• presumptive consent - researchers ask a similar group of people to the participants and if they agree the study is acceptable then consent from the actual participants is presumed

• prior general consent - participants consent to being in a number of studies including one that will involve deception

• retrospective consent - participants give consent during debriefing

Describe how to deal with deception and protection from harm - debriefing

• at end of study participants should be given a full debrief

• here they should be made aware of the true aims of the study and given any details that were withheld from them

• they should be given reassurance they their data will be protected and that they have the right to withhold their data if they wish

• if a participant is concerned about their behaviour or responses to an investigation, they should be made aware that their behaviour was typical or normal

• in the case that a participant feels they have been subject to harm, counselling should be made available to them

What is done to deal with informed consent

• participants should be issued with a consent letter or form detailing all relevant information

• needs to be signed and dated

• under 16’s must have parental consent

What is the BPS Code of Ethics

a quasi-legal document produced by the British Psychological Society that instructs psychologists in the UK about dealing with participants. it is built around 4 major principles: respect, competence, responsibility and integrity

What is a pilot study and why is it used

A small scale version of an investigation that takes place before the real investigation is conducted. The aim is to check that procedures, materials, measuring scales etc, work and allow the researcher to make any changes or modifications if necessary 

What 

• Trial run 

• Smaller number of participants 

• In self report experiments 

• In observations 

Why 

• Allow for adjustments to be made to the experiment 

• Could save money, time, resources, energy etc 

• Ensures that the actual experiment is not wasted 

• Ensures that the experiment is getting a true set of results 

• Allows for control of extraneous and confounding variables 

What is a single blind procedure

• participants are not told the aim of the research at the beginning of the study

• attempts to control for the confounding effects of demand characteristics

What is a double blind procedure

• neither the participant nor the researcher who conducts the study is aware of the aims of the investigation

What are control groups used for

comparison - if the change in behaviour of the experimental group is significantly greater than that of the control group, the researcher can conclude that the cause of this effect was the independent variable

What is participant observation

The researcher takes part in the investigation as a member whose behaviour he/she is watching and recording e.g. Lorenz and his geese

• strength - researcher can experience the situation as the participants do - increased insight & increased validity of findings

• researcher may lose objectivity - ‘going native’

What is non-participant observation

The researcher remains outside of the group whose behaviour he/she is watching e.g. Bobo doll study

• strength - allows researcher to maintain an objective psychological distance from their participants

• weakness - researcher may lose valuable insight to be gained if they were actually taking part in it

What is covert observation

• observations in which participants are unaware they are the focus of the study

• behaviour is observed in secret

• behaviour must be public and happening anyway if the observation is to be ethical

• strength - no problem of participant reactivity, behaviour will be natural, increases validity of data

• weakness - ethics may be questioned

What is overt observation

• when participants are aware their behaviour is being observed and have given their informed consent before

• strength - ethically acceptable (given informed consent)

• weakness - knowledge they are being observed may act as an influence on their behaviour (observer effects and participant reactivity become an issue)

What are controlled observations

• high control over extraneous variables

• systematic, using a standardised procedure

• objective, using a quantitative coding system

• participants know they are under observation

e.g. Ainsworth Strange Situation, Asch’s Line study

• strength - control over EV’s, increased reliability and credibility, high internal validity

• weakness - participants know they are being watched, demand characteristics lowers the internal validity

• weakness - often artificial tasks and stimuli, limited application, findings are not generalisable, lower external and ecological validity

What are naturalistic observations

• field studies

• looks at spontaneous behaviour

• carried out in a natural environment

• participants are not aware of observation

e.g. Rutter’s Romanian Orphanage study

• strength - participants are not aware of observation, low chance of demand characteristics, high ecological validity

• strength - tasks often have more real life application, easier to generalise findings, higher external validity

• weakness - low control over extraneous variables, low degree of control, low internal validity

What is structured observation

• the researcher used various ‘systems’ to organise observations

• e.g. a sampling technique or behavioural category

• observations can be quantified at the end

• strength - quantitative data, observer bias is less likely

• weakness - not much depth or detail

What is unstructured observation

• every instance of a behaviour is recorded in as much detail as possible - useful if behaviours you are interested in do not occur very often, are small in scale and involve few participants

• researcher observes and records as much detail as they can

• no system to follow

• strength - lots of depth and detail, qualitative data

• weakness - risk of observer bias, only used in small scale studies

What are the two types of sampling methods

• event sampling - a target behaviour is established then the researcher records this event every time it occurs, counting the number of times a behaviour occurs

• time sampling - a target individual or group is first established then the researcher records their behaviour in a fixed time frame for example every 60 seconds

What is the AO3 for time sampling

• strength - reduces number of observations

• strength - more structured and systematic

• weakness - may be unrepresentative

• weakness - researcher may miss important details

• weakness - may not reflect whole behaviour

What is the AO3 for event sampling

• strength - may record infrequent behaviour

• strength - researcher could pick up on behaviours that do not occur at regular intervals - such behaviours may be missed in time sampling

• weakness - complex behaviours oversimplified

• weakness - if event is too complex, important details may not be recorded

What is inter-observer reliability and how is it achieved

observers should be trained to establish inter-observer reliability to ensure the observers are consistent in their judgments and that the data they record is the same or similar

e.g. on a scale of 1-10 some may observe behaviour they consider a 4 whereas someone else considers it a 6

achieved by familiarising themselves with the behavioural categories, running a pilot study, comparing data and finally recording and analysing data and inter-observer reliability is calculated

Evaluate inter-observer reliability

Strengths

• data more objective and unbiased - results more credible

• two observers means two opinions

• results more valid if they agree

Weaknesses

• observers have to be trained - time and money

• two observers may be easy to agree but there may be more than two

• more observers = more disagreements

What is quantitative data and evaluate

• data expressed numerically e.g. the amount of words people were able to accurately recall in a memory test

Strength

• more objective and less open to bias

• easier to analyse than qualitative

Weakness

• lacks detail

• may not represent real feelings

What is qualitative data and evaluate

• data expressed in words

• thoughts, feelings and opinions

• the transcript of an interview, diary notes from a counselling session etc

Strengths

• more subjective so rich in detail

• higher external validity that quantitative

Weaknesses

• hard to analyse

• the interpretation is often subjective and may be open to researcher biasW

What is primary data and evaluate

• original data that is collected specifically for the purpose of the investigation by the researcher themselves

Strengths

• fit for purpose

• authentic and less likely to be misinterpreted or used for the wrong reason

Weaknesses

• time consuming to collect

• can be expensive and requires a lot of effort

What is secondary data and evaluate

• data that has been collected by someone else, that already exists before the investigation has been planned

• has usually already been subjected to statistical testing and the significance is already known

Strengths

• inexpensive

• less effort required on the researchers part

Weaknesses

• much variation to the quality and accuracy of data

• can be outdated or incomplete

• could be somewhat irrelevant to the field of study

What are behavioural categories

• a breakdown of the target behaviours - these should be precisely defined and made observable and measurable

• e.g. target behaviour ‘affection’ may be broken down into categories such as hugging, kissing, smiling, holding hands etc.

• strength - more structured and objective data collection

• weakness - categories may be ambiguous

What are questionnaires and evaluate

• a set of written questions designed to collect information

• can discover what people think or feel

• always predetermined (structured)

• can provide qualitative or quantitative data

strength -

• cost effective and quick to distribute

• gather large amounts of data because they can be distributed to large numbers of people

• data is straightforward to analyse

• respondents may feel comfortable to reveal personal info

• reduces experimenter bias

limitations -

• responses may not always be truthful (social desirability bias - give answers that make themselves look better)

• can take time to design

• sample can be biased due to who is willing to fill it out

What do you need for a good questionnaire

• clarity - do not use double negatives or double barreled questions

• bias - do not use leading questions which makes one answer seem more attractive than the other

• analysis - questions need to be written so they are easy to analyse

What are the three types of interview

Structured - pre-determined questions, no deviation from og questions

Pros

• easily repeated

• different people can be compared due to standardised questions

• answers easier to evaluate

Cons

• interviewer bias

• comparability difficult if interviewer behaves differently or different interviewer

Unstructured - new questions developed during course, interviewer may begin with general aims but subsequent questions develop on the basis of the answers that are given

Pros

• more detailed info

Cons

• requires interviewer with more skill - more expensive

• questions may lack objectivity

• interviewer bias

Semi-structured - falls between the two, list of questions that must be asked but interviewer is able to ask follow up questions based on responses

Define correlation

A mathematical technique in which a researcher investigates an association between two variables, called co-variables

plotted on scattergrams

What is the difference between correlations and experiments

correlation - researcher looks for associations among naturally occurring variables - no maniuplation

experiments - IV is manipulated and the effect on the DV is measured

Evaluate correlations

Strength

• useful as a starting point for further research

• relatively quick and economical to carry out

Weaknesses

• can only tell us how variables are related, not why

• there may be a third variable that is not taken into consideration

• vulnerable to misuse - media could present a correlation as a fact when it is not

What is a correlation coefficient and what is it for

• a numerical value between -1 and +1

• shows us the strength and direction of the relationship between 2 variables

• we get it from calculating a statistical test of correlation e.g. Spearman’s rho or Pearsons r

What is ordinal data

• ranked data - ordered in some way

• does not have equal intervals between each unit

• lacks precision

• based on subjective opinions rather than objective means

• e.g. asking everyone on a scale of 1-10 how much they like pizza

• uses Spearman’s rho

What is interval data

• based on numerical scales that have units of equal, precisely defined size

• can only get interval data from ‘public scales of measurement’ e.g. rulers, thermometers etc.

• uses Pearson’s r

What is probability

a measure of the likelihood that a particular event will occur, where 0 indicates statistical impossibility and 1 indicates statistical certainty

What is significance

a statistical term that tells us how sure we are that a difference or correlation exists, it indicates that the association between two or more variables is strong enough for us to accept the alternative (experimental) hypothesis and reject the null hypothesis

Alternative vs null hypothesis

Alternative = directional or non-directional hypothesis that the researcher has stated e.g. age affects mathematical ability

Null hypothesis = states there is no significant difference between specified populations, any observed difference being due to sampling or experimental error e.g. age has no effect on mathematical ability

What is the significance level

the point at which the researcher can claim to have discovered a significant difference or correlation in the data

• usual level for psych is 0.05 (5%) P<0.05 - means that the probability that the result occured by chance is equal to or less that 5%

• some may use <0.01 for things like drug trials that can’t be repeated

the lower the p value, the more statistically significant the result is

What is the sign test and when do we use it

• a calculation used to determine whether a difference is statistically significant

• used when:

1. looking for a difference rather than association

2. experiment would’ve used repeated measures design

3. nominal data

What is the Rule of R

if the statistical tests name has an R in it, then the calculated value must be equal to or moRe than the critical value

calculated value > critical value for test to be significant

if it doesnt, then it has to be less than or equal to

What are type 1 and type 2 errors

Type 1

• a ‘false positive’

• you reject the null hypothesis and accept the alternative hypothesis but you shouldn’t have done

• results were caused by random variables

• more likely to make this error if the significance level is too high

Type 2

• a ‘false negative’

• you have kept the null hypothesis and rejected the alternative hypothesis but you should have kept the alternative hypothesis

• more likely to make this error if the significance level is too low

How would you choose a statistical test

URR Carrots Should Come Mashed With Swede Under Roast Potatoes NOI

What is standard deviation

• a more sophisticated measure of dispersion

• the score tells us how far scores deviate from the mean

• the larger the standard deviation, the greater the dispersion or spread withing a set of data