research methods terminology

experimental method

manipulation of IV to measure effect of DV

aim

general statement of what the researcher intends to investigate

hypothesis

clear, precise, testable statement stating relationship between variables to be studied

directional hypothesis

researcher makes clear, specific difference that is anticipated.

non-directional hypothesis

states that there is a difference but does not state the direction

variables

anything that changes or varies within an investigation

independent variable

aspect of the experimental situation that is manipulated of changes naturally so the effect on the DV can be measured

dependent variable

variable measured by researcher

operationalisation

clearly defining variables in terms of how they can be measured

extraneous variable

any variable apart from the IV that could affect the DV if not controlled

confounding variable

type of EV that changes systematically with the IV. Can’t tell if the change to the DV is because of the IV or CV

demand characteristics; participant reactivity

when participants spend the time trying to figure out the experiment rather than take part

investigator effects

any effect of the investigators behaviour that may give away aim of the study

randomisation

using chance methods to control effects of bias

standardisation

using the exact same formalised procedures and instructions for all participants in a research study

experimental design

participants taking part in an experiment

independent groups design

2 separate groups experience 2 different conditions of the experiment eg different levels of the IV

independent groups evaluation

limitation - different participants in each group so different participant variables which reduces validity

limitation - expensive + time consuming as more participants needed

strength - order effects aren’t a problem, less likely to guess aims

repeated measures

all participants experience both conditions of the experiment

repeated measures evaluation

limitation - each participant has to do at least 2 tasks

limitation - order effects could arise + create boredom - ABBA used

limitation - demand characteristics likely as they could figure out study

strength - participant variables are controlled so higher validity

matched pairs design

participants paired together on variables relevant to experiment, both do different conditions of the IV

matches pairs evaluation

strength - order effects and demand characteristics less of a problem

limitation - participants can never be matched exactly, even identical twins

limitation - time-consuming and expensive

random allocation

participants randomly allocated to different experimental conditions in independent groups design eg name out hat

random allocation evaluation

strength - no bias

limitation - may not be representative

counterbalancing

attempt to control order effects in repeated measures design eg ABBA

counterbalancing evaluation

strength - reduces demand characteristics and boredom

limitation - only attempts to balance out effects, not remove completely

laboratory experiment

conducted in highly controlled environments in a laboratory

laboratory experiment evaluation

strengths - control over confounding variables, high internal validity, replication is possible

limitations - lack generalisability, low external validity, demand characteristics, low mundane realism

field experiment

IV manipulated in a natural everyday setting, researcher goes to participants usual environment

field experiment evaluation

strengths - higher mundane realism, high external validity

limitations - precise replication not easy, ethical issues - consent, invasion of privacy

natural experiment

researcher has no control of an IV on a DV and cant change it. IV is natural and can still be in the lab or field. DV could also be natural or devised

natural experiment evaluation

strengths - provide new opportunities for research, high external validity

limitations - limited generalisability, may not be randomly allocated if independent groups, if in lab it lacks realism - demand characteristics

quasi experiment

IV based on existing difference between people eg age. IV cant be changed. DV may be naturally occurring and still in lab or field

quasi experiment evaluation

strengths - replication possible, controlled conditions

limitations - confounding variables possible, IV not deliberately changed so results unclear

population

group of people who are the focus of the researcher’s interest, from which a smaller sample is drawn

sample

drawn from the target audience and is presumed to be representative of that population

sampling techniques

random, systematic, stratified, opportunity, volunteer

random sampling + evaluation

lottery method - name out of a hat, all members of target population have an equal chance of being selected

strengths - unbiased so confounding/extraneous variables are divided equally in groups = increase internal validity

limitations - difficult + time consuming (complete list of target population may be difficult to obtain), sample may still be unrepresentative, participants could refuse to take part - affects sample

systematic sampling + evaluation

sample frame is produced eg target population in alphabetical order, sampling system is nominated eg every 3rd, researcher works through sampling frame until sample is complete

strengths - objective as researcher has no influence over who is chosen

limitations - time-consuming and participants could refuse to take part

stratified sampling + evaluation

composition of sample reflects proportions of people in certain subgroups, proportions needed for the sample to be representative are worked out

strengths - convenient, less costly for time/money (no need for list of entire target population)

limitation - unrepresentative of target population as is drawn from specific area eg one street so findings cant be generalised, researcher has complete control of selection of participants = researcher bias

volunteer sampling + evaluation

participants selecting themselves to be part of the sample

strengths - easy as requires minimal input from researcher, less time-consuming, participants are more engaged

limitations - volunteer bias as participants likely to be more curious and may want to please researcher

bias

when groups are under or over represented within a sample - limits generalisability

generalisability

extent to which findings/conclusions from a particular investigation can be broadly applied to the population - possible if sample is representative of the target population

informed consent

making participants aware of aims, procedures and their rights beforehand

deception

deliberately withholding or misleading information

protection from harm

participants not placed in high risk situations (mental or physical)

privacy

participants can control information about themselves

confidentiality

our right to have personal data protected

BPS code of ethics

quasi-legal document by BPS (British Psychological Society) that instructs psychology in UK about what behaviour is acceptable when dealing with participants

briefing

informing participants about study beforehand

debriefing

information participants about study afterwards

anonymity

participants personal information is not withheld

right to withhold data

participant has option to not have their data included

pilot study

small-scale version of an investigation that takes place before the real thing, checks the procedures, materials, measuring scaled etc. Allows researcher to make changes if needed

single blind procedure + evaluation

participants not told aim or details of experiment till the end, researcher does know

strength - removes demand characteristics

limitation - researcher bias still likely

double blind procedure + evaluation

neither participant nor researcher know the aims or details

strength - reduces bias and demand characteristics

strength - applied in drug studies eg placebo

naturalistic observation

takes place in setting or context where target behaviour would usually occur. All aspects are free to vary

naturalistic observation evaluation

strengths - high external validity as findings can be generalised to everyday life

limitations - lack of control over research situation so replication is difficult, can’t control confounding/extraneous variables

controlled observation

takes place within a structured environment eg where some variables are managed

controlled observation evaluation

strengths - confounding/extraneous variables less of a factor so replication is easier

limitations - findings cant be generalised to everyday life

covert observation

participants are unaware that they are the focus of the study and their behaviour is being observed

covert observation evaluation

strengths - reduced demand characteristics, behaviour is natural which increase internal validity

limitation - ethics are questioned (people may not want their behaviours noted down)

overt observation

participants are aware they are being observed and give informed consent first

overt observation evaluation

strengths - more ethically acceptable as participants consent

limitations - knowing they’re being observed could cause demand characteristics

participant observation

observer becomes part of the group being studied

participant observation evaluation

strengths - better insight into lives of those studied which increases external validity of findings

limitations - researcher could lose objectivity if too involved

non-participant observation

researcher remains separate from group being studied

non-participant observation evaluation

strength - researcher can maintain objective psychological distance from participants

limitation - loss of closer insight into lifestyle

behavioural categories

when a target behaviour is broken up into components that are observable and measurable

behavioural categories evaluation

strengths - makes data more structured and objective

limitations - categories must be clear, observable, measurable and self-evident, categories can’t overlap

event sampling

target behaviour or event is established then records every time it occurs

event sampling evaluation

strength - detailed data collection

limitation - if environment is busy then could become overwhelming and miss details

time sampling

target individual or group is established then researcher records behaviour in fixed time frame

time sampling evaluation

strength - reduces number of observations made

limitation - may be unrepresentative of whole observation eg something important/interesting may happen outside of the time frame

self-report technique

any method where participant states or explain their own feelings, opinions, behaviours and/or behaviours

questionnaire

pre-set list of written questions in order to assess dependent variable

questionnaire evaluation

strengths - cost effective, large amount of data quickly, can be done without researcher present, straightforward to analyse

limitations - responses not always truthful, demand characteristics (social desirability bias), response bias (not read properly), acquiescence bias (saying yes no matter what)

structured interview

set of predetermined questions asked in fixed order. like questionnaire but in person

structured interview evaluation

strengths - straightforward to replicate, reduced differences between interviewers, analysis of data is easier

limitations - interviewers can’t deviate from topic or explain questions (limits richness of data), interviewee could lie

unstructured interview

like a conversation, no set questions, free-flowing

unstructured interview evaluation

strengths - more flexibility, more likely to gain insight into the interviewees world

limitations - interviewer bias, analysis of data is harder, interviewees could lie, interviewers may go off topic

open questions

does not have  fixed range of answers, respondents free to answer in any way

open questions evaluation

strength - wide range of data collected

limitation - difficult to analyse

closed questions

offers a fixed number of responses. eg yes/no or rating something on a scale

closed questions evaluation

strength - quantitate data = easy to analyse

limitation - may lack depth and detail

correlation

investigating association between two variables - co-variables

correlation evaluation - strengths

useful preliminary tool for research, precise and quantifiable measure of relationship between 2 variables, suggest idea for future research, starting point for experimental study, quick/economical to carry out, no need for controlled environment, secondary data can be used = less time consuming

correlation evaluation - limitations

tells us how variables are related by not why, doesn’t demonstrate cause-effect relationship, intervening variables possible, may be misuse or minterpreted

qualitative data

expressed in words and non-numerical, can be converted for analysis

qualitative data evaluation

strengths - rich detail, participant can fully report thoughts and feelings, high external validity

limitations - difficult to analyse, patterns/comparisons hard to identify, subject to bias

quantitative data

data that can be counted, usually given as number

quantitative data evaluation

strengths - simple to analyse, comparison is easy, objective = less likely of bias

limitations - narrower in meaning, may fail to represent ‘real life’

primary data

obtained first-hand by researchers. eg questionnaire, interview or observation

primary data evaluation

strengths - specific to investigation, designated specifically for target information

limitations - time and effort, planning, prep and resources

secondary data

collected by someone else, who isn't conducting the research. eg journal articles, websites or books

secondary data evaluation

strengths - inexpensive, minimal effort, desired information may already exist

limitations - data may be outdates/incomplete, may not completely match needs/objectives, challenges validity of conclusions

meta-analysis

process of combining findings from number of studies on particular topic to produce overall statistical conclusion

meta-analysis evaluation

strengths - can create a larger/more varied sample, results can be generalised, high validity

limitation - prone to publication bias (file drawer problem), conclusions may be biased to match predictions

measures of central tendency

averages to give more typical values in set of data

(mean, median, mode)

mean + evaluation

average by adding up all values in a set of data + dividing by the number of values

strengths - representative of data as a whole + includes all values

limitations - sensitive as easily distorted by extreme values