Research methods

standardised procedures

all subjects should be subjected to the same environment, conditions and experiences

inderpendent variable

variables the research manipulates

dependent variable

variable measured by the researcher

EV's

any variable other than the IV that had an effect on the DV

operationalisable

this means when we identify an IV or DV we may need to state it in a clearly measurable way

lab experiment

highly controlled

field experiment

carried out in a natural environment. IV is still manipulated but is done in an environment typically to study behaviour

natural experiment

carried out in a natural environment but IV is not manipulated and is naturally occurring

quasi experiment

variables have not been and cannot be manipulated by anyone, they just exist . You cannot randomly allocate participants to a condition

mundane realism

the degree to which the experimental situation resembles places and events in the real world

demand characteristics

A cue that makes participants unconsciously aware of the aims of a study or helps participants work out what the researcher expects to find.

aim

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

hypothesis

a testable statement at the start of the study that clearly states the relationship between variables

null hypothesis

no connections

directional hypothesis

direction of the results is predicted participants who/ will

non directional hypothesis

a change or difference is predicted but a direction will not be specific there will be no difference/ relationship

confounding variables

a form of IV An EV that varies systematically with the IV so we cannot be sure of the true source of change in the DV

Types of EVs

situational, participant, investigator effect, demand characteristics

situational variable

noise, lighting, temp, order effects

participant variables

mood, intelligence,prior knowledge, anxiety, health status, individual characteristics

Investigator effects

researcher gives clues to participants about how to behave

demand characteristics

environmental clues tell us how to behave ie, surroundings, researcher characteristics

randomisation

randomly allocating participants to a condition

inderpendent group design

participants only take part in one study

strengths and limitations of inderpendent group design

s/ participants are less likely to guess aim of study l/individual differences overcome/ random allocation

repeated measures design

a participaant takes part in both conditions of the experiment

repeated measures design evaluation

s/ participant variables are controlled l/ order effects outcome/ counterbalancing

matched pairs design

participants are matched based on certain characteristics, one person from each pair takes part in one condition

evaluation of matched pairs design

s/ order effects removed l/ time consuming and expensive outcome/ only use relavant characteristics

order effects

practise,bordem fatigue

random sampling

every member of the target population has an equal chance of being selected. (lottery method)

systematic sampling

nth term of target population

stratified sampling

The structure of sample is directly proportional of people in strata within target population

volunteer sampling

whoever puts themselves forward

opportunity sampling

using whoever is avaliable

ethical issues

Deception, right to withdraw, informed consent, privacy, confidentiality, protection from harm

observational techniques

a method in which the researcher watches/ listens to a participant engaging in behaviour.

naturalistic observation

behaiour being studied is not interfered with in any way.

controlled observation

behaviour being studied is observed in specific situations, set up by a researcher

participant observation

researcher participates in the activity under study

non- participant observation

researcher observers without getting involved

participant obvs evaluation

strength/ greater understanding as they build a relationship with participants limitation/ researcher loses objectivity

non- participant obvs

strength/ researcher remains objective limitation/ people act diffrently when they know they are being studied

covert observation and evaluation

participants dont know they are being observed- removes strength/ demand characteristics limitation/ confidentiality

overt observation and evaluation

participants know they are being observed strength/ less ethical issues limitation/ demand characteristics

types of observational design

structures and unstructured

event sampling

counting number of times a behaviour occurs

time sampling

record behaviour within a pre- established time frame.

controlled observations

strength/ easier to replicate limitation/ not easier to apply to everyday life

naturalistic evaluations

strength/ high external validity limitation/ may be uncontrolled EV's

case study

a research method that includes the detailed study of a single individual, institution or event often a unique case

case study evaluation

strength/ rich in data, hollistic understanding limitation/ difficult to generalise

reliablitiy

how consistant the findings from an investigation are

internal reliablity

whether something is consistent within its self

external relaibility

whether a measure is consistent

Validity

accuracy

content analysis

a type of observation in which people are studied indirectly via forms of communication they have produced

ways to categories behaviour

behavioural catergories and counting number of occuransce

evaluation of content analysis

strength/ quick and effective limitation/ bias, lack of objectivity

corrolation

investigating a relationship between 2 variables

positive corolation

when both variables increase or decrease

negative corolation

when one variable increases and another decreases

closed questions

likert scale, fixed choice, rating scale

questionaire

open and closed questions

evaluation of open questions

strength/ validity limitation/ more challenging to produce statistics

evaluation of closed questions

strength/ easier to analyse limitation/ unrepresentative

interview types

structured, unstructured and semi structured

evaluation of structured

strength/ easy to replicate limitation/ interviews cannot deviate from question0 fustration

evaluation of unstructured

strength/ more flexibility limitation/ difficult to replicate, lying

Types of data

primary and secondary

primary data evaluations

strength/ reliable and more control

limitation/ research bias and time consuming

secondary data evaluations

strength/ less time consuming

limitation/ inaccurate reliablility, outdated and bias

meta analysis

a statistical technique used to gather data from lots of studies on the same topic and combine them to see the overall effect

meta analysis evaluations

strength/ easier to generalise, increases validity

limitation/ publication bias, not a match

Descriptive statistics

summerising and analysising numerical data to draw meaningful conclusions, measures of centeral tendancy measue dispersion and also graphs.

Types of data

nominal, ordinal and interval

nominal

separates into categories- no numerical meaning

ordinal

data is ordered different, each is not the same

Interval

data measured using units of data- temp and time

measure of central tendancy

tells us about the centre value, they are averages.

Mean, medium and mode

mean

interval data, add then divide

strength/ accounts for all scores

limitation/ outlier values may distort results

median

line up number, middle number. ordinarl and interval.

strength/not affected by extreme scores

limitation/ not representative, time consuming

mode

most common

strength/ not affected by extreme scores

limitation/ more than one, not representative, no info about other data

measure of dispersed

how dispersed data is

range and standard of deviation

range

highest subtract lowest

strength/ easy to calculate

limitation/ affected by extremes, not representative, clustered data

standard of deviation

sophisticated measure if dispersion from the mean

high SD- spread out the mean

low SD- clustered around mean

strength/ assesses overall data spread, persise

limitation/ hide extreme values, time consuming

normal distribution

bell shaped curve, mean, median and mode at midpoint.

Distribution is systematic

skewed distribution

data can be positive or negative

positive- distribution on left, tail on rights

negative- most distribution on right,tail on the left

Statistical test decisions

Simon- sign test

Cowell- chi squared

Wants- Wilcoxon T

More- Mann Whitney U

Singers- Spearman’s rho

Receiving- related T

Unanimous- unrelated T

Praise- Pearson r

Type 1 error

Null hypothesis is rejected and alternative hypothesis is accepted, but it should have been the other way round as the hypothesis is true, optimistic error

Type 2 error

Null hypothesis is accepted but should have been alternative hypothesis because alternative is true, false negative.