Research Methods And Research Designs Flashcards
What is an independent groups design?
Participants are in separate/independent groups. Each group only takes part in one level of the IV. Compare the two groups to the same DV
What is a repeated measures design?
All participants participate in all IV levels, no groups
Compare all participants individually on both IV levels for the DV
What is a matched pairs design?
Match participants on key characteristic RELEVANT TO THE STUDY that seem to affect the outcome of the DV
- This pair is split up and allocated to group A and B, taking part in different levels of the IV
- continue in the same way as with independent groups
What are two limitations of repeated measures design?
. Order effect - order of levels of IV participated in May affect performance
. Demand characteristics - participants may guess the purpose of the experiment for the second test which may affect their behaviour.
How can you deal with the limitations of repeated measures designs?
. May use two different tests to reduce a practice effect
. Use counterbalancing to deal with order effects
. Use a cover story about the purpose of the test to avoid participants guessing the aims of a study, although this is deception
What are two limitations of the independent groups design?
. Participant variables (things about the participant) cannot be controlled (e.g characteristics/abilities of individual participants)
. Requires more participants than repeated measures to get the same amount of data as everyone only does one level of IV
How can you deal with the limitations of independent groups designs?
. Randomly allocate participants to the conditions which should distribute participant variables evenly
What are the limitations of the matched pairs design?
. Very time-consuming and hard to match participants on key variables effectively
. It is not possible to know everyone characteristic relevant to the study, so you can’t control all participant variables when other important characteristics are probably missed
How can you deal with the limitations of a matched pairs design?
. Restrict number of variables required to match to make it easier and less time-consuming
. Conduct a pilot study to re-consider key variable relevant to the study
Why is counterbalancing important?
It reduces the order effects in repeated measures designs as it ensures that each condition is tested first or second in equal amounts across the participants
What are the two ways to carry out counterbalancing?
Way 1: AB or BA
Way 2: ABBA
How does AB or BA method of counterbalancing work?
. Participants split into two equal groups
. Group 1: A then B
. Group 2: B then A
Still repeated measures as comparisons are made individually so the groups doesn’t matter and they are still taking part in both conditions
How does ABBA method of counterbalancing work?
. All participants take part in each condition twice in different orders
First time:
- condition A
- condition B
Second time:
- condition B
- condition A
Note that this is very time-consuming
What is an experimental design?
Type of procedure used to control factors such as participant variables that could affect an experiment’s results
What are the 3 guiding principles to writing good questionnaire questions?
- Clarity - unambiguous so the reader understands what is being asked
- Bias
- Analysis - generally want answers easy to analyse (closed questions)
Mnemonic: CAB
What else must be considered in good questionnaires?
- Filler questions: include some irrelevant questions to distract from the main purpose of the survey and reduce demand characteristics
- Sequencing of questions: start with easily digestible questions so overwhelming or potentially anxiety-inducing questions can be saved until the respondent is relaxed
- Sampling technique: how to select respondents
- Pilot study: questions can be refined in response to any difficulties encountered
What is the main difference between interviews and questionnaires?
Questionnaires are always structured but interviews can be structure or unstructured
What is a lab experiment?
An experiment containing an independent variable that is manipulated and a dependent variable that is measured, in a special environment where the independent vary can be controlled to exclude extraneous variables so that it doesn’t interfere with the dependent variables results
What is a field experiment?
An experiment conducted in a more ‘natural’ environment, where the IV is deliberately manipulated by the researcher and the researcher measures the DV (basically a lab experiment in a natural environment)
What is the main difference between a field and lab experiment?
. In a field experiment, the participant is usually not aware that they are participating in an experiment, so they would elicit more natural behaviour
. In a lab experiment, the participant is usually aware they are participating, so may alter their behaviour as a result of demand characteristics
Is Johnson and Scott’s weapon focus study a field or lab experiment?
Field as the actual behaviour being measured was natural (ability to identify the man that ran through the room) even though it seems like a controlled lab experiment on the surface
What is a natural experiment?
An experiment where the IV isn’t deliberately manipulated for practical/ethical reasons, so the IV is said to vary ‘naturally’ rather than deliberately. The DV may then be tested in a lab
Why are natural and quasi experiments not ‘true’ experiments?
The independent variable isn’t deliberately manipulated so it isn’t possible to establish cause and effect between DV and IV as you don’t know whether the changes in the dependent variable are directly caused by the IV
What is a quasi experiment?
When the IV is naturally occurring, just a difference between people that exists. The IV isn’t deliberately made to vary, it just does naturally. The DV may then be measured in a lab
How should you check for a quasi experiment in a stemmed question?
Identify the IV and DV, if the IV is naturally occurring and it wouldn’t make sense (would be unethical/impossible) to manipulate, it is a quasi experiment
What are demand characteristics and who invented the term?
A cue that makes participants unconsciously aware of the aims of a study or helps participants work out what the researcher expects to find, conveying the experimental hypothesis to participants. This will lead to a change in the natural behaviour of the participants as they will pay close attention to cues in an experiment to be as helpful as possible.
How is it a con that demand characteristics can alter the behaviour of participants?
This means the demand characteristics may act as an extraneous variable
What are investigator effects?
Any cues from an investigator/researcher that has an effect on a participants performance in a study other than what was intended, encouraging certain behaviours that may lead to an unnatural fulfilment of the investigator’s expectations. These cues act as extraneous or confounding variables
What are the strengths of lab experiments?
. Hold high internal bad lift as extraneous variables can be controlled
- this means we can be confident that any observed change in the DV is due to the manipulation of the IV only
What are the limitations of lab experiments?
. Participants usually aware that they are being studied so they may search for cues about the aims of the experiment and display demand characteristics, reducing ecological validity
. IV or DV may be operationalised in a way that doesn’t represent everyday experiences, leading to low ecological validity
. Participants may feel uncomfortable in an unknown and artificial environment, so may not display normal behaviour
What are the strengths of field experiments?
. Participants not likely to be aware that their behaviour is being studied, so won’t respond to demand characteristics as they won’t be searching for cues
. Field experiment takes place in natural setting = natural behaviour as participants may feel more comfortable in that environment
What are the limitations of field experiments?
. IV in a field experiment may lack mundane realism, meaning field experiments may not necessarily be more like everyday life than it seems compared to lab studies
. Difficult to control extraneous variables
. Difficult to debrief participants if they don’t know they are being studied
What are the main reasons that researchers can’t establish cause and effect from natural and quasi experiments?
. Lack of control over the IV means we can’t say for sure that any change in the DV was caused by the IV e.g there might be uncontrolled confounding variables
. If an independent groups design is used, it isn’t possible to randomly allocate to
What are the two types of investigator effects?
Direct investigator effects and indirect investigator effects
What are direct investigator effects and give examples?
When individuals change their behaviour due to unconscious encouragement directly from the investigator interacting with the participant e.g leading questions may encourage an investigator to give the answer the investigator wants
What are indirect investigator effects and give an example?
Investigator effects that occur as a consequence of the investigator designing the study e.g investigator may operationalise variables in a way that the desired result is more likely
What is the ‘investigator loose procedure effect’?
Situations when an investigator may not clearly specify the standardised instructions and/or standardised procedures, leaving room for the results to be influenced by the experimenter and leaving the results susceptible to investigator effects
How can we deal with demand characteristics and investigator effects?
- Single blind design
- Double blind design
- Experimental realism
What is a single blind design?
When the participants isn’t aware of the research aims and/or which condition of the experiment they are taking part in. This prevents them from seeking cues about the aims and changing their behaviour accordingly (reduces demand characteristics)
What is a double blind design?
When both the participants and investigator are ‘blind’ to the aims and/or hypotheses, meaning the investigator won’t unconsciously produce cues that the participants will react to (reduces demand characteristics and investigator effects)
