research methods
Aim Definition
General statement of what researcher intends to investigate, the purpose of the study
Hypothesis Definition
Clear, precise, testable statement that states the relationship between the variables to be investigated. Stated at the outset of any study.
Directional + Non-directional Hypothesis Definition (+ when we would use them)
Directional Hypothesis states the direction of the difference or relationship. Used when a theory or findings of previous research studies suggest a particular outcome. Non-directional Hypothesis does not state the direction of the difference or relationship. Used when there is no theory/previous research or findings from earlier studies are contradictory.
Variables Definition
Any 'thing' that can change or vary within an investigation. Generally used in experiments to determine if changes in one thing result in changes to another.
Independent Variables Definitions
Some aspect of the experimental situation that is manipulated by the researcher (or changes naturally) so the effect on DV cab be measured.
Dependent Variable Definition
The variable thats measured by researcher. Any effect on DV should be caused by change in IV.
Operationalisation Definition
Clearly defining variables in terms of how they can be measured.
Extraneous Variables
Any variable, other than IV, that may affect DV if not controlled. Do not vary systematically with IV. May make it harder to detect a result but do not confound findings of study.
Confounding Variables
Varies systematically with IV. Therefore can't tell whether change in DV due to IV or confounding variable.
Demand Characteristics
Any cue from researcher or research situation that participants may interpret as revealing purpose of investigation. May lead to participant changing their behaviour within research situation. May act in a way they think is expected + overperform to please experimenter (please-U effect). May deliberately underperform to sabotage results of study (Screw-U effect). Either way participants behaviour no longer natural (extraneous variable that may affect DV)
Investigator Effects
Any effect of investigators behaviour (conscious or unconscious) on research outcome (DV). Includes: design of study, selection + interaction with participants during research process. Coolican states this can include expectancy effects + unconscious cues. Eg: leading questions in eyewitness testimony.
Randomisation
Use of chance methods to control for effects of bias when designing materials + deciding order of experimental conditions. Attempts to control investigator effects.
Standardisation
Using exactly the same formulised procedures + instructions for all participants in a research study. Such standardisation means that non-standardised changes in procedure do not act as extraneous variables.
Independent groups
Participants allocated to different groups where each group represents one experimental condition.
Repeated Measures
All participants take part in all conditions of the experiment.
Matched Pairs
Pairs of participants are 1st matched on some variables that may affect DV. Then one member of pair assigned to condition A and one assigned to condition B. An attempt to control for the confounding variable of participants variables + often neccessitates use of pre-test matching to be effective.
Random Allocation
Attempt to control for participant variavles in an independent groups design which ensures that each participant has the same chance of being in one condition as any other.
Counter Balancing
Attempt to control for the effects of order in repeated measures design: half participants experience conditions in one order and other half in opposite order.
Independent groups evaluation: limitation of participant variables
Participants who occupy diff groups are not the same in terms of participant variables. If researcher finds mean difference between groups on the DV this may be more to do with participant variables than effects of IV. These differences may act as CVs, reducing the validity of the findings. To deal with this problem- random allocation.
Independent groups evaluation: limitation of economical
Less economical than repeated measures as each participant contributes to single result only. Twice as many participants needed to produce equivalent data to that produced in repeated measures.
Strength independent groups: order effects
Order effects aren't a problem whereas they are in repeated measures. Participants also less likley to guess aim.
limitation repeated measures: order effects
Each participant has to do at least 2 tasks + order of tasks may be significant (order effects). To deal with this problem- counter-balancing. Order effects could also arise as repeating 2 tasks could create boredom or fatigue that might cause detoriation of performance on second task. Alternatively participants performance may improve through effects of practice + participants may perform better on 2nd task. Order acts as confounding variable.
limitation repeated measures: aim
Also more likley participants will work out aim of study when they experience all conditions of experiment. Demand characteristics tend to arise more in repeated measures rather than independent groups.
Strength repeated measures: participant variables
Participant variables controlled (higher validity) and fewer participants needed (less time spent recruiting them + more economical).
Strength matched pairs: order effects
Participants only take part in single condition so order effects + demand characteristics less of problem.
Limitation matched pairs: participant variables
Although there is some attempt to reduce participant variables, participants can never be matched exactly. May still be important differences between them that may affect DV.
Limitation matched pairs: time-consuming + expensive
Matching may be time-consuming + expensive (especially if pre-testing required) so less economical than other designs.
Lab Experiment
Takes place in highly controlled envioroment within which researcher manipulates IV + records effect on DV whilst maintaining strict control of extraneous variables.
Lab strengths: control
High control over CVs + EVs. Means researcher can ensure any effect on DV likely result of manipulation of IV. Thus, can be more certain about demonstrating cause + effect (high internal validity).
Lab strengths: replication
Replication more possible than in other types of experiment because of high level of control. Ensures new EVs not introduced when repeatimg experiment. Replication vital to check results of any study to see whether findings valid + not just one off.
Lab Limitations: generalisability
May lack generalisability. Lab envioroment may be artifical + not like everyday life. In an unfamiliar context participants may behave in unusual ways so their behaviour cannot be generalised beyond research setting (low external validity).
Lab Limitations: Demand Characteristics
Participants usually aware they're being tested in lab experiment (even if they don't know why) + this may also give rise to unatural behaviour (demand characteristics)
Lab Limitations: mundane realism
Tasks participants asked to carry out in lab experiments may not represent everyday experience. Eg: Baddeley- recalling unconnected lists of words as part of memory experiment. Lacks mundane realism.
Field Experiment
An experiment that takes place in a natural setting within which researcher manipulates IV + records effect on DV.
Field strength: mundane realism
High mundane realism than lab experiments because envioroment more natural. Thus field experiments may produce behaviour thats more valid + authentic. Especially case as participants may be unaware they're being studied (high external validity).
Field Limitations: lack of control
Because of increased realism there is a loss of control of CVs + EVs. Means cause + effect between IV + DV in field studies may be much more difficult to establish + precise replication often not possible.
Field limitation: ethical issues
Important ethical issues- if participants unaware they're being studied, they cannot consent to being studied + such research could be an invasion of privacy.
Natural Experiment
An experiment where change in IV not brought about by researcher but would've happened even if researcgwe had not been there. The researcher records effect of a DV they've decided on.
Natural Strengths: oppurtunities
Provide oppurtunities for research that may not otherwise be undertaken for practical or ethical reasons (such as studies of institutionalised romanian orphans- Rutter et al).
Natural strength: high external validity
Natural experiments often have high external validity because they involve study of real-world issues + prpblems as they happen, such as effects of natural disaster on stress levels.
Natural Limitations: generalisability
Naturally occuring event may only happen very rarely, reducing oppurtunity for research. Also may limit scope for generalising findings to other similar situations.
Natural limiations: random allocations
Participants may not be randomly allocated to experimental conditions (only applies to independent groups). Means researcher might be less sure whether IV affected DV. Eg: romanian orphans, IV was whether children were adopted early or late. However, lots of differences between these groups, such as those who were adopted late may have also been less sociable than some of the other children which may have made them less appealing for prospective parents.
Natural limitations: Lab
Such research may have been conducted in a lab + therefore may lack realism + demand characteristics may be an issue.
Quasi Experiment
Study thats almost an experiment but lacks key parts. The IV hasn't been determined by anyone (researcher or any other person), the variables simply exist.
Quasi strength
Often carried out under controlled conditions and therefore share some strengths of lab experiment (eg: replication).
Quasi limitations
Can't randomly allocate participants to conditions + thereforw may be confounding variables. IV not deliberately changed by researcher + therefore we cannot claim IV caused any observed change.
Population
A group of people who are the focus of the researchers interest, from which a smaller sample is drawn.
Random Sample
All members of target pop have equal chance being selected. 1st step: obtain complete list of all members of target pop. 2nd step: all names on list assigned number. 3rd step: actual sample selected through use of lottery methods (eg. computer randomiser or picking names out of hat).
Systematic Sampling
When every nth number of target pop selected. Sampling frame produced (list of people in target pop ordered in, for example, alphabetical order). Sampling system nominated (eg. every 3rd). May begin from randomly determined start to reduce bias. Researcher works through sampling frame until sample complete.
Stratified Sample
Composition of sample reflects proportions of people in certain subgroups (strata) within target pop or wider pop. Researcher 1st identifies diff strata that make up pop. Then proportions needed for sample to be representative worked out. Finally, participants that make up each stratum selected using random sample.
Oppurtunity sample
As representative samples of target pop so difficult to obtain, many researchers decide to select anyone who's willing + availiable. Researchers take chance to ask whoevers around at time of study (eg: in the street).
Volenteer Sampling
Involves participants selecting themselves to be part of sample. Researcher may place advert in newspaper.
Random Sampling Strength
Potentially unbiased meaning that CVs + EVs should be equally divided between the diff groups, enhancing internal validity.
Random Sampling Limitations
However, random sampling difficult + time-consuming + complete list of target pop may be extremely difficult to obtain. May still end up with sample thats unrepresentative. Selected participants may refuse to take part (meaning you end up with something more like a volenteer sample).
Systematic Sampling Strength
Objective as once system for selection established, researcher has no influence over who's chosen (especially if start randomly selected).
Systematic Sampling Weakness
Method time-consuming + participants may refuse to take part (resulting in volenteer sample).
Statified Sampling Strength
Produces representative sample as its designed to accurately refelct the composition of the pop. Means that generalisation of findings becomes possible.
Stratified sampling Weakness
Identified strata cannot reflect all ways that people diff, so complete representation of target pop not possible.
Oppurtunity Sampling Strength
Convienent + method much less costly than other sampling techniques because list of target pop not required (random) + no need to divide pop into diff strata (stratified).
Oppurtunity sampling Limitation
Sample unrepresentative of target pop as its drawn from very specific area (such as one street in one town) so findings cannot be generalised to target pop. Reseracher has complete control over selection of participants + could (for example) may avoid people they do not like look of (researcher bias).
Volunteer sampling strength
Collecting sample easy. Requires minimal input from researcher + so is less time-consuming than other forms of sampling. Researcher ends up with participants that are more engaged.
Volunteer sampling limitation
Volunteer bias is a problem. Asking for volunteers may attract certain 'profile' of person (one who is curious + more likely to try to please researcher). This might then affect how far findings can be generalised.