Research Methods Flashcards
What is an independent variable?
Manipulated by the researcher
What is a dependent variable?
Measures to observe the effect of the IV
What’s is an extraneous variable?
Can be managed by control measures to minimise their effect on the DV e.g. age, gender, IQ
What is a confounding variable?
Can’t be controlled by the researcher e.g. socioeconomic status, participants past experiences.
What is a hypothesis?
A clear, precise, testable statement that states the relationship between variables to be investigated. Stated at the outset of any study.
What is a directional hypothesis?
States direction of difference/relationship.
Includes words more/less, higher/lower etc
Use when previous research suggests particular outcome.
What is a non-directional hypothesis?
Does not state the difference.
Tend to use when there is no previous research/findings from earlier studies that are contradictory.
What is a pilot study?
A small scale version of an investigation that take place before the real investigation is conducted.
What are the advantages of pilot studies?
- Ensures the experiment us measuring what it sends out to investigate (increased validity).
- Let’s researcher tribal the experimental procedure, and tries to eliminate participant error.
- Let’s researcher identify extraneous variables before committing too much time or funding.
What are the disadvantages of pilot studies?
- Requires extra costs, time and resources.
- Doesn’t guarantee success of main study.
- Can’t use the same participants for the pilot as the main study. Requires further recruitment.
What is experimental design?
The different ways in which the testing of participants can be organised in relation to the experimental conditions.
What is independent groups design?
Participants allocated to different groups where each group represents once experimental condition.
Two separate groups of participants experience two different conditions of the experiment.
What are the advantages of independent groups design?
- No order effects: different participants do each condition there are no order effect whereby the order conditions are completed may influence the outcome.
- Demand characteristics share reduced: participants do one condition each, so there is less chance of guessing the purpose of the study and so affecting their performance.
- Time saved: both sets of participants can be tested at same time, reducing time and effort.
What are the disadvantages of independent groups design?
- More participants needed: with participants each doing only one condition, more participants will be needed to gather sufficient data.
- Group differences: difference in results between the two conditions may be due to participants a variables not manipulations of the IV - this issue can be minimised by random allocation of participants to each condition.
What is random allocation?
An attempt to control for participant variables in an independent groups design, which ensures that each participant has the same chance of being in one conditions as any other.
What is repeated measures design?
All participants tale part in all conditions of the experiment.
Each participant would be tested for one condition and later the other condition.
Following this 2 sets of data are compared to see if there’s a difference.
What is an advantage of repeated measures design?
- No group differences: the same people are measured in all conditions, there are no participants variables between the conditions.
- More data/fewer participants: each participant produces two or more scores so producing more data, fewer participants needed to gather volume of data required.
What are the disadvantages of repeated measures design?
- Demand characteristics: by participating in all conditions, its more likely participants may guess study’s purpose and act accordingly.
- Takes more time: a gap may be needed between the conditions to counter the effects of fatigue/boredom. Each test may also require different materials to be prepared.
- Order effects: participants do all the conditions, the order completed may affect results. Participants may perform worse on second due to boredom or better due to practice - deal;t with by counterbalancing.
What is counterbalancing?
An attempt to control for the effects of order in a RMD, half experience conditions in order A-B and half in B-A
What is matched pairs design?
Pairs of participants are first matched on some variable that may affect the DV, then one is assigned to condition A and the other to condition B.
Participants paired together on variable(s) relevant to the experiment.
What are the advantages of matched pairs design?
- No order effects: different participants do each condition there are no order effects.
- Demand characteristics: participants do one condition each, so there is less chance of them wor,in out the purpose of the study.
- Reduced group differences: as participants are matched, there should be less chance of participant variables affecting the results.
What are the disadvantages of matched pairs design?
- More participants required: with participants only doing one condition, more will be needed to gather sufficient data.
- Matching is difficult: it is impossible to match all the variables between participants and an unmatched variable might be important, also even two closely matched individuals may have different levels of motivation at any given time.
- Time consuming: lengthy process to match participants.
What is a lab experiment?
An experiment that takes place in a controlled environment within which the researcher manipulates the IV and records the effect on the DV, whilst maintaining strict control of extraneous variables.
How controlled is a lab experiment?
Highly controlled
What are the advantages of lab experiments?
- High degree of control: experiments control all the variables and the IV and DV are precisely operationalised and measured, this leads to greater accuracy and objectivity.
- Replication: other researchers can repeat the experiment to check results.
- Cause and effect: as all other variable are controlled, the effect (change in the DV) must be solely caused by the manipulation of the IV.
- Isolation of variables: in the lab, individual pieces of behaviour can be isolated and rigorously tested.
What are the disadvantages of lab experiments?
- Experimenter bias: experimenters’ expectations can affect results and participants may be influenced by these expectations.
- Problems operationalising the IV and DV: to gain precision measurements it can become too specific and not relate to wider behaviour.
- Low external (ecological) validity: high degrees of control make the experimental situation artificial and unlike real life, means it can be difficult to generalise to other settings.
- Demand characteristics participants are aware they are being tested and so may unconsciously alter their behaviour.
- Low mundane realism: the task of the participants have to carry out may represent real life experience.
What is a field experiment?
In natural setting, researcher manipulates IV and records effect on DV.
What is the level of control in field experiments?
No level of control.
What are the advantages of field experiments?
- Higher mundane realism: environment is more natural so involves more everyday behaviours.
- High external validity: real life environment.
- No demand characteristics: often participants are unaware of the experiment, so there are no demand characteristics.
What are the disadvantages of field experiments?
- Less control: it is more difficult to control extraneous, so causality is harder to established.
- Replication: difficult to exactly repeat as the conditions may never be precisely the same again.
- Ethics: lack of informed consent, potential privacy issues.
- Sample bias: participants are not randomly allocated to groups so samples may not be comparable to each other.
What is a natural experiment?
An experiment where the change in the IV is not brought about by the researcher but would have happened even if the researcher had not been there, the researcher records the effect on the DV.
What are the levels of control in a natural experiment?
No level of control.
What are the advantages of natural experiments?
- Research opportunities: provides opportunities for research where otherwise it would not have been practical or ethical to do so, such as Romanian orphan study.
- High external validity: involve study of real-life issues and problems as they happen e.g. effects of natural disaster on stress levels.
- No demand characteristics.
What are the disadvantages of natural experiments?
- Limited generalisation: naturally occurring event may happen rarely so may limit scope for generalising.
- Sample bias: participants may not be randomly allocated to experimental conditions (only applies when IGD), cannot be sure if IV affected DV, e.g. orphan study the IV was adoption age, this may have been reasons for age of adoption.
- Less control
- Limited replication
- Ethics
What is a quasi experiment?
A study that is almost an experiment but lacks key ingredients, the IV has not been determined by anyone, the ‘variables’ simply exist, such as being young or old (strictly speaking this is not an experiment).
What are the levels of control in a quasi experiment?
High level of control.
What are the advantages of quasi experiments?
Often carried out under controlled conditions so share the strengths of a lab experiment.
What are the disadvantages of quasi experiments?
May be confounding variables - like natural experiments participants cannot be randomly allocated to conditions.
What is peer review?
The assessment of scientific work by others who are specialists in the same field to ensure that any research intended for publication is of high quality.
- Scrutinised by two or more expert in the particular field.
What are the aims of peer review?
1) To allocate research funding: independent peer evaluation also takes place to decide whether or not to award funding for a proposed research project, may be coordinated with government run funding organisations.
2) To validate the quality and relevance of research: all elements of research are assessed fro quality and accuracy.
3) To suggest amendments or improvements: reviewers may suggest minor revisions of the work and improve the report or in extreme circumstances may conclude that the work is inappropriate for publication and should be withdrawn.
What are the reviewer options?
1) Accept work unconditionally.
2) Accept it so long as the researcher improves it in certain ways.
3) Reject it but suggest revisions and resubmission.
4) Reject it outright.
What is a single blind review?
Usual form of peer review, names of reviewers are not revealed to researchers, reviewer anonymity should lead to an unbiased review free from interference by the researcher.
What are the disadvantages of a single blind review?
- Danger anonymous reviewers may delay the process allowing them to publish similar research first.
- May hide behind anonymity to be undeservedly harsh.
What is a double blind review?
Both the reviewers and researcher are anonymous, prevent bias, not be based on a researcher’s reputation.
What is a disadvantage of double blind reviews?
Researcher may be identified from their writing/research style.
What is open review?
Reviewers and researcher are know to each other, reducing risk of personal comments and plagiarism and encourages open, honest peer reviewing.
What is a disadvantage of open review?
Criticism may be watered down due to politeness or fear or retribution from famous or powerful researchers.
What are the advantages of peer review?
- Vital in establishing the validity and accuracy of research.
- Anonymous reviewers may lead to harsh critiques as there is competition between researchers (open review prevents this).
- Publication bias: tendency for editors of journals to want to publish ‘headline grabbing’ findings to increase the credibility and circulation of their publication, also prefer to publish positive results - creates a false impression of psychology.
What are the disadvantages of peer review?
- Slow process which may take months or years to complete.
- Consequences of false research being accepted as true can be problematic as other may build upon the work.
- Peer review may suppress opposition to mainstream theories, reviewers tend to be critical of work that contradicts their own view and see those that match more favourably - established researchers are more likely to be reviewers so the process may slow down the rate of change.
What is an example of the implications of psychological research for the economy?
- Creation of effective therapies for mental disorders - allow people to return to work.
- Reduces costs to healthcare and criminal justice systems as psychologically healthy people are less likely to need them.
- Attachment research and childcare.
What are psychological implications within the economy?
- Ethics must come before profits.
- Psychology must not be used to exploit people.
- Psychologists must take responsibility for the implications of their actions.
What is a population?
A large group of people who are the focus of the researcher’s interest, from which a smaller sample is drawn.
What is a target population?
Subset of the population from which a sample may be drawn.
What is a sample?
A group of people who take part in a research investigation, the sample is drawn from the (target) population and is presumed to be representative of that population.
What is generalisation?
The extent to which finding’s and conclusions from a particular investigation can be broadly applied to the population.
What is bias?
In the context of sampling, when certain groups may be over or under represented within the sample selected, limits the generalisations that can be made.
What is a sampling technique?
Method used to select people from the population.
What is a random sample?
All members of the target population have an equal chance of selection.
How would you select a random sample?
1) Obtain a list of all members of the target population.
2) All the names on the list are assigned a number.
3) Sample generated through a lottery method (computer based randomiser or numbers from a hat).
What are the advantages of a random sample?
- Unbiased selection: no bias in selection, increasing chances of getting an unbiased and representative sample, no researcher bias.
- Generalisation: sample should be representative, results can then be generalisable to the target population.
What are the disadvantages of a random sample?
- Not representative: unbiased selection does not guarantee an unbiased sample, chance means all one gender could be randomly selected, also participants may refuse to take part.
- Impractical: random sampling is difficult to achieve as it is sometimes difficult to get full details of a target population, time consuming.
What is a systematic sample?
Where every nth member of thee target population is selected.
How do you select a systematic sample?
1) Sampling frame is produced, which is a list of people in the target population organised into alphabetical order.
2) A sampling system is nominated (nth) or the interval may be determined randomly to reduce bias.
3) Researcher then works through the sampling frame until the sample is complete.
What are the advantages of systematic sampling?
- Unbiased selection: no bias in selection, representative sample chance increased, avoids researcher bias (no influence over who is chosen).
- Generalisation: usually representative.
What are the disadvantages of systematic sampling?
- Not representative: unbiased selection does not guarantee an unbiased sample.
- Periodic traits: sampling technique may coincide with the frequency of the trait.
What is stratified sampling?
Composition of the sample reflects the proportions of people in certain sub-groups (strata) within the target population or wider population.
How do you carry out stratified sampling?
1) Researcher identifies the different strata that make up the population.
2) The proportions needed for the sample to be representative are worked out.
3) Participants that make up each stratum are selected using random sampling.
What are the advantages of stratified sampling?
- Representative: as selection occurs from representative sub groups within the population, the sample itself should be representative, avoids researcher bias.
- Unbiased: as random sampling is performed upon the subgroups.
