Research Methods Flashcards
aim
what the researcher intends to investigate
hypothesis
statement stating relationship between IV & DV
state the 3 types of hypothesis
null, directional, non-directional
null hypothesis
nothing will happen
directional hypothesis
1 tailed, one specific group will do better than the other
non-directional hypothesis
2 tailed, predicts something will happen but not ‘direction’ of the effect
independent variable
manipulated by researcher so DV can be measured
dependant variable
measured by researcher
what do you have to do once you have made the aims and hypothesis
operationalise variable e.g. turn UV & DV into something we can measure
name all research issues
extraneous variable, confounding variable, demand characteristics, investigator effects
research issues - extraneous variable
variable affecting DV
additional/unwanted - should be identified + have steps taken to minimise effects
doesn’t vary systematically with IV
research issues - confounding variable
varies systematically with IV so can’t tell is change in DV is due to IV or varaible
research issues - investigator effects
effect of investigator’s behaviour on research outcome
e.g. leading questions
Coolican: include expectancy effects + unconscious bias - actions of researcher related to study design (selection of PPs, instructions)
research issues - demand characteristics
cues from researchers / situation that may be interpreted as revealing purpose
act in way they think expected + over-perform (please-U effect)
underperform to deliberately sabotage (screw-U effect)
research issues (combat) - randomisation
control investigator effects through use of chance methods to reduce researcher’s unconscious biases
research issues (combat) - standardisation
using exactly the same formalised procedures / instructions for all PPs in a research study
case studies
in-depth investigation, description, analysis of single individuals, group, institution, event
tend to take place over long time (longitudinal)
content analysis
research technique enabling indirect study of behaviour by examining communication that people produce e.g. in texts, emails, TV, film
aim to summarise & describe communication in systematic way so overall can be drawn
coding
stage of content analysis - categorise large sets of info into meaningful units
may involve counting up number of times particular word/phrase appears to produce quantitative data
thematic analysis
inductive & qualitative approach to analysis that involves identifying implicit/explicit ideas within data
themes often emerge once data been coding
evaluate case studies
+ rich, detailed insights may shed light on unusual + atypical forms of behaviour - preferred to more ‘superficial’ forms of data from experiment/questionnaire
+ contribute to understanding of ‘normal’ functioning e.g. HM significant as it demonstrated ‘normal’ memory processing
+ generate hypotheses for future study + 1 solitary contradictory instance may lead to revision of entire theory
- generalisation when dealing with small sample sizes
- information in final report based on subjective selection & interpretation
- personal accounts prone to inaccuracy & memory decay (low validity)
evaluate content analysis
+ useful - gets around ethnical issues
+ most material already exists within public domain - no issues obtaining permission
+ high external validity
+ flexible - produce both qualitative & quantitative data
- people tend to be studied indirectly so communication they produce usually analysed outside context within which it occurred
- researcher may attribute opinions
- lack objectivity especially when more descriptive forms of thematic analysis employed
assessing reliability
- test retest: questionnaire, testing over time, correlation -0.8+
- inter-observer reliability: multiple observers - overcome bias 0.8+ pilot study
assessing reliability - test retest
method assessing reliability of questionnaire/psychological test by assessing person on 2 separate occasions
shows to what extent test produces same answers i.e. is reliable
must be sufficient time between test & retest to ensure PP can’t recall answers but not so long attitudes, opinions, abilities changed
assessing reliability - inter-observer reliability
extent to which there is agreement between 2+ observers
measured by correlating observations of 2+ observers
(total number of agreements)/(total number of observations) >+0.80 data have higher inter-observer reliability
issue: everyone has own unique way of seeing world - relevant observational research as researcher’s interpretations may differ - introducing subjectivity, bias, unreliability
reliability
how consistent findings are - measuring device said to be reliable if it produces consistent results
improving reliability - questionnaires
test-retest method
if produces low test-retest reliability may require some items to be ‘deselected’/rewritten (if questions complex may be interpreted differently) solution replace some of open questions with fixed choice alternatives
improving reliability - interviews
ensure reliability best by use same interviewer - if not possible interviewers must be properly training so no asking leading/ambiguous questions
easily avoided in structured interviews where interviewer’s behaviour more controlled by fixed questions
improving reliability - experiments
lab experiment reliable by struct control on procedure
precise replication of method rather than demonstrating reliability of findings
improving reliability - observations
reliability improved by making sure behavioural categories properly operationalised + measurable + self-evident - categories shouldn’t overlap + all possess behaviours should be covered
if categories not operationalised well different observers have to make own judgements of what to record + end up with differing and inconsistent records
validity
extent observed event genuine (does it measure what supposed to) (can it be generalised)
face validity
a measure scrutinised to determine whether it appears to measure what its supposed to
concurrent validity
extent psychological measure relates to existing similar measure
ecological validity
extend findings can be generalised to settings/situation
form of external validity
if task used to measure DV is not ‘like everyday life’ (i.e. low mundane realism can lower eco valid)
temporal validity
extend findings can be generalised to other historical times
form of external validity
internal validity
refers to whether effects observed due to manipulation of IV and not another factor
major threat to IV is if PPs respond to demand characteristics e.g. Milgram ‘played along’ + didn’t believe they were administering shocks
external validity
relates to factors outside investigation e.g. generalising to other settings, populations, eras
ecological
validity - qualitative methods
high eco valid than quanti (less interpretive) because depth & detail associated with case studies and interviews (better reflect PPs reality)
validity further enhanced through triangulation - use number of different sources as evidence e.g. interviews, diary, observation
type 1 error
reject null hypothesis when we shouldn’t - if probability level too loose/lenient (e.g. 0.1 an ‘optimistic error’
incorrect rejection of true null hypothesis (false +tive)
type 2 error
accepting null hypothesis when we shouldn’t - if probability level too tight/stringent (e.g. 0.01 a ‘pessimistic error’
failure to reject false null hypothesis (false -tive)
levels of measurement
quantitative data classified into types/levels of measurement
e.g. nominal, ordinal, interval
chi-squared
test for association (difference or correlation) between 2 variables/conditions
data should be nominal level using unrelated design
Mann-Whitney
test for significant difference between 2 sets of scores
data should be ordinal level using unrelated groups
Pearson’s r
parametric test for correlation when data at interval level
Related t-test
parametric test for difference between 2 sets of scores
data must be interval with related design
sign test
statistical test analyse difference in scores between related items i.e. same PPs tested twice
nominal
spearsman’s rho
test for correlation when data at least ordinal level
unrelated t-test
parametric test for difference between 2 sets of scores
data interval with unrelated design
Wilcoxon
test for significant difference between 2 sets of scores
data ordinal level with related design
experimental design
related design: repeated, matched
unrelated design: independent
table to work out test
Carrots Should Come
Mashed With Swede
Under Roast Potatoes
nominal data
presented in form of categories
ordinal data NO UNITS
ordered in some way e.g. scale of 1-10
doesn’t have equal intervals
lacks precision - based on subjective opinion
due to unsafe nature, ordinal data not used as part of statistical testing
interval data
numerical scales include units of equal size
HAS UNITS
more detail
public scales of measurement produce data based on units of measurement (time, temperature weight)
most precise & sophisticated
probability
measurement of likelihood that particular event will occur where 0 indicates statistical impossibility + 1 statistic certainty
significance
how sure we are that difference or correlation exists
significant result can reject null hypothesis
levels of significance and probability
usual significance in psychology is 0.05 (5%) -> p <= 0.05
can never be 100% certain about result -> psychology settled on convectional level of probability where prepared to accept results may have occurred by chance
order to psychological investigations
abstract, introduction, method, results, discussion, references
psychological investigations: abstract
key details of research project
short summary (150-200 words)
psychological investigations: introduction
look at past research on similar topic
literature review following logical progression - begin broadly + gradually become specific until aims & hypothesis presented
psychological investigations: method
description of what researchers did
split into several subsections
sufficient detail so other researchers able to replicate
design clearly stated and reasons/justification
sample -> information related to people involved: how many, biographical/demographic information + sampling method & target population
apparatus/materials
procedure -> list everything that happened - briefing, standardised, instructions, debriefing
ethics -> explanation of how these addressed
psychological investigations: results
description of what researcher found
summarise key findings
inferential statistics include choice of statistical test, calculated & critical values, level of significance + final outcome
any raw data collected
psychological explanations: discussion
consideration of what results can tell us in terms of psychological theory
summarise results/findings in verbal form
mindful of limitations + discuss
wider implications considered
psychological explanations: referencing
author(s), date, title of book (in italics), place of publication, publisher
paradigm
set of shared assumption + agreed methods with scientific discipline
paradigm shift
result of scientific revolution: significant change in dominant unifying theory within scientific discipline
empirical method
scientific approaches based on gathering evidence through direct observation & experience
falsifiability
principle that theory can’t be considered scientific unless it admits possibility of being proved untrue
Popper: genuine scientific theories should hold themselves up for hypothesis testing + possibility of being proven false - theory of falsification: even when scientific principle successfully tested no necessarily true just not proven false yet - theories that survive most attempts to falsify become strongest
reason for null hypothesis
paradigms & paradigm shifts
Kuhn: suggested what distinguishes scientific disciplines from non-scientific disciplines in a shared set of assumptions & methods - suggested social sciences lack universally accepted paradigm + best seen as ‘pre-science)
psychology marked by too much international disagreement + has too many conflicting approaches to qualify as a science + therefore is pre-science
Kuhn: progress within established science occurs where there’s scientific revolution - handful researchers question accepted paradigm, critique gather popularity + eventually paradigm shift when too much contradictory evidence to ignore
e.g. Kuhn cited change from Newtonian paradigm in physics towards Einstein’s theory of relativity as paradigm shift
theory construction & hypothesis testing
theory: set of general laws/principles that have ability to explain particular events/behaviours
theory construction occurs gathering evidence via direct observation
should be possible to make clear + precise predictions on basis of theory
theories should suggest number of possible hypothesis
hypothesis tested using systematic & objective methods to tell if it should be supported/refuted
deduction: process of deriving new hypotheses from existing theories
replicability
if scientific theory ‘trusted’ findings must be shown to be repeatable across a number of different contexts & circumstances
replication important role in determining validity of finding
replication in determining reliability of method used
Popper: by repeating study over different contexts & circumstances can generalise
objectivity & the empirical method
researchers must strive to maintain objectivity - must keep ‘critical distance’ during research
must not allow personal opinions/biases to ‘discolour’ data they collect/influence behaviour of PPs
lab experiments - more control - most objective
objectivity basis of empirical methods e.g. experimental methods, observational method
theory can’t claim to be scientific unless it’s been empirically tested & verified
the scientific cycle
science based on concept of ‘empiricism’ - belief knowledge gained from experience - leads to idea evidence must inform theories
systematic and objective evidence leads to formation of a theory
once evidence no longer fits theory - theory should be abandoned
aim & hypothesis
aim: general statement of what researcher intends to investigate; purpose of study
hypo: clear, precise, testable statement, that states relationship between independent and dependent variable (prediction)
types of extraneous variable
situational variables: relating to the environment; time of day, temperature, lighting, instructions
participant variables: intelligence, age, gender and personality - controlled through experimental design and random assigning
confounding variables
vary systematically with IV
not able to tell if change in DV due to IV or confounding variable
demand characteristics
any cue from researcher or situation that may be interpreted by PPs as revealing purpose
leading to PP changing behaviour - may act in way they think expected/over-perform ‘please-U effect’ or under-perform to sabotage ‘screw-U effect’
participant reactivity significant extraneous variable
investigator effects
any effect of investigator’s behaviour on research outcome
Coolican: can include expectancy effects + unconscious cues - any actions of researcher that are related to study design
leading questions
randomisation
using chance methods to reduce investigator effect and demand characteristics (control effects of bias)
standardisation
using exactly the same formalised procedures + instructions for all PPs in research study
extraneous variable
variable that affects the DV
unwanted should be identified at start of study and steps taken to minimalize influence
don’t confound with findings
independent groups design
PPs allocated to different groups where each group represents 1 experimental condition
when 2 separate groups experience 2 different conditions - performance of 2 groups compared
repeated measures
all PPs take part in all conditions of the experiment
2 mean scores from both conditions would be compared
matched pairs design
pairs of PPs first matched on some variables that may affect DV - then 1 member of pair assigned to condition A or condition B
attempt to control confounding variable + PP variables
evaluate independent groups
- PPs in different groups not same in terms of PP variables (act as confounding variable reducing validity) (deal with this using random allocation)
- less economical each PP only contributes single result only
+ order effects no a problem
evaluate repeated measures
- each PP has to do at least 2 tasks so order of tasks may be significant (use counterbalancing)
- order effects could create boredom + fatigue might cause deterioration in performance (confounding variable)
- demand characteristics
+ PP variables controlled (higher validity)
+ fewer PPs needed
evaluate matched pairs
+ PPs only take part in single condition so order effects + demand characteristics less of problem
- PPs never matched exactly
- matching may be time consuming + expensive, less economical
laboratory experiment
controlled environment within which researcher manipulates IV + record effect on DV, whilst maintaining strict control of extraneous variables
field experiment
natural setting within which researcher manipulates IV + records the effect
natural experiment
change in IV not brought about by researcher but would have happened even if researcher not been there
researcher record effect on a DV they have decided on
quasi-experiment
study that’s almost experiment but lacks key ingredients
IV hasn’t been determined by anyone - the ‘variables’ simply exist (being old/young)
evaluate lab experiments
+ high control over confounding + extraneous variables TMT ensure any effect on DV likely to be result of manipulation of IV (more certain about cause + effect (high internal validity))
+ easy to replicate
- lack generalisability (artificial task) - PPs behave unusual in unfamiliar context (low external validity) - PPs aware they being tested so demand characteristics - tasks not represent everyday life (low mundane realism)
evaluate field experiments
+ high mundane realism because natural environment - produce behaviour more valid/authentic because PPs unaware they being studied (high external validity)
- loss of control of confounding + extraneous variables TMT cause + effects more difficult to establish + precise replication often not possible
- ethical issues - PPs unaware being studies + can’t consent
evaluate natural experiments
+ provides opportunities for research that may not be undertaken for practical/ethical reasons e.g. Romanian orphans
+ high external validity - involve study of real-world issues
- naturally occurring event may occur rarely
- PPs may not be randomly allocated to experimental conditions if there is an independent groups TMT less sure whether IV affected DV
- may be conducted in lab - lack realism + demand characteristis
evaluate quasi-experiments
+ often controlled
- can’t randomly allocate PPs to conditions + therefore may be confounding variables
common ethical issues
informed consent, deception, protection from harm, confidentiality and privacy, right to withdraw
BPS code of Ethics and Conduct
- respect (upholding dignity of others (privacy, consent + making PPs aware of rights))
- competence (completing work to high, professional standard)
- responsibility (to clients/PPs/public (providing robust evidence) + to psychology (upholding its scientific nature)
- integrity (transparency over bias + limitations)
ethical issues - consent
need to be aware of following details in order to give fully informed consent:
statement participation voluntary, purpose, risks + discomfort, procedures, benefits to society and individual, length of time subject expected to participate
ethical issues - combat consent
BPS: if don’t fully disclose before asking consent additional measures must be in place
presumptive consent using similar sample - fully debrief at earliest opportunity
children struggle understand what they consenting to require special consideration - using guardian/carer
independent advisor must approve anything that might result in negative consequences
cost-benefit analysis: researchers must weigh up potential benefits of study against potential negatives
naturalistic observation
watching + recording behaviour in setting within which it would normally occur
controlled observation
watching + recording behaviour within structured environment
covert observations
PPs behaviour watched + recorded without their knowledge/consent
overt observations
PPs behaviour watched + recorded with their knowledge/consent
participant observations
researcher becomes a member of group whose behaviour they’re watching + recording
non-participant observation
researcher remains outside group whose behaviour they are watching + recording
evaluate all observations
+ give special insight into behaviour
- observer bias (observer’s interpretation of situation may e affected by their expectations) (may be reduced by using more than 1 observer)
- can’t remonstrate casual relationships
evaluate naturalistic and controlled observations
+ high external validity (generalised to everyday life because behaviour studied within environment it would normally occur)
- lack of control (can’t replicate)
- uncontrolled confounding/extraneous variables more difficult to judge any pattern of behaviour
- controlled: not easily applied
+ controlled: easier to replicate
evaluate covert and overt observations
+ natural behaviour (PPS don’t know being watched remove demand characteristics increase internal validity)
- ethics questioned (right to privacy)
+ overt: ethically acceptable BUT knowledge being observed may significantly influence behaviour
evaluate PP and non-PP observations
+ PP: researcher experience situation as the PP’s do giving increased insight into lives of studies increase external validity
- PP: danger researcher come to identify too strongly with those studied + lose objectivity - called ‘going native’ when line between being researcher + PP become blurred
- non-PP: maintain objective psychological distance
- non-PP: lose valuable insight as they are too far removed from people + behaviour
observational design - behavioural categories
when target behaviour broken up into components that are observable + measurable (operationalisation)
observational design - event sampling
target behaviour/event first established then researcher records this event every time it occurs
observational design - time sampling
target individual/group first established then researcher records their behaviour in fixed time frame
evaluate unstructured versus structured observations
+S: use beha cat recording data easier + systematic - data numerical TMT analysing straightforward
-U: produce quali
+ more rich detail - appropriate small-scale
- greater risk observer bias
evaluate behavioural categories
+ make data collection more structured + objective
evaluate sampling methods
+ E: useful when target event happens infrequently + could be missed if T used
- if specified event too complex observer overlook
+ T: reduces number observations have to be made
- instances when behaviour is sampled unrepresentative
self-report techniques - questionnaires
PPs answer set pre-written questions
designing careful to work: clarity (avoid ambiguity) and bias (avoid leading ?)
open ?: provide own answer + quali - more insight + detail - PPs not articulate struggle - harder analyse
closed ?: pre-determined responses + quanti - easier analyse - forces PPs make choice so doesn’t always give actual answer (lack validity)
+ cheap + easy distribute
- only completed by people who can read/write + have time
- hard to get right difficult to design + if not done right can be meaningless
questionnaires design
likert scales (PPs indicate agreement using scale)
rating scales (get PPs identify with a value representing strength of feelings about topic)
fixed choice option (include list of possible options which PPs tick)
self-report design - interviews
structured: predetermined questions - standardised easily repeated - easy analyse - require trained interviewer
unstructured: set of ideas predetermined with some questions but questions developed as interview progresses its responsive - more detail - harder analyse - require highly trained interviewer expensive
semi-structured: list of pre-determined but interviewer free to ask follow up
- can lie (social desirability bias + demand characteristics undermine internal validity)
- may not know how they feel/remember event accurately
- only certain types people willing - unrepresentative sample low external validity
meta-analysis
researcher looks at findings from many different studies + produce statistic to represent overall effect - researcher will use secondary data
+ large varied sample, results generalised to larger pop increase validity
- conclusions biased as researcher purposely exclude negative or non-significant findings
correlations
investigate relationship between co-variables
show strength of association between co-variables by plotting each pair of points on scatter graph
no manipulation so can’t establish cause and effect
measures of central tendency
descriptive analytics can analyse data
involve graphs, tables allow identify trends
mean, median, mode
measures of dispersion
indicate how data spread out
range + standard deviation
range skewed by large data points
standard shows to what extent values deviate from mean arguably more representative than mean - low SD indicate consistency: IV more consistent effect - larger SD indicate variability
bar chart
data in categories (nominal/ordinal)
discrete (in categories) so bars separate
historgram
present continuous data on interval/ratio scales of measurement
columns equal width per equal category
all categories represented
scattergran
used when doing correlational analysis
visual picture of relationships
distributions
spread of data
mean, median + mode occupy same midpoint of curve
positive skew - most distribution concentrated toward right
negative skew - most distribution concentrated towards right
