Research Methods Flashcards
Experimental Method
Involved the manipulation of an independent variable (IV) to measure the effect on the dependent variable (DV). Experiments may be laboratory, field, natural or quasi.
Aim
A general statement of what the researcher intends to investigate, the purpose of the study.
Hypothesis
A clear, precise, testable statement that states the relationship between the variables to be investigated. Stated at the outset of the study.
Directional Hypothesis
States the direction of the difference or relationship between the IV and DV.
Non-Directional Hypothesis
Does not state the direction of the difference or relationship between the IV and DV.
Variables
Any ‘thing’ that can vary or change within an investigation. Variables are generally used in experiments to determine if changes in one thing result in changes to another.
Independent Variable
(IV) Some aspect of the experimental situation that is manipulated by the researcher - or changes naturally - so the effect on the DV can be measured.
Dependent Variable
(DV) The variable that is measured by the researcher, any effect on the DV should be caused by the change in the IV.
Operationalisation
Clearly defining variables in terms of how they can be measured.
When do we use a Directional Hypothesis?
When the theories or findings of previous research studies suggest a specific outcome.
When do we use a Non-Directional Hypothesis?
When there is no theory or previous research, or findings from previous studies are contradictory.
Levels of the IV
How many different conditions there are in an experiment.
Extraneous Variables
(EV) Any variable, other than the IV that may effect the DV if it is not controlled. Do not vary systematically with the IV.
Confounding Variables
A kind of EV that varies systematically with the IV, so we can’t tell if the IV is the variable making the change to the DV or if its the EV.
Demand Characteristics
Any cue from the researcher or from the research situation that may be interpreted by participants are revealing the purpose of an investigation. This may lead to a participant changing their behaviour within the research situation.
Investigator Effects
Any effect of the investigator’s behaviour (conscious or unconscious) on the research outcome (the DV). This may include everything from the design of the study to the selection of, and interaction with, participants during the research process.
Randomisation
The use of chance methods to control for the effect of bias when designing materials and deciding the order of experimental conditions.
Standardisation
Using exactly the same formalised procedures and instructions for all participants in a study.
Experimental Design
The different ways in which participants can be organised in relation to the experimental conditions.
Independent Groups Design
Participants are 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 Design
Pairs of participants are first matched on some variable(s) that may effect the dependent variable. Then one member of the pair is assigned to Condition A, and the other to Condition B.
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 condition as any other.
Counterbalancing
An attempt to control for the effects of order in a repeated measures design: half the participants experience the conditions in one order, and the other half in the opposite order.
Evaluation: Independent Groups Design
- Economical issue, twice as many participants would be needed to produce equivalent significant data to a repeated measures design
- No order effects, less risk of fatigue and uninterest
- Less risk of demand characteristics as seeing only one condition
Evaluation: Repeated Measures Design
- Order effects, each participant must partake in multiple conditions and may become bored/tired
- Higher risk of demand characteristics, as participants take part in all conditions
- Participant variables are controlled as everybody takes part in every task
- Less participants needed, half of independent groups/matched pairs
Evaluation: Matched Pairs Design
- May be time consuming and expensive, as every participant must be matched for a particular variable
- Less risk of participant variables as one has been matched, however you cannot match EVERY participant variable
- Participants only take part in one condition, less order effects and demand characteristics
Laboratory (Lab) Experiment
An experiment that takes place in a controlled environment within which the researcher manipulated the IV and records the effect on the DV, whilst maintaining strict control of extraneous variables.
Field Experiment
An experiment that takes place in a natural setting within which the researcher manipulates the IV and records the effect on the DV.
Natural Experiment
An experiment where the IV is naturally occurring and is caused to vary by some other natural factors. The researcher records the effect on a DV they have decided on.
Quasi Experiment
A study where the IV is naturally occurring and is already a difference between people that already exist such as age or gender. The researcher records the effect on a DV they have decided on
Evaluation: Laboratory Experiment
- High control over EVs and CVs, so the effect on the DV is more likely to be from the IV, meaning it has high validity
- Replication is easier because of high control, so the findings can be verified
- May lack external validity, as they occur in artificially crafted settings, they may not generalise to real life
- Participants are fully aware they are in an experiment, may result in demand characteristics
- May not represent everyday experience, low mundane realism
Evaluation: Field Experiment
- Higher mundane realism as the environment is more natural and may produce more authentic and realistic behaviour
- Less control over EVs and CVs, cause-and-effect relationship may be more difficult to find, lower internal validity
- Ethical issues, if participants are unaware they are being observed they cannot give informed consent and may be an invasion of privacy
Evaluation: Natural Experiment
- Provide opportunities for research that may not otherwise be undertaken for practical or ethical reasons
- Natural experiments often have high external validity because they involve the study of real-world issues and problems that happen
- Natural occurring events occur rarely, reducing opportunities for research
- Participants cannot randomly be allocated to experimental conditions, so there is less certainty that the IV directly affected the DV as it may have been influenced by participant variables
Evaluation: Quasi Experiment
- Can be replicated somewhat as they are often carried out under controlled conditions
- May have confounding/participant variables as participants cannot be randomly allocated to groups
- The IV cannot be manipulated so we struggle to prove it has caused any observable change
Population
A group of people who are the focus of the researcher’s interest, from which a smaller sample is drawn.
Sample
A group of people who take part in a research investigation. The sample is drawn from a (target) population and is presumed to be representative of that population.
Sampling Techniques
The method used to select people from the population.
Bias
In the context of sampling, when certain groups are over or under represented within the sample selected. For instance, there may be too many younger people. This limits the extent to which generalisations can be made to the target audience.
Generalisation
The extent to which findings and conclusions from a particular investigation can be broadly applied to the population. This is possible if the sample of participants is representative of the target population.
Random Sample
Begin with a list of every member of the population, and input their names into a program that assigns them a number from 1-n, where n is the amount of people in the population. Then use a random number generator to generate a number and find which member of the population is matched to this number. Repeat this until the desired sample size is met.
Systematic Sample
Begin with a list of every member of the population, and select every nth person to be in your sample.
Stratified Sample
Begin with a list of every member of the population and identify the different sub-groups/strata that make up the population. Then calculate how many people from each sub-group/strata would be needed so that the amount from each sub-group/strata in the sample is proportional to the amount in the population. Finally use random sampling for each sub-group/strata.
Opportunity Sample
Selecting people who happen to be willing and available to take part in the study by asking around at the time of the study.
Volunteer Sample
Using a notice board (or similar) to advertise the study and participants willingly come to the researcher, volunteering to take part.
Evaluation: Random Sample
- Usually unbiased as every participant has an equal chance of being selected and extraneous/confounding variables should be equally divided
- More difficult and time consuming, as a sampling frame (list of population) may be needed
- Does not guarantee a representative sample as it is random, increases the likelihood of one but no guarantee
Evaluation: Systematic Sample
- Objective, as once a system is chosen the researcher has no influence over who is chosen
- More difficult and time consuming, as a sampling frame (list of population) may be needed
Evaluation: Stratified Sample
- Produces an accurate sample as it is accurately designed to reflect the population, this means that generalisation of findings becomes possible
- However, it cannot account for every single sub-group, so complete representation of the population is not possible
- More difficult and time consuming, as a sampling frame (list of population) may be needed
Evaluation: Opportunity Sample
- Convenient and easy, as a sampling frame (list of population) is not required
- May include bias as the sample is unrepresentative as it only includes people from a specific area and cannot generalise to an entire population
- Researcher has full control, and may avoid those they judge to not be fit for the study, introducing researcher bias
Evaluation: Volunteer Sample
- Convenient and easy, as a sampling frame (list of population) is not required
- Volunteer bias is a problem, asking for volunteers may attract a specific demographic of people from the population, i.e. those who are confident and have enough time on their hands to partake
Ethical Issues
Arise when conflict exists between the rights of participants in research studies and the goals of research to produce authentic, valid and worthwhile data.
BPS Code Of Ethics
A document produced by the BPS (British Psychological Society) that instructs psychologists in the UK about what behaviour is and isn’t acceptable when dealing with participants.
Ethical Issue: Informed Consent
- Involves participants being aware of the aims of the research and clearly understanding what will happen to them in an experiment and willingly stating they accept the terms and wish to continue
- May introduce demand characteristics however, as they know what they are being studied on
- Participants should be issues a consent letter detailing all relevant information
Alternative Ways of Gaining Consent
1) Presumptive Consent - Asking a similar group of people if the study is acceptable, if they approve, then the consent of the original participants is ‘presumed’.
2) Prior General Consent - Participants give their permission to take part in a number of different studies, including one that will involve deception. By consenting, participants are effectively agreeing to be deceived.
3) Retrospective Consent - Participants are asked for their consent during debriefing after already having taken part.
Ethical Issue: Deception
- Deliberately misleading or withholding information from the participants at any stage of the investigation
- If they have been deceived, they cannot give informed consent
- However, there are occasions where deception can be justified if it does not cause the participant undue stress
- At the end of the study, participants should be given a full debrief of what the experiment was and should be told the true aims
- They should also be told that their data is confidential and can be withdrawn should they choose it to be
- Participants should be told their behaviour was natural, and given a counselor if they are under extreme stress
Ethical Issue: Protection From Harm
- Participant should never be in any more risk than they would be in their daily lives
- They should be protected from both physical AND psychological harm
- They should not feel inadequate, embarrassed or under any stress
- They should leave the experiment feeling exactly how they did before they arrived
- At the end of the study, participants should be given a full debrief of what the experiment was and should be told the true aims
- They should also be told that their data is confidential and can be withdrawn should they choose it to be
- Participants should be told their behaviour was natural, and given a counselor if they are under extreme stress
Ethical Issue: Privacy And Confidentiality
- Participants data should be kept anonymous and protected, and can be withdrawn at any time should the participants choose it to be
- Privacy extends to the area the experiment took place, such that institutions or geographical locations are not named
- Participants should not be referred to by name in their data, numbers/initials are plausible substitutes
- Participants should always be reminded in the debrief that their data is private and will not be shared
Ethical Issue: Right To Withdraw
- Participants should always be reminded that their participation is voluntary and they have the right to leave at any time
- They should never feel obliged or forced to stay in a study should they feel stressed, uncomfortable or just unwilling to continue taking part
- Remind the participant before and after the experiment that they have the right to withdraw at any time
Pilot Study
A small-scale version of an investigation that takes places before the real investigation is conducted. The aim is to check that the procedures, equipment and measuring scales all work as intended so that modifications can be made before the real experiment.
Single-Blind Procedure
Where participants are left in the dark about the aim of the research at the beginning of the study. Other details may be kept from the participants, such as the experimental condition they are in, or whether there is another condition at all. This reduces the chance of demand characteristics, but can be deemed unethical.
Double-Blind Procedure
Neither the participant nor the researcher who conducts the study are aware of the aims of the investigation, with a third party often being the one in control. They are often an important feature of drug trials. This reduces the chance of demand characteristics and researcher effects, but can be deemed unethical.
Naturalistic Observation
Watching and recording behaviour in the setting within which it would normally occur.
Controlled Observation
Watching and recording behaviour within a structured environment, i.e. one where some variables are managed.
Covert Observation
Participants’ behaviour is watched and recorded without their knowledge or consent.
Overt Observation
Participants’ behaviour is watched and recorded with their knowledge and consent.
Participant Observation
The researcher becomes a member of the group whose behaviour he/she is watching and recording.
Non-Participant Observation
The researcher remains outside of the group whose behaviour he/she is watching and recording.
Evaluation: All Observations
- Have the benefit of capturing what people actually do, opens up the possibility of finding unexpected behaviour
- However observer bias is an issue, as one person’s interpretation may diff from another’s
- Difficult to detect a cause-and-effect relationship
Evaluation: Naturalistic Observations
- Have high external validity as they can generalise to everyday life, as behaviour is observed in locations where they would naturally occur
- However, lack of control can make replication difficult
- Extraneous variables and confounding variables may be present
Evaluation: Controlled Observations
- Have lower external validity as they observe situations that occur in artificially created settings
- Replication is easier, and extraneous variables/confounding variables are less of a factor
Evaluation: Overt Observations
- More ethically/morally acceptable
- However, participants know they are being watched, may introduce demand characteristics
Evaluation: Covert Observations
- Demand characteristics are controlled, as participants are unaware they are being watched, more genuine behaviour
- Higher internal validity
- Has ethical issues however, as participants cannot give informed consent and their own privacy is invaded
Evaluation: Participant Observations
- As the researchers are also taking part, they have increased insight into the activity and participants, higher external validity
- However, the researcher can identify too strongly with who they are studying and lose objectivity
Evaluation: Non-Participant Observations
- Maintain an objective psychological distance so there is less danger of becoming subjective
- However, less insight may be gained than in a participant observation
Behavioural Categories
When a target behaviour is broken up into components that are observable and measurable (links to operationalisation)
Event Sampling
A target behaviour or event is first established, then the researcher records this event every time it occurs
Time Sampling
A target individual or group is first established, then the researcher records their behaviour in a fixed time frame, say, every 60 seconds
Evaluation: Behavioural Categories
- Can make data more structured and objective
- However, categories must be clear and unambiguous, and should not require further interpretation
- All possible forms of the behaviour should be on the check list
- Categories must not overlap, e.g. grinning and smiling
Evaluation: Event Sampling
- Useful when the target behaviour/event happens quite infrequently and could be missed if time sampling was used
- However if the event is too complex, details may be missed
Evaluation: Time Sampling
- Useful in reducing the number of observations that need to be made
- However, those segments of observation may not be representative of the observation as a whole
- Additionally, if an important behaviour occurs outside of the time segment, it must be discarded
Self-Report Technique
Any method in which a person is asked to state or explain their own feelings, opinions, behaviours and/or experiences related to a given topic
Questionnaire
A set of written questions used to assess a person’s thoughts and/or experiences
Interview
A ‘live’ encounter where one person asks a set of questions to assess an interviewee’s thoughts and/or experiences, the questions may be pre-set (structured interview) or may develop as the interview goes along
Structured Interview
An interview made up of pre-determined questions that are asked in a fixed order
Unstructured Interview
An interview which works more like a conversations, the questions are not pre-determined and develop as the interview progresses
Evaluation: Questionnaire
- Cost-effective, can gather large amounts of data quickly as they can be distributed in large numbers to lots of people
- Researcher does not need to be present during the interview
- Very straightforward data to analyse, especially if data is quantitative
- Responses may not always be truthful, and it is much easier to lie on a questionnaire, social desirability bias
- Questions may just be skim read and not answered with thought and full attention
Evaluation: Structured Interview
- Very straightforward to replicate due to standardised format
- However, lacks rich data with insight into participants as they cannot deviate from the script to ask any more questions
Evaluation: Unstructured Interview
- Much more flexible than the structured interview, the researcher can follow up points made by interviewees
- However, increases the risk of interviewer bias
- Analysis of the data is much harder, as there is a lot more complex and irrelevant information
Open Questions
Questions for which there is no fixed choice of response and respondents can answer in any way they wish
Closed Questions
Questions for which there is a fixed choice of responses determined by the question setter
Likert Scale
A type of closed question, participants indicate their agreement with a statement using a scale of usually five points, usually ranging from ‘Strongly Agree’ to ‘Strongly Disagree
Rating Scale
A type of closed question, participants identify a value that represents their strength of feeling about a particular topic
Fixed-Choice Option
A type of closed question, participants select from a list of possible options which ones apply to them
Writing Good Questions
- Should be easily understood
- Avoid emotive language and opt for neutral alternatives
- Avoid leading questions that imply a specific answer is correct
- No double barrelled questions
- No double negatives
Correlation
A mathematical technique in which a researcher investigates an association between two variables, called co-variables
Co-Variables
The variables investigated within a correlation, for example, height and weight
Positive Correlation
As one co-variable increases, so does the other
Negative Correlation
As one co-variable increases, the other decreases
Zero Correlation
There is no relationship between the co-variables
Evaluation: Correlation
- Helps find patterns between two co-variables and can often be used as an idea of what to expect for researchers before they commit to conducting a study
- Relatively quick and economic to carry out, no controlled environment needed
- Does not tell us WHY they are related, cannot show a cause-and-effect relationship
- It is a possible that there’s a third variable messing with the results, ‘the third variable’ problem
- Correlations can be easily misused or misinterpreted
Qualitative Data
Data that is expressed in words and is non-numerical (however can be converted to numbers for purpose of analysis)
Quantitative Data
Data that can be counted and are usually numbers
Primary Data
Information that has been obtained first-hand by a researcher for the purposes of a research project
Secondary Data
Information that has already been collected by someone prior to the present research project
Meta-Analysis
The process of combining the findings from a number of studies on a particular topic, the aim is to produce an overall statistical conclusion based on a range of studies
Evaluation: Qualitative Data
- Offers much more rich data as it gives more detail
- Greater external validity as it shows more about the world’s view
- More difficult to analyse and draw conclusions
- Less objective as answers are left up to interpretation
Evaluation: Quantitative Data
- Easier to analyse and draw conclusions with
- More objective as answers are answers are very factual and statistical
- Offers less rich data as it has little detail
- Less external validity
Evaluation: Primary Data
- Authentic and works well for the investigation it is intended to be used for
- Requires more effort, planning, and money
Evaluation: Secondary Data
- Can be accessed in a matter of minutes with minimal effort required
- Uncertain variation in quality and authenticity of data, data may be outdated or just incorrect
Descriptive Data
The use of graphs, tables and summary statistics to identify trends and analyse sets of data
Measures of Central Tendency
The general term for any measure of the average value in a set of data
Mean
Adding up all the values in a set and diving by the total number of values in set
Median
The central value in a set of data when values are arranged from lowest to highest
Mode
The most frequently occuring value in a set of data
Range
The difference between the highest value and the smallest value in a set of data
Standard Variation
Tells us how far scores move away from the mean, the larger the SV, the greater the spread of data
Scattergram
A type of graph that represents the strength and direction of the relationship between co-variables in a correlational analysis
Bar Chart
A type of graph in which the frequency of each variable is represented by the height of the bars
Histogram
A type of graph which shows frequency but, unlike a bar chart, the area of the bars represents the frequency
Normal Distribution
A symmetrical spread of frequency data that forms a bell-shaped pattern, the mean, median and mode are all located at the highest peak
Skewed Distribution
A spread of frequency data that isn’t symmetrical, where the data clusters to one end
Positive Skew
A type of frequency distribution in which the long tail is on the right side of the peak and most of the distribution is concentrated on the left, the mode is higher than the mean
Negative Skew
A type of frequency distribution in which the long tail is on the left side of the peak and most of the distribution is concentrated on the right, the mode is smaller than the mean
Statistical Testing
Provides a way of determining whether or not hypotheses should be accepted or rejected, by using them we can discover whether the differences or relationships between variables are significant or have occurred by chance
Sign Test
Statistical test used to analyse the difference in scores between related items
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
Evaluation: Peer Review
- Researchers may not be entirely objective as the person they are reviewing the work of may be an enemy, competitor for the same job, or trying to publish findings they PERSONALLY disagree with
- Can result in the burial of groundbreaking research
