Research Methods Flashcards
What are standardised procedures?
A set of procedures that are the same for all participants in order to be able to repeat the study. Each participant experiences the same thing in each condition otherwise results may vary.
What are extraneous variables?
Any variable other than the IV that might potentially affect the dependent variable and therefore obscure the results
How is a hypothesis different to an aim?
A hypothesis is more precise about what the outcome is likely to be rather than a statement of intention. It is operationalised. Should include the levels of the IV
What is a confounding variable
An uncontrolled extraneous variable that exerts an unwanted effect on the results.
What is meant by ecological validity?
External validity about a place. Findings can be generalised from the research setting to other settings.
What is meant by population validity?
Findings can be generalised to people different from the original sample. It is a type of external validity.
What is meant by historical validity?
A type of external validity referring to time. Findings apply across different time period. Can the findings remain valid in different time periods?
What is the difference between a directional and a non-directional hypothesis?
Directional – leaning to one a specific outcome. states the direction between the conditions
Non-directional – states that there is a difference between the conditions without stating the direction of the difference.
What is a pilot study?
A small scale trial run done before the real research to find a resolve issues before conducting the full study
What is a confederate?
A person instructed by the researcher on how they need to act. According to participants they believe the confederate is a participant also.
Name the three types of experimental design
Repeated measures, independent groups, matched pairs design
What happens in a repeated measure design?
Participants take part in all conditions
What happens in an independent group’s design?
Participants are split into different groups representing the different levels of the IV to complete the task under different conditions
What are matched pair design?
Participants matched in terms of key variables such as age and IQ. one member of each pair is allocated to one of the conditions under test and the second person is allocated to the other condition.
What is the limitation of repeated measures design? And how would you deal with this?
Order effects e.g practice effect (doing better on the second condition) or boredom effect (doing worse on the second condition)
They may also guess the hypothesis and alter their behaviour on the second one.
Counterbalancing - ABBA design.
What is counterbalancing?
ABBA design used as a precaution against order effects.
Some of the participants do condition A then B, and some do B then A. It involves altering the order in which participants complete the different conditions.
What are limitations of independent groups designs?
•Participant variables like individual differences are less controlled which introduces more variation due to extremely variables and may even introduce a confounding variable
•more participants are needed than in a repeated measure design because they are two separate groups
How can we deal with the limitations of independent groups?
Randomly allocate participants to distribute the participant variables that might otherwise influence the results. this can be decided by tossing a coin for example.
Give a strength of independent groups design
Reduces order effects because participants only take part in one condition their performance in the one condition will not influence their performance in another.
Give one strength of repeated measures design
No participant variables can affect results
What is a limitation of match pairs design?
Time-consuming to find sufficient participants matched on key variables
Matching is always imperfect and there may be variables that are missed . Matching is never perfect.
How may you deal with the time-consuming limitation on match pairs design?
Restrict the number of variables to match participants on
One strength of matched pairs design
Participant variables are controlled to reduce extraneous participant variables
What is a field experiment?
An experiment conducted in the participants home ground and not controlled environment and the IV is manipulated by the experimenter.
What is a laboratory experiment?
An experiment conducted in a controlled environment where the experiment controls the IV. participants are aware they are taking part but may not know the aims.
What is cause-and-effect?
The manipulation of the IV and observing consequence changes in the DV.
Strengths of lab and field experiment
• good control of the IV makes experiments high in internal validity so more easily replicated, meaning you can do it again to check the same effect occur as many times this makes it more reliable.
• well designed experiments lead to greater confidence that any changes in the DV are caused by the IV.
• more certainty of cause and effect
Limitation of lab experiments
Low in ecological validity. Because of the high control in the experimental situation, the results may not reflect real life as not as many things are controlled in real life so it may not be generalisable to other contexts. these studies lack mundane realism.
•demand characteristics – the lab environments may influence people to think how they should be behaving/looking for clues. They end up behaving artificially and not naturally so this is a threat to validity.
Limitation of field experiment
Ethical issues – if participants do not know they are taking part of the study they cannot have the right to withdraw or fully give informed consent.
What are demand characteristics?
Clues that make participants aware of the aims of a study, so their behaviour is influenced and they end up behaving artificially which is a threat to validity.
What are investigator effects?
Anything researcher unintentionally does that has an effect on influencing participants behaviour that become EVs and then affect the data collected in the study
What is the meaning of generalisation?
Applying the findings of a particular study to the population
What is the difference between a population and a sample?
A population is a group of people with the character characteristics that the researcher is interested in from which the sample is drawn. The sample is the selected participants from the population that is intended to produce a representative group.
What is a natural experiment?
The IV naturally occurs, usually to do with events, and the DV is gathered after the event for example looking for differences in behaviour before and after the event.
What is a quasi-experiment?
The IV occurs naturally and the DV can be measured in a laboratory. E.g Comparing characteristics of people that are pre-existing.
What is the strength of using natural or quasi experiments?
Opens up research possibilities - enables psychologists to study ‘real’ life problems with higher mundane realism and ecological validity
Limitations of natural or quasi experiments (2)
•doubts over cause and effect - lack of control over IV so we cannot be certain that it caused the changes in the DV due to possible confounding variables.
•may be pre-existing uncontrolled differences that act as confounding variables so sample may be biased. Participants cannot be randomly allocated.
How can investigator effects be reduced?
Standardised instructions and double blind procedures. Separate research can be carried out by two or more researchers and comparison between the two. (Inter-observer reliability)
What are advantages of open questions?
Detailed information (qualitative information) can be given as respondents can expand on their answers. New insights can be given too that provide opportunities to further explore.
What are disadvantages of open questions?
Not all participants feel so vocal with expressing their opinions so might not capture everything.
Qualitative data may be more difficult to compare and summarise BECAUSE OF VARIETY.
What are advantages of closed questions?
Limited range of answers so can produce quantitative data that can be easier to analyse and produce findings.
What are disadvantages of closed questions?
Participants are forced to answer in a certain way data may lack validity.
What is debriefing and why is it important?
Debriefing is post-research interview to informs participants of the true nature of the study.
It is important to restore them to their original state and may be used to gain useful feedback.
What are correlations?
When a researcher/psychologist is looking for a relationship between two co-variables. They look for similarities.
What is a correlation coefficient?
A number between -1 and +1 that tell us how closely the co-variables in a correlational analysis are associated.
What is a limitation of correlations?
No conclusion can be made on cause and effect, only association between the variables
What is a case study
A detailed study of a single institution, individual or event. They provide rich data but are hard to generalise from.
What is content analysis?
A form of indirect observation in which artefacts people produce are analysed.
What is meta analysis?
A researcher combines findings from similar studies and produce a statistic to represent the overall effect.
Meta analysis systematic review
Findings from carefully selected studies are summarised to give knowledge in a particular area.
Strength of meta analysis
Combining results from different studies increases sample size which means findings can be generalised and you’ll end up with high population validity.
Limitation of meta analysis
Research designs in the studies selected may vary so they are not easily comparable. Combining then may obscure any differences so conclusions are not always valid.
Strengths of a case study (give 2)
• richness and depth of analysis
• useful for investigating rare cases that wouldn’t be ethical to generate experimentally
Strength of content analysis
High ecological validity because it’s on tangible evidence.
Limitation of content analysis
Observer bias reduces validity of the findings as observers may interpret data differently.
What are measures of central tendency?
Statistic that provide information on a typical value in a data set. Mean, median, mode.
What are measures of dispersion?
Statistics that provide information about how spread out a set of data are. Range, standard deviation.
What is a nominal level of measurement
Simply counting something
Evaluation of the mean
• + most sensitive and it uses all values in the data set
• - can be distorted by extreme values in the set, and so misrepresent the data set.
Evaluation of the median
•+ unaffected by extreme scores
• - may not be representative as it doesn’t use all values in the set
Evaluation of the mode
• + unaffected by extreme values , data used can be nominal
• - not useful when there’s multiple modes.
Evaluation of the range
• + easy to calculate
• - sensitive to distortion by extreme values. Doesn’t tell you how far away the data points are from the mean
Evaluation of standard deviation and what is it
It is a measure of how much scores in a data set differ from the mean
+ a precise measurement as it uses all values in the data set
- May conceal some of the characteristics like extreme values
Limitations of a case study (2)
•problems with establishing cause and effect. No control against which to make comparisons.
•potentially unreliable recollection of past events. We are using old data that may not be accurate.
Low generalisability to other individuals due to the small sample size
