Research Methods: Flashcards
Hypotheses:
What is an IV
What is DV
Extraneous variables
Independent Variable: The thing the experimenter changes.
Dependent Variable: The thing measured by the experimenter, so the thing that changes as a result of the IV being applied.
EV’s something that may unintentionally affect the DV so should be controlled.
Formula for an alernative Hypothesis
relationship + DV + two levels of IV (one being the control group)
What is a Null Hypthesis
A statement that there is no relationship between the variables being tested
What is an Alternative Hypothesis
The traditional form of hypothesis, opposite to Null hypotheses. States a relationship beween variables.
What is an Extraneous variable
The only thing that should cause a change in the DV is the IV. EV’s are unwanted variables that could also affect the DV.
Research Procedures: Define instructions to participants
Research Procedures: Instructions to participants means giving the same information abt the study to all participants.
Research Procedures: What are standardised procedures?
Research Procedures: What are standardised procedures? The list of instructions given to all participants.
Research Procedures: what is Randomisation
Research procedures: Randomisation is using change, ie tossing a coin to control effects of bias when designing a study.
Research Procedures: Ethical issues, what are the four elements of informed consent?
Research Procedures: Ethical issues
1. Informed consent: Participants should be told the purpose of research and that they can leave at any time.
- Deception: Participants should not be lied to or misled. Mild deception can be justified.
- Privacy: Participants have the right to control information about themselves.
- Confidentialilty: Personal data must be protected and respected.
Research Procedures: Define what is meant by ethical issues
Research Procedures:
Ethical issues are the conflicts between participants rights and wellbeing and the need to gain valuable results.
Research Procedures: Four ways to deal with ethical issues.
Research Procedures: Ethical issues can be dealt with by adhering to:
- British Psychological Society (BPS) guidelines
- Dealing with informed consent; Partificipants or guardians sign a form telling them what is expected.
- Dealing with deception and protection from harm: Participants must be fully debriefed to explain true aims and reduce distress. Further action can be offered if appropriate.
- Dealing with privacy and confidentialilty: Participants should be anonymous (number or initialed). Data cannot be shared unless agreed to in advance.
What is BPS and what does it do.
BPS stands for British Psychological Society and is a code of conduct that all professional Psychologists in the UK must adhere to.
Reliability: Quantitative methods, 4 points abt reliability one general and three relating to Lab / ints-Quest / observation
Reliability, Quantitative methods:
- Tend to be most reliable.
- Lab experiments, easy to control and replicate
- interviews/questionaires. Closed questions most reliable. Same person shuld answer the same question in the same way.
- Observation. One observer, obtain same result when repeated. Two observers, obtain same results (interobserver reliability).
Reliability: Qualitative methods, one general points abt reliability abt Case studies and unstructured interviews
Reliability, Qualitative methods:
- Less reliable
- Case studies and unstructured interviews are diffult to repeat in the same way.
What is validity
Validitiy is representative of “Real world” application
Validity with regard to sampling methods, 2 general comments
- May not reflect the whole population
2. Representativeness low in opportunity sampling and high in statified sampling.
Validity with regard to Experimental design repeated measures and indep groups and how to overcome. 2 points
Validity with regard to experimental design:
- Repeated measures, issue with order effects, overcome by counterbalancing.
- Independent groups, issue with participant variables, ovcome by random allocation.
Validity with regard to Quantitative methods, lab, field, and one general
Validity with regard to quantitative methods.
- Lab experiments: task, setting, participant awareness challenge validity. but high control.
- Field experiments: task and control challenge validity but more natural.
- Methods producing numerical data lack validity as they reduce behavior to a score.
Validity with regard to Qalitative methods, one point abt case studies and one general
Validity with regard to qualitative methods;
1. Case studies high validity as they give great insight into behaviour.
- Difficul to analyse qualitative data so it lacks validity.
Sampling: define Random Sampling
Random sampling uses a target population and means each person has an equal chance of selection using random generator/names in a hat etc.
Sampling: define Opportunity sampling
Opportunity sampling: Using the people that are available at the time.
Sampling: evaluate random sampling
Sampling, random sampling evaluation:
No bias as everyone has an equal chance of selection.
Takes time as need list of all members of the target population.
Sampling, evaluate Opportunity sampling
Sampling, opportunity sampling evaluation:
Quick and cheap as people already there
Only represents the population from which it was drawn.
Sampling: systematic sampling define
Sampling, systematic sampling is when selecting every nth person from the target population list.
Sampling: systematic sampling evaluation
Sampling, systematic sampling evaluation:
Avoids researcher bias
Risk of ending up a non representative sample.
Sampling: define Stratified sampling
Sampling, definition of stratisfied sampling:
Selecting particpants in proportion to frequency in target population.
Sampling: Stratified sampling evaluation
Sampling: Stratifiend sampling evaluation
- Most representative model
- Very time consuming
What is a correlation
A correlation shows how things are linked/associated.
Correlations: What do type of data do co-variables have to be.
Correlations: Co-variables are quantitative
Correlation: What is a scatter diagram
Graph plotting the correlation data. Dot placed where the result from each axis meet.
Correlation: name three types of correlation
Three types of correlation:
- Positive - as one variable increases the other increases.
- Negative - as one variable increases the other decreases.
- Zero - no relationship between variables.
Correlation: evaluation
Correlation, evaluation:
Strengths:
good starting point for research
Can be used to investigate curvilinear relationships so many uses.
Weakness:
Don’t show cause and effect.
No control of EV’s so conclusion may be wrong.
Interviews: three types
Interviews, types:
- structured, all q’s prepared
- unstructured, more like a conversation. may have general q’s prepared and creates new q’s as converation evolves.
- semi-structured (most in some interviews are like this) q’s predecided but follow up as the interview evolves.
Interviews: evaluation, two positive and two negative
Interviews evaluation:
Strength:
Produce a lot of information
Lots of insight gained into thoughts and feelings.
Weakness:
Data difficult to analyse
Some people may feel uncomfortable talking face to face.
Questionnaires: Two types of question and then 2 strengths and 2 weaknesses for questionnaires.
Questionnaires:
types of questions: Open / closed.
Strength:
Can gather lots of information from lots of people
easy to analyse closed questions
Weakness:
Social desirability bias
Questions may be leading to lack validity.
Experiments, 3 types
Types of experiment:
- Laboratory
- Field
- Natural
Laboratory Experiments: evaluation 2 strenths and 2 weaknesses
Laboratory experiments, evaluation:
Strength:
EV’s can be controlled
Standardised procedure so easy to replicate
Weakness:
Behaviour in a lab may be less normal so difficult to generalise
Participants may adapt behaviour because they know they are being watched.
Field experiment: evaluation, two strengths and two weaknesses.
Field experiment, evaluation
Strength:
More realistic than a lab because a natural environment.
Can use standardised procedures so some control.
Weakness:
May lose control of EV’s so difficult to prove cause and effect.
Ethical issues because participant may not be aware of the study.
Natural experiment: evaluation 2 strengths and 2 weaknesses
Natural experiment: evaluation
Strength:
May have high validity because of real-world variables.
can standardise procedure so some control over EV’s
Weakness:
Few opportunities to do this kind of research as behaviour may be rare.
May be EV’s because participants not randomly allocated to conditions.
Define Laboratory experiment
Laboratory experiment definition:
Takes place in a laboratory and experimenter has hight control over what happens.
Define Field experiment
Field experiment definition:
takes place in a natural setting.
IV manipulated by experimenter
Define Natural experiment
Natural experiment definition:
Takes place in a natural or lab setting.
IV is not changed by experimenter, it varies naturally.
Experimental design. Three types
Experimental design:
- independent groups
- repeated measures
- matched pairs
Experimental design: define Independent groups
Experimental design: Independent groups =
different group of participants for each level of IV
Min a control and an experimental group.
Experimental design: define Repeated measures
Experimental design: Repeated measures =
all participants take part in all levels of IV
Experimental design: define Matched pairs
Experimental design: Matched pairs =
participants tested on variables relevant to the study. They are then paired on the outcome so that each condition has a matched group.
Experimental design: Independent groups evaluation, one + and one -
Experimental design; Independent groups evaluation
Strength
Order effects are not a problem
Weakness
Different participants in each group so participant variables can as as an EV.
Experimental design: Repeated measures evaluation, two strenghts and one weakness
Experimental design: Repeated measures evaluation
Strength
No participant variables
Fewer participants so less expensive
Weakness:
Order effects reduce validity, eg practice.
Experimental design: Matched pairs evaluation, one strenght and two weaknesses
Expermimental design: Matched pairs evaluation
Strength
No order effects so few participant variables
Weakness
Takes time to match all participants
Doesn’t control all participant variables.
Experimental design. One way to deal with participant Variables in an independent groups design.
Allocation to conditions: Participants should be allocated using chance or a systematic method.
Experimental design: One way to deal with order effects in a repeated measures design.
Counterbalancing. Half of one group do one condition in one order that other half do the opposite order.
What is a case study:
A case study is an indepth investigation of an individual, group, even or institution.
What sort of data is collected from a case study and comment about the length of the study and how this helps the study.
Two attributes of a case study:
- Qualitative data, ie peoples experiences in words. Can included quantitative data such as IQ scores.
- Longitudinal. Seeing how behaviour changes over time. May also include retrospective case history.
Case study, evaluation, two positive and two negative
Case study evaluation:
Strength: research lacks a specific aim so researcher more open minded.
Best way to study rare behaviours.
Weakness:
Focus on one individual or event so results cannot be generalised.
Results subject to subjective interpretation.
What is an Observation and what is the diffierence between natural and controlled.
An observation is when a researcher watches or listens to participants and records data.
Natural observation is where the researcher just watches, nothing is changed.
Controlled observation is where the researcher manipulates aspects of the environment.
Observation, difference between Covert and Overts
Observation.
Covert is where participants are not aware that they are being studied.
Overt is where participants are aware they are being studied.
Observation, differerence between partipant versus non-participant
Observation,
Participant is where the researcher becomes part of the group.
Non participant, researcher remains separate.
Observation, what are catergories of behaviour
Observation. Catergories of behaviour is defining the target behaviour into separate, observable categories.
What is Interobserver reliability
Two researchers should product the same record of the behaviour. This can be check by comparing the data observed at the same time to make sure that it correlates.
Observation, evaluation, 2 strenghts and 2 weaknesses
Observation: Evaluation
strength;
Greater validity because it’s based on what people do.
Real life behaviour when people don’t know that they are being watched.
weakness:
Ethical concerns as can’t get participant consent when observing in a public place.
Observer bias may affect validity.
Quantitative data, evaluation, 2 points
Quantitative data, evaluation:
Easy to analyse and draw conclusions.
Lacks depth, not reflecting real world complexity.
Qualitative data, evaluation 2 points
Qualitative data, evaluation:
More depth and detail
difficult to analyse and summarise.
Primary data, evaluation two points.
Primary data, evaluation:
Suits aim of research so more useful
It takes time and effort to collect.
Secondary data, evaluation two points
Secondary data, evaluation:
Easy and convenient, saving expense
May not fit what the researcher is investigating.
Descriptive statistics. What is range
Descriptive statistics: Range
Spread of data.
Arrange highest to lowest and subtract lowest frm highest score.
Descriptive statistics: Range, evaluation 2 points
Descriptive statistics, Range, evaluation:
Easy to calculate
Can be distorted by extreme scores.
Descriptive statistics, what is Mean
Descriptive statistics, mean is a mathematical average
calculate by adding all the scores and then dividing by the number of scores.
Descriptive statistics, Mean: evaluation, 2 points
Descriptive statistics, Mean, evaluation:
Uses all data so most sensitive to measure
Can be distorted by extreme values
Descriptive statistics, what is Median
Descriptive statistics, Median is the middle value.
Data put in order from highest to lowest and middle number identified.
Descriptive statistics, Median, evaluation, 2 points.
Descriptive statistics, Median,evaluation:
not effected by extreme scores.
Less sensitive than the mean to variations in values.
Descriptive statistics, what is Mode
Descriptive statistics, Mode is the most common score(s).
Descriptive statistics: Mode,evaluation, 2 points
Descriptive statistics, Mode, evaluation:
Very easy to calculate
Can be unrepresentative.
Describe and explain a Scatter diagram
A scatter diagram is used to display correlation. a co-variable on x and y axis and a dot placed where the co-variables meet.
Describe and explain a frequency table.
A table showing the number of times an event occurs. Systematic to display data in rows and columns.
What is a Frequency diagram, describe the two types and define normal distribution.
Bar chart: can be in any order.
Histogram, continous categories, no spaces between bars.
Normal distribution: symmetrical spread forms a bell shape with mean,median and mode at peak.
What is standard form
Standard form is mathematical shorthand to represent very large or small numbers.
