Research methods Flashcards
What is an aim?
A straightforward expression, identifying the purpose of an investigation. Normally contains the words ‘investigate’ or ‘investigation’
What is a hypothesis?
A hypothesis is a precise, testable statement of what the researcher predicts will be the outcome of the study. Will always contain information about two variables. Usually proposes a possible relationship or cause and effect between two variables
What is an experimental/alternative hypothesis?
A hypothesis used in the context of an experiment. Predicts a difference/relationship between two variables
What is a directional (one-tailed) hypothesis?
States the expected direction of the results (use the words: more, less, increased, decreased, improved)
What is a non-directional (two-tailed) hypothesis?
States an expected difference, but does not state the direction of the results (use the words: difference, affect)
Starts with ‘there will be a difference’
What is a null hypothesis?
Predicts no difference between the two variables. It states that there will be no relationship/difference between the variables being investigated.
Always starts with ‘there will be no difference’
What is meant by ‘operationalising variables’?
Explaining how variables will be measured (DV) or manipulated (IV)
What is meant by ‘extraneous variables’?
An extraneous variable is one which MIGHT interfere with the DV (also referred to as uncontrolled variables or nuisance variables)
Why is it important to standardise in research?
- We need to make sure the procedure used and what participants are required to do is consistent
- If we do not ensure this we cannot be sure that the IV is truly manipulating changes in the DV
What is meant by the term ‘mundane realism’?
Refers to how a study mirrors the real world
If a study lacks mundane realism what are researchers unable to confidently do?
Generalise the data beyond the particular unique research setting
What is meant by the term ‘validity’?
Validity refers to whether an observed effect is a genuine one. A study is valid if it measures what it claims to measure
What is internal validity?
Concerned with what is going on inside of a study
What is external validity?
The degree to which a research finding can be generalised to other settings, groups of people and over time
What is the experimental design?
The way in which participants are allocated during an experiment
What are the two types of conditions in a basic experiment?
- The experimental condition
- The control condition
State the three types of experimental design
- Repeated measures
- Independent measures
- Matched pairs
Describe repeated measures
- The group does the experimental task with the IV set for condition 1
- The group repeats the experimental task with the IV set for condition 2
The same participants take part in both conditions
What are the problems with repeated measures?
- Individual characteristics of participants might influence the way they perform in an experiment
- Practice effect may occur, when the participants have done one condition they might perform better in the second one because they know the task
- Order effects such as fatigue and boredom affect the results
- Increased chance of demand characteristics
What are the strengths of repeated measures?
- Fewer participants are needed
- Good attempt to control participant variables
Describe independent measures
-Participants are randomly allocated to one or other of the conditions
- One group takes part in one condition
- One group takes part in the other condition
What are the strengths of independent measures?
- Reduced chance of demand characteristics
- Can use the same stimulus materials
- Order effects do not occur as the participants do only one condition
What are the problems with independent measures?
- More participants are needed
- Individual characteristics of participants which might influence the way they perform in an experiment
- Least effective design for controlling participant variables
Describe matched pairs
-Participants are matched as closely as possible with another participant- the pairs are randomly allocated to either one or the other condition
What are the strengths of matched pairs ?
- Participants are matched as closely as possible with another participant
- Identical twins provide researchers with a close match
- Order effects do not occur as the participants do only one condition
- Participant variables are eliminated
What are the problems with matched pairs?
- It is not possible to match all the participants characteristics
- More participants are needed
- Matching participants is very time consuming
- Individual characteristics of participants which might influence the way they perform in an experiment
What is counterbalancing?
A technique used to reduce order effects in a repeated measures design
What does counterbalancing ensure?
Each condition is tested equally as first of second
What are the two ways of counterbalancing?
- AB or BA
- ABBA
Describe the AB or BA way of counterbalancing
- Divide participants into two groups
- In group 1 each participant does A then B
- In group 2 every participant does B then A
How are results compared in the AB or BA way?
You have all the data for participants and can compare their performance on the two conditions
Describe the ABBA way of counterbalancing
- A ll participants take part in each condition twice
- Trial 1: Condition A
- Trial 2: Condition B
- Trial 3: Condition B
- Trial 4: Condition A
How are results compared in the ABBA way?
Scores on Trial 1 and 4 are compared with scores on Trial 2 and 3
What is meant by validity?
Validity refers to whether an observed effect is a genuine one. A study is valid if it measures what it claims to measure
What is internal and external validity?
Internal validity- concerned with what is going on inside of a study
External validity- The degree to which a research finding can be generalised to other settings, groups of people and over time
What are the three types of external validity?
- Population
- Historical
- Ecological
What is a pilot study?
A pilot study is a small-scale practice investigation, where researchers can check all aspects of research. Changes to design, method and analysis can be made in the light of this.
The findings from a pilot study are….?
Irrelevant
What are the some of the problems in a study that a pilot study can show?
- The study doesn’t relate to real life
- Demand characteristics
- Whether the sample can be generalised
- Standardised procedures
- Experimental design
- Ethical issues
What are the three key features of experimental design?
- MANIPULATION OF THE IV- the IV is directly manipulated by the researcher to produce a change in the DV
- CONTROL- efforts are made to control or hold constant all variables other than the IV and DV
- RANDOMISATION- participants are randomly allocated to each of the conditions
What is a quasi-experiment? Give an example
In a quasi-experiment, the IV does not vary-it is a condition that already exists (e.g. age, gender). There is no direct manipulation of the IV and lack of random allocation.
Example: Sheridan and King
What are the strengths of quasi-experiments?
- Can be used when it is not possible to manipulate the IV
- They are easy to repeat and check the results (high in reliability)
- They can be used to determine cause and effect relationships due to the manipulation of the IV
What are the weaknesses of quasi-experiments?
- Participants know they are in a study so may guess the aim of the study and change their behaviour to fit accordingly (demand characteristics)
- The experiment is highly controlled so the situations may be seen as unrealistic and artificial
- The experimenter’s expectations can affect the results and participants may be influenced by these expectations
- Not possible to randomly allocate participants to conditions and therefore there may be confounding variables
What are natural experiments? Give an example.
In a natural study, the researcher takes advantage of a naturally occurring variable. This usually takes place when it is not practical or unethical to manipulate the IV
Example: Rutter and Songua-Barke
What are the strengths of natural experiments?
- Due to the real world setting, results are more likely to relate to real life (mundane realism)
- The participants usually don’t know they’re in a study so their behaviour is more natural
- Can be used when it is not possible to manipulate the IV
What are the weaknesses of natural experiments?
- It is more difficult to control extraneous variables
- Some argue these experiments are unethical because the participants are not aware they are in a study
- It is difficult to repeat the experiment because the situation/environment will never be exactly the same again
What are field experiments? Give an example.
A field study takes place in a natural environment. The IV is manipulated but extraneous variables cannot be controlled. Participants not necessarily randomly allocated
Example: Bushman
What are the strengths of field experiments?
- Due to the real world setting, results are more likely to relate to real life (mundane realism)
- The participants usually don’t know they’re in a study so their behaviour is more natural
What are the weaknesses of field experiments?
- It is more difficult to control extraneous variables
- Some argue these experiments are unethical because the participants are not aware they are in a study
- It is difficult to repeat the experiment because the situation/environment will never be exactly the same again
What is a lab experiment? Give an example.
An experiment that is carried out in a controlled environment where the IV is manipulated. All other extraneous variables are controlled. Participants are randomly allocated to conditions
Example: Loftus and Palmer
What are the strengths of lab experiments?
- Has a high degree of control
- They are easy to repeat and check the results (high in reliability)
- They can be used to determine cause and effect relationships due to the manipulation of the IV
What are the weaknesses of lab experiments?
- Participants know they are in a study so may guess the aim of the study and change their behaviour to fit accordingly (demand characteristics)
- The experiment is highly controlled so the situations may be seen as unrealistic and artificial
- The experimenter’s expectations can affect the results and participants may be influenced by these expectations (investigator effects)
What are demand characteristics?
A cue that makes participants unconsciously aware of the aims of the study or helps participants work out what the researcher expects to find
What are investigator effects?
Anything that an investigator does that has an effect on a participant’s performance in a study other than what was intended.
How can you reduce investigator effects?
Double-blind designs
What is a single-blind design?
In a single-blind study, the participant is not aware of the research aims. This prevents them from seeking cues about the aims and reacting to them
What is a double-blind design?
Both the participant and the person conducting the experiment are blind to the aims. Therefore the person conducting the investigation is less likely to produce cues
What is experimental realism?
Experimental realism occurs when the task is sufficiently engaging so the participant pays attention to the task and not the fact that they are being observed
What is the target population?
A specific group of people the researcher is often interested in
What is a sample?
A sample is a small group of participants the researcher is interested in representing a target population
What is opportunity sampling?
Recruit those people who are most convenient or most available
What is random sampling?
A sample of participants produced by using a technique such that every member of the target population being tested has an equal chance of being selected
What is volunteer sampling?
Also known as a self-selected sample. To recruit participants, advertisements are placed in a newspaper or on a noticeboard or on the internet
What is systematic sampling?
A sample obtained by selecting every nth person
What is stratified sampling?
Subgroups (strata) within a population (ethnicity, gender, age) are identified. Participants are obtained from each of the strata in proportion to their occurrence in the population
Evaluate volunteer sampling
Strength: it is easy to locate a sample
Weakness: Inevitably biased due to the sample being drawn from a small part of the population
Weakness: Participants are more likely to be motivated causing a sample bias
Evaluate stratified sampling
Weakness: very time consuming
Strength: likely to be more representative because there is a proportional and randomly selected representation of subgroups
Strength: most representative of the target population
Evaluate systematic sampling
Weakness: not truly random unless you select a number at random, to begin with
Evaluate random sampling
Strength: unbiased
Evaluate opportunity sampling
Strength: gives access to a variety of participants
How do you carry out the lottery method of random sampling?
- Obtain a list of all the people in the population
- Put all the names in a lottery barrel or hat
- Select the number of names required
How do you carry out the random number method of random sampling?
- Every member of the population is given a number
- The starting position is determined blindly
- If your population is less than 100 you read the table two digits at a time
How do you carry out the random number generator method of random sampling?
- Number every person in the population
2. Using Microsoft Excel type =RAND(100) to get a number between 1 and 100
What is an ethical issue?
A conflict about what is acceptable in psychological research
What is the British Psychological Society (BPS)?
The organisation responsible for setting out guidelines of what is/ is not acceptable in psychological research
What is informed consent?
When someone agrees to participate in research, their consent must be informed
What are the arguments for informed consent from the participants and researchers perspective?
Researcher: sometimes informed consent is not possible because revealing the true aims of the study may lead to demand characteristics
Participant: consent is a basic human right and participants should be notified of the true aims in order to make an informed decision about whether they want to be in the study
What is deception?
Information being withheld from participants/ misleading participants
What are the arguments for deception from the participants and researchers perspective?
Researcher: Participants may alter their behaviour is deception does not occur
Participant: Unethical. Participants are prevented from giving informed consent- participants may be agreeing to something they don’t completely understand
What is the right to withdraw?
Participants have the right to withdraw at any time during the research, regardless of whether or not they have been paid
What are the arguments for the right to withdraw from the participants and researchers perspective?
Researcher: results may be sabotaged or biased if participants leave during the study
Participant: important knowledge in the case that the participant begins to feel emotionally distressed
What is the protection of participants?
Psychologists have the responsibility to ensure that their participants do not experience any psychological/physical harm during research
What are the arguments for protection of participants from the participants and researchers perspective?
Researcher: can be difficult to guarantee. It is difficult to predict the outcome of certain procedures
Participant: no physical or psychological harm should happen during the study
What is confidentiality?
Participants have the right for their information to remain private and used only for the purposes of the study
What are the arguments for confidentiality from the participants and researchers perspective?
Researcher: difficult to protect. sometimes it might be obvious who took part
Participant: Data Protection Act makes confidentiality a legal right and data must not be able to identify participants
What are the arguments for privacy from the participants and researchers perspective?
Researcher: difficult to avoid (e.g. field studies)
Participant: people do not expect to be observed in certain situations but it might be more acceptable in public spaces
What is a sample bias?
All sampling methods are inevitably biased even though they aim to produce a representative sample
What is volunteer bias?
Volunteers who take part are more likely to be different to other members of the population and this distorts the data
What are the four different ways that ethics are dealt with?
- Cost-benefit analysis: the costs of the research are judged against the benefits from the perspectives of the participant, society and groups of individuals
- Ethics committee: in places where research takes place a board must approve the study before it begins, taking into consideration how issues will be dealt with and weighing up the costs and benefits
- Ethical guidelines: give guidance on how to deal with ethical dilemmas and tell psychologists what is and isn’t acceptable
- Punishments: psychologists who ignore guidelines and behave unethically will be barred from research or practice
What does a debriefing statement need to be/include?
- Personalised
- Explanation of aim
- Description of all conditions
- Deception involved
- Specific ethical issues e.g. right to withdraw, confidentiality
Evaluate ethical guidelines and cost-benefit analysis
- Ethical guidelines are too general because they can’t cover every single situation
- Cost-benefit analysis is difficult to predict prior to the study and even after the study (it solves nothing because you can’t exchange one set of dilemmas for another)
What are examples of non-experimental methods?
- Case studies
- Content analysis
- Meta-analysis
- Correlational analysis
- Self-report techniques (interviews and questionnaires)
- Naturalistic and controlled observations
What is inter-observer reliability?
Inter-observer reliability refers to the extent to which there is consistency between 2 or more recordings
What are the advantages of a structured observation?
- Objective and rigorous
- Better method to use in comparison to unstructured observations
What are the advantages of unstructured observation?
-good to use as a pilot study, especially when the area of research is new
What are the disadvantages of unstructured observation?
- All behaviour is recorded, but no system is in place
- Visible and eye-catching data may be recorded but may be of no importance to the researcher
- There may be too much data to record
What are behavioural categories?
Target behaviour is systematically divided up into operationalised and specific categories
What do behavioural categories have to be?
- Objective
- Mutually exclusive
- Covers all possible behaviours within the target behaviour
What is event sampling?
Counting the number of times a behaviour occurs in a given time period
What is time sampling?
Recording behaviours within a specific time frame
What are questionnaires?
A set of written questions, designed to collect information about a topic
What are the features of a good questionnaire? (4)
- Clarity- there should be no ambiguity and the respondent should understand clearly what is being asked
- Analysis- should include both closed and open questions to be easily analysed
- Bias- Bias should be avoided by avoiding questions that may lead respondents to answer in a particular way
- Filler questions should be included to distract respondent and thus reduce demand characteristics
What is the Lickert scale?
Respondents indicate their agreement with a statement using a 5 point scale
What is a fixed choice option?
This includes a list of possible options and respondents indicate those that apply to them
What is an advantage of closed questions over open questions?
Closed questions are easier to analyse as data from open questions cannot be analysed statistically
What is a structured interview?
Pre-determined questions asked in a fixed order
What is an unstructured interview?
- more like a conversation
- no set questions
- there is a general aim and interviewee is encouraged to expand and elaborate their answers through prompts by interviewer
What are the advantages of a structured interview?
- more reliable
- avoid interviewer bias
What is a correlation?
A relationship between two co-variables. A correlational analysis is looking to determine the extent to which a relationship exists between co-variables
What are correlations represented on?
A scattergram
How should a scattergram be plotted?
- Label axis
- Title
- Sensible scaling
- Correctly plotted data
What is a positive correlation?
As one variable increases, the other increases
What is a disadvantage of a correlational analysis?
Difficult to establish a cause and effect
What is a correlational coefficient?
A numerical representation of the strength and direction of the relationship of two co-variables
What can a correlation coefficient range from?
0 to 1
What is the difference between correlations and experiments?
- We can not establish a cause and effect in a correlational analysis because the IV is not being directly manipulated
- Covariables are simply measured
- Correlations offer an indication of the nature of the relationship between two co-variables
What is a strength of self report techniques?
Allows access to what people think and feel
What are the weaknesses of self-report techniques?
- People may not be honest
- Social desirability bias
- Answers may lack validity
- The sample may lack representativeness and the data may not be able to be generalised
What are the strengths of a questionnaire?
- can be distributed to large numbers of people cheaply and quickly
- data can be collected from a large sample
- participants may feel more willing to reveal personal information than in an interview
- reduces social desirability bias
What is a weakness of a questionnaire?
-only filled in by people who can read and write and who are willing to spend time filling it in, resulting in a biased sample
What are the strengths of a structured interview?
- Easily repeated
- Answers from different people can be compared
- Easier to analyse
What are the weaknesses of a structured interview?
- Low reliability if the same interviewee behaves differently or if the same interviewers behave differently
- Interviewer bias
What is the strength of an unstructured interview?
More detailed information can be obtained
What are the weaknesses of an unstructured interview?
- Require interviewers with more skill
- More expensive to produce
How are interviews recorded?
Interviews may be audio recorded or video recorded so that the interviewer’s listening skills are not disrupted and everything the interviewee says is documented
What effect does the interviewer have on the interview?
Non verbal communication- certain behaviours communicate disapproval and others encourage the respondent to speak
Listening skills- they should not interrupt too often and they should have a range of encouraging comments
What should the questioning skills be like in an unstructured interview?
- Important to be aware of the questions already asked and avoid repeating them
- Avoid probing
- Ask more focused questions
What is nominal data?
Data are in separate categories (e.g. favourite football team)
What is ordinal data?
Data are ordered in some format
What is interval data?
There are equal intervals between each data point (e.g. temperature)
What is ratio data?
There is an absolute zero point- there is no value below zero (e.g. heigh, weight)
What are measures of central tendency? State the three types.
Measures of tendency tell us where the average is in a set of data. The three measures of tendency are:
- Mean
- Median
- Mode
What is an advantage and disadvantage of the mean?
-It is the most sensible measure of central tendency, taking ALL scores into account
However
-One result that is extreme can easily distort your mean= less valid
What is an advantage and disadvantage of the median?
-Median is best on ranked (ordinal) data
However
-Ignores all other data
What is an advantage and disadvantage of the mode?
-Mode can be used for nominal data
However
-Ignores the rest of the data
What are measures of dispersion? Name the two types
Measures of dispersion tell you about how all the data is spread. You can measure dispersion using:
- Range
- Standard deviation
What does the standard deviation tell us?
- The standard deviation allows us to see the consistency at which the IV impacted upon the DV
- The more spread the data is from the mean the higher the deviation
What are the characteristics of a histogram?
- Area within the bars is proportional to the frequencies represented
- The vertical axis must start at zero
- The horizontal axis must be continuous
- There should be no gaps between the bars
What are the characteristics of a scattergram?
-Used when doing a correlational analysis (association between two sets of data)
What are the characteristics of a bar charts?
- The height of each bar represents the frequency
- Suitable for data which is discontinuous (has no particular order)
- A space is left between each bar to indicate lack of continuity
What are the characteristics of a line graph?
- Continous data on the x axis
- Dot to mark each point
- Each dot is connected by a line
What is a normal distribution?
An arrangement of data that is symmetrical and forms a bell-shaped pattern
-The mean, median and/or mode falls in the centre at the highest peak
What is a negative skew?
When data is skewed to the left: the median is typically greater than the mean
What is a positive skew?
when data is skewed to the right: the mean is greater than the median
What is quantitative data?
- Quantity
- Looks at averages and differences between groups
- Deals with numbers
- Data can be measured
What are the advantages of quantitative data?
- Easy to analyse
- Can be used in lab, field, natural and quasi studies
What is qualitative data?
- concerned with attitudes, beliefs, fears and emotions
- quality
- deals with descriptions
- data is observed, not measured
What is the advantage of qualitative data?
can be used for self-report techniques and interviews
What is primary data?
- Collected first hand from the researcher
- Collecting primary data would involve designing a research study
- Can be an experiment, questionnaire etc
What is secondary data?
- Originally collected for a different purpose other than the current research
- May originally have been collected by a different researcher
- Government statistics, institutional reports and previous studies are examples of secondary data
What does statistical testing determine?
Whether a hypothesis should be accepted or rejected
What is a sign test?
A statistical test used to analyse the differences in scores
When should you use a sign test?
- When looking for a difference rather than an association
- Experiment would have used repeated measures design
- The data should be nominal; (categorical data)
What is the probability value in psychology?
Usually 0.05 (5%)- this is the level at which the hypothesis is either rejected or accepted
What is peer review?
The evaluation of quality and validity in scientific, academic or professional work by other experts working in the same field
What are some of the implications of faulty data?
- Psychology loses credibility as a field
- Leads to discrimination against certain groups
- Other psychologists use the data in their own research and a whole field of research becomes false
- Breaching ethical issues
What is an academic journal?
Typically peer reviewed, academic journals are periodicals in which researchers publish articles on their work. Most often these articles discuss recent research
What are the three purposes of peer reviews?
- Assessing the research ratings of university departments- science departments are required to actively carry out research. The research is quality assessed and departments are funded depending on how good the research is
- Allocation of research funding- the government uses 5.8 billion pounds for scientific research and peer reviews are required to decide which research is most likely to be worthwhile
- Publication of research in academic journals and books- the point of journals is to share results of research. Without peer review, there is the issue of incorrect or false data being publicised
Evaluate peer review
- If peer review hasn’t been carried out by an expert poor research might be passed because the reviewer didn’t really understand it
- Anonymous per review is honest and objective BUT the veil of anonymity can be used to settle old scores or bury rival research
- Journals prefer to publish positive results which creates a bias in published research
- Peer review preserves the status quo because it results in a preference for research that goes with existing theory
- Peer review can never deal with already published data that might be fraudelent
- On sites like Wikipedia it is more difficult to detect ‘subtle viewpoint promotion’, however bias that would be unchallenged ina traditional reference work would be more likely to be pointed out
What is economic psychology?
The development and application of theoretical and psychological knowledge in the context of practical economic problems
Name three ways psychological research benefits the economy
- Attachment- Bowlby highlighted the importance of emotional care in early childhood which has helped shape policy in ensuring the healthy development of children
- Improving memory- The cognitive interview improves the amount of accurate information collected from eyewitnesses- this is able to reduce expenses on wrongful arrests and ensures criminals are caught
- Mental health- The direct cost of mental health in England is 22.5 billion pounds. Evidence based research on effective drug therapies is important in reducing costs and helping people return to work