The variable that is manipulated by the researcher
Dependent variable
The variable that is measured
Extraneous variable
A variable (other than the IV) that might affect the DV
Confounding variable
A type of extraneous variable that you did not control for that does interact with the IV and affect the DV
Operationalisation of variables
Drawing out the most relevant elements of the variables so we can measure them
Demand characteristics-
The tendency of participants to work out how the experimenter expects them to behave and act accordingly
Investigator effects
The researcher exerting an influence, either consciously or unconsciously, on the outcome of the research
Laboratory experiment
Direct manipulation of an independent variable
High levels of control to control extraneous/confounding variables
Randomisation of participants and other factors
High levels of control in laboratory experiments
Increases internal validity but reduces ecological validity
Demand characteristics in laboratory experiments
Reduce internal validity as they mean the DV may not be a true reflection of behaviour
Field experiment
Carried out in the natural environment
Researcher still manipulates IV and measures DV
Attempts to control extraneous variables as much as possible
Field experiments
Have higher ecological validity but lower control over extraneous variables compared to laboratory experiments
Natural experiment
Takes advantage of naturally occurring events over which the researcher has no direct control over the IV
Participants are already assigned to a condition of the IV
Natural experiments
Have high ecological validity but limited opportunities to observe the desired behaviour and less control over extraneous variables
Quasi-experiment
Uses a pre-existing IV that does not vary, so participants are not randomly allocated to conditions
Repeated measures design
All participants take part in all levels of the IV and the results of the DV in both conditions are compared
Independent groups design
Participants are split so that different participants take part in different levels of the IV, and the results of the DV from each group are compared
Matched pairs design
Different participants are used in each level of the IV but they are matched as much as possible on key characteristics that are likely to influence the DV
Factors to consider in experimental designs
Order effects
Number of participants
Participant variables
Demand characteristics
Ways to deal with limitations of experimental designs
1. Counterbalancing to control order effects
2. Randomly allocating participants to conditions to distribute participant variables
3. Conducting a pilot study to identify key matching variables
4. Using independent groups to reduce demand characteristics
Interviews
Aim to gather information about what people (interviewees) know, feel and/or do about a particular topic
Provide a natural and flexible approach to questioning
Interview structure
1. Structured
2. Semi-structured
3. Unstructured
Structured interviews
Interviewees are asked the same set of standardised questions in the same order
Semi-structured interviews
Interviewer may use some of the same questions for all interviewees, but there is flexibility in the order, whether they are asked at all and, sometimes, in how questions are phrased
Unstructured interviews
More informal, the purposeful conversation about the topic of interest is allowed to unfold in its own way
Checklist for planning interviews
Have you stated the aim of the interview?
Have you clearly described the research question?
Have you generated an appropriate set of questions?
Have you planned the order in which the questions will be presented?
Have you planned the interview to obtain the required balance between structured and unstructured interviewing?
Have you identified and approached potential respondents?
Have you decided how the information is to be recorded in the interview?
Have you considered the ethical issues raised by the proposed research?
Have you considered your non-verbal communication and listening skills?
Strengths of interviews
May lead to more accurate data being gathered
May lead to more detailed data being gathered
Limitations of interviews
Can be hard to analyse
Interpersonal variables can affect the interaction between the interviewer and respondent
Correlation
Analysis of the relationship between co-variables
Correlation
Calculates a correlation coefficient, a statistic that has a value between -1 (perfect negative correlation) and +1 (perfect positive correlation)
Correlations are usually plotted onto a scatter plot so you can visually see whether the relationship is positive, negative or if there is zero correlation
Positive correlation
As one variable tends to increase, so does the other
Negative correlation
As one variable tends to increase, the other decreases
Zero correlation
Shows no relationship between the two variables
Experiment
The experimenter deliberately manipulates the impact each condition/level of the IV has on the DV
Correlation
No deliberate change is made to any variable, the impact of one variable on another is not being tested, just the relationship between co-variables
Strengths of correlations
Can indicate the direction and strength of the relationship between two variables
Allow researchers to statistically analyse situations that could not be manipulated experimentally for ethical or practical reasons
Limitations of correlations
Do not establish cause and effect, only a relationship between two variables
Cannot measure non-linear relationships
Pilot study
A small scale study, carried out with a restricted number of participants who will not take part in the study itself, before the process of collecting data begins
Issues to be identified in a pilot study
Experiments: Confounding/extraneous variables, whether materials used are suitable, whether timings are appropriate, whether standardised instructions are clear
Observations: Whether behavioural categories are clear and unambiguous, whether timing and CCTV are correct, whether sampling technique is appropriate
Interviews: Whether extraneous variables are controlled, whether questions are clear and understandable, whether recording methods are suitable, quality of the interviewer, structure of the interview
Benefits of a pilot study
Increase validity - measuring what you set out to measure
Increase reliability - ensuring the data is recorded in the same way